Merge branch 'master' into api-add-missing-map

Co-authored-by: Pepe Fagoaga <pepe@prowler.com>

.env

@@ -4,13 +4,16 @@
 
 #### Prowler UI Configuration ####
 PROWLER_UI_VERSION="stable"
-SITE_URL=http://localhost:3000
+AUTH_URL=http://localhost:3000
 API_BASE_URL=http://prowler-api:8080/api/v1
 NEXT_PUBLIC_API_DOCS_URL=http://prowler-api:8080/api/v1/docs
 AUTH_TRUST_HOST=true
 UI_PORT=3000
 # openssl rand -base64 32
 AUTH_SECRET="N/c6mnaS5+SWq81+819OrzQZlmx1Vxtp/orjttJSmw8="
+# Google Tag Manager ID
+NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID=""
+
 
 #### Prowler API Configuration ####
 PROWLER_API_VERSION="stable"
@@ -24,6 +27,10 @@ POSTGRES_USER=prowler
 POSTGRES_PASSWORD=postgres
 POSTGRES_DB=prowler_db
 
+# Celery-Prowler task settings
+TASK_RETRY_DELAY_SECONDS=0.1
+TASK_RETRY_ATTEMPTS=5
+
 # Valkey settings
 # If running Valkey and celery on host, use localhost, else use 'valkey'
 VALKEY_HOST=valkey
@@ -33,10 +40,10 @@ VALKEY_DB=0
 # API scan settings
 
 # The path to the directory where scan output should be stored
-DJANGO_TMP_OUTPUT_DIRECTORY = "/tmp/prowler_api_output"
+DJANGO_TMP_OUTPUT_DIRECTORY="/tmp/prowler_api_output"
 
 # The maximum number of findings to process in a single batch
-DJANGO_FINDINGS_BATCH_SIZE = 1000
+DJANGO_FINDINGS_BATCH_SIZE=1000
 
 # The AWS access key to be used when uploading scan output to an S3 bucket
 # If left empty, default AWS credentials resolution behavior will be used
@@ -123,4 +130,23 @@ SENTRY_ENVIRONMENT=local
 SENTRY_RELEASE=local
 
 #### Prowler release version ####
-NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.5.0
+NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.6.0
+
+# Social login credentials
+SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
+SOCIAL_GOOGLE_OAUTH_CLIENT_ID=""
+SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET=""
+
+SOCIAL_GITHUB_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/github"
+SOCIAL_GITHUB_OAUTH_CLIENT_ID=""
+SOCIAL_GITHUB_OAUTH_CLIENT_SECRET=""
+
+# Single Sign-On (SSO)
+SAML_PUBLIC_CERT=""
+SAML_PRIVATE_KEY=""
+
+# Lighthouse tracing
+LANGSMITH_TRACING=false
+LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
+LANGSMITH_API_KEY=""
+LANGCHAIN_PROJECT=""

.github/dependabot.yml

@@ -9,108 +9,112 @@ updates:
   - package-ecosystem: "pip"
     directory: "/"
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
+      interval: "monthly"
+    open-pull-requests-limit: 25
     target-branch: master
     labels:
       - "dependencies"
       - "pip"
 
-  - package-ecosystem: "pip"
-    directory: "/api"
-    schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
-    target-branch: master
-    labels:
-      - "dependencies"
-      - "pip"
-      - "component/api"
+  # Dependabot Updates are temporary disabled - 2025/03/19
+  # - package-ecosystem: "pip"
+  #   directory: "/api"
+  #   schedule:
+  #     interval: "daily"
+  #   open-pull-requests-limit: 10
+  #   target-branch: master
+  #   labels:
+  #     - "dependencies"
+  #     - "pip"
+  #     - "component/api"
 
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
+      interval: "monthly"
+    open-pull-requests-limit: 25
     target-branch: master
     labels:
       - "dependencies"
       - "github_actions"
 
-  - package-ecosystem: "npm"
-    directory: "/ui"
-    schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
-    target-branch: master
-    labels:
-      - "dependencies"
-      - "npm"
-      - "component/ui"
+  # Dependabot Updates are temporary disabled - 2025/03/19
+  # - package-ecosystem: "npm"
+  #   directory: "/ui"
+  #   schedule:
+  #     interval: "daily"
+  #   open-pull-requests-limit: 10
+  #   target-branch: master
+  #   labels:
+  #     - "dependencies"
+  #     - "npm"
+  #     - "component/ui"
 
   - package-ecosystem: "docker"
     directory: "/"
     schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 10
+      interval: "monthly"
+    open-pull-requests-limit: 25
     target-branch: master
     labels:
       - "dependencies"
       - "docker"
 
+  # Dependabot Updates are temporary disabled - 2025/04/15
   # v4.6
-  - package-ecosystem: "pip"
-    directory: "/"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 10
-    target-branch: v4.6
-    labels:
-      - "dependencies"
-      - "pip"
-      - "v4"
+  # - package-ecosystem: "pip"
+  #   directory: "/"
+  #   schedule:
+  #     interval: "weekly"
+  #   open-pull-requests-limit: 10
+  #   target-branch: v4.6
+  #   labels:
+  #     - "dependencies"
+  #     - "pip"
+  #     - "v4"
 
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 10
-    target-branch: v4.6
-    labels:
-      - "dependencies"
-      - "github_actions"
-      - "v4"
+  # - package-ecosystem: "github-actions"
+  #   directory: "/"
+  #   schedule:
+  #     interval: "weekly"
+  #   open-pull-requests-limit: 10
+  #   target-branch: v4.6
+  #   labels:
+  #     - "dependencies"
+  #     - "github_actions"
+  #     - "v4"
 
-  - package-ecosystem: "docker"
-    directory: "/"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 10
-    target-branch: v4.6
-    labels:
-      - "dependencies"
-      - "docker"
-      - "v4"
+  # - package-ecosystem: "docker"
+  #   directory: "/"
+  #   schedule:
+  #     interval: "weekly"
+  #   open-pull-requests-limit: 10
+  #   target-branch: v4.6
+  #   labels:
+  #     - "dependencies"
+  #     - "docker"
+  #     - "v4"
 
+  # Dependabot Updates are temporary disabled - 2025/03/19
   # v3
-  - package-ecosystem: "pip"
-    directory: "/"
-    schedule:
-      interval: "monthly"
-    open-pull-requests-limit: 10
-    target-branch: v3
-    labels:
-      - "dependencies"
-      - "pip"
-      - "v3"
+  # - package-ecosystem: "pip"
+  #   directory: "/"
+  #   schedule:
+  #     interval: "monthly"
+  #   open-pull-requests-limit: 10
+  #   target-branch: v3
+  #   labels:
+  #     - "dependencies"
+  #     - "pip"
+  #     - "v3"
 
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "monthly"
-    open-pull-requests-limit: 10
-    target-branch: v3
-    labels:
-      - "dependencies"
-      - "github_actions"
-      - "v3"
+  # - package-ecosystem: "github-actions"
+  #   directory: "/"
+  #   schedule:
+  #     interval: "monthly"
+  #   open-pull-requests-limit: 10
+  #   target-branch: v3
+  #   labels:
+  #     - "dependencies"
+  #     - "github_actions"
+  #     - "v3"

.github/labeler.yml

@@ -27,6 +27,11 @@ provider/github:
       - any-glob-to-any-file: "prowler/providers/github/**"
       - any-glob-to-any-file: "tests/providers/github/**"
 
+provider/iac:
+  - changed-files:
+      - any-glob-to-any-file: "prowler/providers/iac/**"
+      - any-glob-to-any-file: "tests/providers/iac/**"
+
 github_actions:
   - changed-files:
       - any-glob-to-any-file: ".github/workflows/*"

.github/pull_request_template.md

@@ -16,6 +16,7 @@ Please include a summary of the change and which issue is fixed. List any depend
 - [ ] Review if code is being documented following this specification https://github.com/google/styleguide/blob/gh-pages/pyguide.md#38-comments-and-docstrings
 - [ ] Review if backport is needed.
 - [ ] Review if is needed to change the [Readme.md](https://github.com/prowler-cloud/prowler/blob/master/README.md)
+- [ ] Ensure new entries are added to [CHANGELOG.md](https://github.com/prowler-cloud/prowler/blob/master/prowler/CHANGELOG.md), if applicable.
 
 #### API
 - [ ] Verify if API specs need to be regenerated.

.github/workflows/api-build-lint-push-containers.yml

@@ -61,7 +61,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Set short git commit SHA
         id: vars
@@ -70,18 +70,18 @@ jobs:
           echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           # Set push: false for testing
@@ -94,7 +94,7 @@ jobs:
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           push: true
@@ -106,7 +106,7 @@ jobs:
 
       - name: Trigger deployment
         if: github.event_name == 'push'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
         with:
           token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
           repository: ${{ secrets.CLOUD_DISPATCH }}

.github/workflows/api-codeql.yml

@@ -44,16 +44,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/api-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/api-pull-request.yml

@@ -28,6 +28,10 @@ env:
   VALKEY_DB: 0
   API_WORKING_DIR: ./api
   IMAGE_NAME: prowler-api
+  IGNORE_FILES: |
+    api/docs/**
+    api/README.md
+    api/CHANGELOG.md
 
 jobs:
   test:
@@ -71,19 +75,22 @@ jobs:
           --health-retries 5
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@v45
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files: api/**
-          files_ignore: |
-            api/.github/**
-            api/docs/**
-            api/permissions/**
-            api/README.md
-            api/mkdocs.yml
+          files_ignore: ${{ env.IGNORE_FILES }}
+
+      - name: Replace @master with current branch in pyproject.toml
+        working-directory: ./api
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          BRANCH_NAME="${GITHUB_HEAD_REF:-${GITHUB_REF_NAME}}"
+          echo "Using branch: $BRANCH_NAME"
+          sed -i "s|@master|@$BRANCH_NAME|g" pyproject.toml
 
       - name: Install poetry
         working-directory: ./api
@@ -92,13 +99,25 @@ jobs:
           python -m pip install --upgrade pip
           pipx install poetry==2.1.1
 
+      - name: Update poetry.lock after the branch name change
+        working-directory: ./api
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          poetry lock
+
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
 
+      - name: Install system dependencies for xmlsec
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libxml2-dev libxmlsec1-dev libxmlsec1-openssl pkg-config
+
       - name: Install dependencies
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -117,6 +136,12 @@ jobs:
         run: |
           poetry check --lock
 
+      - name: Prevents known compatibility error between lxml and libxml2/libxmlsec versions - https://github.com/xmlsec/python-xmlsec/issues/320
+        working-directory: ./api
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          poetry run pip install --force-reinstall --no-binary lxml lxml
+
       - name: Lint with ruff
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -144,8 +169,9 @@ jobs:
       - name: Safety
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        # 76352 and 76353 come from SDK, but they cannot upgrade it yet. It does not affect API
         run: |
-          poetry run safety check --ignore 70612,66963
+          poetry run safety check --ignore 70612,66963,74429,76352,76353
 
       - name: Vulture
         working-directory: ./api
@@ -167,7 +193,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
@@ -175,11 +201,20 @@ jobs:
   test-container-build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Test if changes are in not ignored paths
+        id: are-non-ignored-files-changed
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: api/**
+          files_ignore: ${{ env.IGNORE_FILES }}
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
       - name: Build Container
-        uses: docker/build-push-action@v6
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.API_WORKING_DIR }}
           push: false

.github/workflows/backport.yml

@@ -23,7 +23,7 @@ jobs:
     steps:
       - name: Check labels
         id: preview_label_check
-        uses: docker://agilepathway/pull-request-label-checker:v1.6.55
+        uses: agilepathway/label-checker@c3d16ad512e7cea5961df85ff2486bb774caf3c5 # v1.6.65
         with:
           allow_failure: true
           prefix_mode: true
@@ -33,7 +33,7 @@ jobs:
 
       - name: Backport Action
         if: steps.preview_label_check.outputs.label_check == 'success'
-        uses: sorenlouv/backport-github-action@v9.5.1
+        uses: sorenlouv/backport-github-action@ad888e978060bc1b2798690dd9d03c4036560947 # v9.5.1
         with:
           github_token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
           auto_backport_label_prefix: ${{ env.BACKPORT_LABEL_PREFIX }}

.github/workflows/build-documentation-on-pr.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Leave PR comment with the Prowler Documentation URI
-        uses: peter-evans/create-or-update-comment@v4
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
         with:
           issue-number: ${{ env.PR_NUMBER }}
           body: |

.github/workflows/conventional-commit.yml

@@ -18,6 +18,6 @@ jobs:
     steps:
       - name: conventional-commit-check
         id: conventional-commit-check
-        uses: agenthunt/conventional-commit-checker-action@v2.0.0
+        uses: agenthunt/conventional-commit-checker-action@9e552d650d0e205553ec7792d447929fc78e012b # v2.0.0
         with:
             pr-title-regex: '^([^\s(]+)(?:\(([^)]+)\))?: (.+)'

.github/workflows/create-backport-label.yml

@@ -0,0 +1,67 @@
+name: Create Backport Label
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  create_label:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      issues: write
+    steps:
+      - name: Create backport label
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          RELEASE_TAG: ${{ github.event.release.tag_name }}
+          OWNER_REPO: ${{ github.repository }}
+        run: |
+          VERSION_ONLY=${RELEASE_TAG#v} # Remove 'v' prefix if present (e.g., v3.2.0 -> 3.2.0)
+
+          # Check if it's a minor version (X.Y.0)
+          if [[ "$VERSION_ONLY" =~ ^[0-9]+\.[0-9]+\.0$ ]]; then
+            echo "Release ${RELEASE_TAG} (version ${VERSION_ONLY}) is a minor version. Proceeding to create backport label."
+
+            TWO_DIGIT_VERSION=${VERSION_ONLY%.0} # Extract X.Y from X.Y.0 (e.g., 5.6 from 5.6.0)
+
+            FINAL_LABEL_NAME="backport-to-v${TWO_DIGIT_VERSION}"
+            FINAL_DESCRIPTION="Backport PR to the v${TWO_DIGIT_VERSION} branch"
+
+            echo "Effective label name will be: ${FINAL_LABEL_NAME}"
+            echo "Effective description will be: ${FINAL_DESCRIPTION}"
+
+            # Check if the label already exists
+            STATUS_CODE=$(curl -s -o /dev/null -w "%{http_code}" -H "Authorization: token ${GITHUB_TOKEN}" "https://api.github.com/repos/${OWNER_REPO}/labels/${FINAL_LABEL_NAME}")
+
+            if [ "${STATUS_CODE}" -eq 200 ]; then
+              echo "Label '${FINAL_LABEL_NAME}' already exists."
+            elif [ "${STATUS_CODE}" -eq 404 ]; then
+              echo "Label '${FINAL_LABEL_NAME}' does not exist. Creating it..."
+              # Prepare JSON data payload
+              JSON_DATA=$(printf '{"name":"%s","description":"%s","color":"B60205"}' "${FINAL_LABEL_NAME}" "${FINAL_DESCRIPTION}")
+
+              CREATE_STATUS_CODE=$(curl -s -o /tmp/curl_create_response.json -w "%{http_code}" -X POST \
+              -H "Accept: application/vnd.github.v3+json" \
+              -H "Authorization: token ${GITHUB_TOKEN}" \
+              --data "${JSON_DATA}" \
+              "https://api.github.com/repos/${OWNER_REPO}/labels")
+
+              CREATE_RESPONSE_BODY=$(cat /tmp/curl_create_response.json)
+              rm -f /tmp/curl_create_response.json
+
+              if [ "$CREATE_STATUS_CODE" -eq 201 ]; then
+                echo "Label '${FINAL_LABEL_NAME}' created successfully."
+              else
+                echo "Error creating label '${FINAL_LABEL_NAME}'. Status: $CREATE_STATUS_CODE"
+                echo "Response: $CREATE_RESPONSE_BODY"
+                exit 1
+              fi
+            else
+              echo "Error checking for label '${FINAL_LABEL_NAME}'. HTTP Status: ${STATUS_CODE}"
+              exit 1
+            fi
+          else
+            echo "Release ${RELEASE_TAG} (version ${VERSION_ONLY}) is not a minor version. Skipping backport label creation."
+            exit 0
+          fi

.github/workflows/find-secrets.yml

@@ -7,11 +7,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
       - name: TruffleHog OSS
-        uses: trufflesecurity/trufflehog@v3.88.16
+        uses: trufflesecurity/trufflehog@90694bf9af66e7536abc5824e7a87246dbf933cb # v3.88.35
         with:
           path: ./
           base: ${{ github.event.repository.default_branch }}

.github/workflows/labeler.yml

@@ -14,4 +14,4 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/labeler@v5
+    - uses: actions/labeler@8558fd74291d67161a8a78ce36a881fa63b766a9 # v5.0.0

.github/workflows/pull-request-check-changelog.yml

@@ -0,0 +1,83 @@
+name: Check Changelog
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, labeled, unlabeled]
+
+jobs:
+  check-changelog:
+    if: contains(github.event.pull_request.labels.*.name, 'no-changelog') == false
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    env:
+      MONITORED_FOLDERS: "api ui prowler"
+
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+
+      - name: Get list of changed files
+        id: changed_files
+        run: |
+          git fetch origin ${{ github.base_ref }}
+          git diff --name-only origin/${{ github.base_ref }}...HEAD > changed_files.txt
+          cat changed_files.txt
+
+      - name: Check for folder changes and changelog presence
+        id: check_folders
+        run: |
+          missing_changelogs=""
+
+          for folder in $MONITORED_FOLDERS; do
+            if grep -q "^${folder}/" changed_files.txt; then
+              echo "Detected changes in ${folder}/"
+              if ! grep -q "^${folder}/CHANGELOG.md$" changed_files.txt; then
+                echo "No changelog update found for ${folder}/"
+                missing_changelogs="${missing_changelogs}- \`${folder}\`\n"
+              fi
+            fi
+          done
+
+          echo "missing_changelogs<<EOF" >> $GITHUB_OUTPUT
+          echo -e "${missing_changelogs}" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
+
+      - name: Find existing changelog comment
+        id: find_comment
+        uses: peter-evans/find-comment@3eae4d37986fb5a8592848f6a574fdf654e61f9e #v3.1.0
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          comment-author: 'github-actions[bot]'
+          body-includes: '<!-- changelog-check -->'
+
+      - name: Comment on PR if changelog is missing
+        if: steps.check_folders.outputs.missing_changelogs != ''
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          comment-id: ${{ steps.find_comment.outputs.comment-id }}
+          body: |
+            <!-- changelog-check -->
+            ⚠️ **Changes detected in the following folders without a corresponding update to the `CHANGELOG.md`:**
+
+            ${{ steps.check_folders.outputs.missing_changelogs }}
+
+            Please add an entry to the corresponding `CHANGELOG.md` file to maintain a clear history of changes.
+
+      - name: Comment on PR if all changelogs are present
+        if: steps.check_folders.outputs.missing_changelogs == ''
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          comment-id: ${{ steps.find_comment.outputs.comment-id }}
+          body: |
+            <!-- changelog-check -->
+            ✅ All necessary `CHANGELOG.md` files have been updated. Great job! 🎉
+
+      - name: Fail if changelog is missing
+        if: steps.check_folders.outputs.missing_changelogs != ''
+        run: |
+          echo "ERROR: Missing changelog updates in some folders."
+          exit 1

.github/workflows/pull-request-merged.yml

@@ -0,0 +1,37 @@
+name: Prowler - Merged Pull Request
+
+on:
+  pull_request_target:
+    branches: ['master']
+    types: ['closed']
+
+jobs:
+  trigger-cloud-pull-request:
+    name: Trigger Cloud Pull Request
+    if: github.event.pull_request.merged == true && github.repository == 'prowler-cloud/prowler'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          ref: ${{ github.event.pull_request.merge_commit_sha }}
+
+      - name: Set short git commit SHA
+        id: vars
+        run: |
+          shortSha=$(git rev-parse --short ${{ github.event.pull_request.merge_commit_sha }})
+          echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
+
+      - name: Trigger pull request
+        uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
+        with:
+          token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+          repository: ${{ secrets.CLOUD_DISPATCH }}
+          event-type: prowler-pull-request-merged
+          client-payload: '{
+            "PROWLER_COMMIT_SHA": "${{ github.event.pull_request.merge_commit_sha }}",
+            "PROWLER_COMMIT_SHORT_SHA": "${{ env.SHORT_SHA }}",
+            "PROWLER_PR_TITLE": "${{ github.event.pull_request.title }}",
+            "PROWLER_PR_LABELS": ${{ toJson(github.event.pull_request.labels.*.name) }},
+            "PROWLER_PR_BODY": ${{ toJson(github.event.pull_request.body) }},
+            "PROWLER_PR_URL":${{ toJson(github.event.pull_request.html_url) }}
+          }'

.github/workflows/sdk-build-lint-push-containers.yml

@@ -59,16 +59,16 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Install Poetry
         run: |
-          pipx install poetry==1.8.5
+          pipx install poetry==2.*
           pipx inject poetry poetry-bumpversion
 
       - name: Get Prowler version
@@ -108,13 +108,13 @@ jobs:
           esac
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Login to Public ECR
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           registry: public.ecr.aws
           username: ${{ secrets.PUBLIC_ECR_AWS_ACCESS_KEY_ID }}
@@ -123,11 +123,11 @@ jobs:
           AWS_REGION: ${{ env.AWS_REGION }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           push: true
           tags: |
@@ -140,7 +140,7 @@ jobs:
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           # Use local context to get changes
           # https://github.com/docker/build-push-action#path-context

.github/workflows/sdk-bump-version.yml

@@ -0,0 +1,145 @@
+name: SDK - Bump Version
+
+on:
+  release:
+    types: [published]
+
+
+env:
+  PROWLER_VERSION: ${{ github.event.release.tag_name }}
+  BASE_BRANCH: master
+
+jobs:
+  bump-version:
+    name: Bump Version
+    if: github.repository == 'prowler-cloud/prowler'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Get Prowler version
+        shell: bash
+        run: |
+          if [[ $PROWLER_VERSION =~ ^([0-9]+)\.([0-9]+)\.([0-9]+)$ ]]; then
+            MAJOR_VERSION=${BASH_REMATCH[1]}
+            MINOR_VERSION=${BASH_REMATCH[2]}
+            FIX_VERSION=${BASH_REMATCH[3]}
+
+            # Export version components to GitHub environment
+            echo "MAJOR_VERSION=${MAJOR_VERSION}" >> "${GITHUB_ENV}"
+            echo "MINOR_VERSION=${MINOR_VERSION}" >> "${GITHUB_ENV}"
+            echo "FIX_VERSION=${FIX_VERSION}" >> "${GITHUB_ENV}"
+
+            if (( MAJOR_VERSION == 5 )); then
+                if (( FIX_VERSION == 0 )); then
+                  echo "Minor Release: $PROWLER_VERSION"
+
+                  # Set up next minor version for master
+                  BUMP_VERSION_TO=${MAJOR_VERSION}.$((MINOR_VERSION + 1)).${FIX_VERSION}
+                  echo "BUMP_VERSION_TO=${BUMP_VERSION_TO}" >> "${GITHUB_ENV}"
+
+                  TARGET_BRANCH=${BASE_BRANCH}
+                  echo "TARGET_BRANCH=${TARGET_BRANCH}" >> "${GITHUB_ENV}"
+
+                  # Set up patch version for version branch
+                  PATCH_VERSION_TO=${MAJOR_VERSION}.${MINOR_VERSION}.1
+                  echo "PATCH_VERSION_TO=${PATCH_VERSION_TO}" >> "${GITHUB_ENV}"
+
+                  VERSION_BRANCH=v${MAJOR_VERSION}.${MINOR_VERSION}
+                  echo "VERSION_BRANCH=${VERSION_BRANCH}" >> "${GITHUB_ENV}"
+
+                  echo "Bumping to next minor version: ${BUMP_VERSION_TO} in branch ${TARGET_BRANCH}"
+                  echo "Bumping to next patch version: ${PATCH_VERSION_TO} in branch ${VERSION_BRANCH}"
+                else
+                  echo "Patch Release: $PROWLER_VERSION"
+
+                  BUMP_VERSION_TO=${MAJOR_VERSION}.${MINOR_VERSION}.$((FIX_VERSION + 1))
+                  echo "BUMP_VERSION_TO=${BUMP_VERSION_TO}" >> "${GITHUB_ENV}"
+
+                  TARGET_BRANCH=v${MAJOR_VERSION}.${MINOR_VERSION}
+                  echo "TARGET_BRANCH=${TARGET_BRANCH}" >> "${GITHUB_ENV}"
+
+                  echo "Bumping to next patch version: ${BUMP_VERSION_TO} in branch ${TARGET_BRANCH}"
+                fi
+            else
+                echo "Releasing another Prowler major version, aborting..."
+                exit 1
+            fi
+          else
+            echo "Invalid version syntax: '$PROWLER_VERSION' (must be N.N.N)" >&2
+            exit 1
+          fi
+
+      - name: Bump versions in files
+        run: |
+            echo "Using PROWLER_VERSION=$PROWLER_VERSION"
+            echo "Using BUMP_VERSION_TO=$BUMP_VERSION_TO"
+
+            set -e
+
+            echo "Bumping version in pyproject.toml ..."
+            sed -i "s|version = \"${PROWLER_VERSION}\"|version = \"${BUMP_VERSION_TO}\"|" pyproject.toml
+
+            echo "Bumping version in prowler/config/config.py ..."
+            sed -i "s|prowler_version = \"${PROWLER_VERSION}\"|prowler_version = \"${BUMP_VERSION_TO}\"|" prowler/config/config.py
+
+            echo "Bumping version in .env ..."
+            sed -i "s|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${PROWLER_VERSION}|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${BUMP_VERSION_TO}|" .env
+
+            git --no-pager diff
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
+        with:
+            author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
+            token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+            base: ${{ env.TARGET_BRANCH }}
+            commit-message: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
+            branch: "version-bump-to-v${{ env.BUMP_VERSION_TO }}"
+            title: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
+            body: |
+              ### Description
+
+              Bump Prowler version to v${{ env.BUMP_VERSION_TO }}
+
+              ### License
+
+              By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
+
+      - name: Handle patch version for minor release
+        if: env.FIX_VERSION == '0'
+        run: |
+            echo "Using PROWLER_VERSION=$PROWLER_VERSION"
+            echo "Using PATCH_VERSION_TO=$PATCH_VERSION_TO"
+
+            set -e
+
+            echo "Bumping version in pyproject.toml ..."
+            sed -i "s|version = \"${PROWLER_VERSION}\"|version = \"${PATCH_VERSION_TO}\"|" pyproject.toml
+
+            echo "Bumping version in prowler/config/config.py ..."
+            sed -i "s|prowler_version = \"${PROWLER_VERSION}\"|prowler_version = \"${PATCH_VERSION_TO}\"|" prowler/config/config.py
+
+            echo "Bumping version in .env ..."
+            sed -i "s|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${PROWLER_VERSION}|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${PATCH_VERSION_TO}|" .env
+
+            git --no-pager diff
+
+      - name: Create Pull Request for patch version
+        if: env.FIX_VERSION == '0'
+        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
+        with:
+            author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
+            token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+            base: ${{ env.VERSION_BRANCH }}
+            commit-message: "chore(release): Bump version to v${{ env.PATCH_VERSION_TO }}"
+            branch: "version-bump-to-v${{ env.PATCH_VERSION_TO }}"
+            title: "chore(release): Bump version to v${{ env.PATCH_VERSION_TO }}"
+            body: |
+              ### Description
+
+              Bump Prowler version to v${{ env.PATCH_VERSION_TO }}
+
+              ### License
+
+              By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

.github/workflows/sdk-codeql.yml

@@ -21,6 +21,7 @@ on:
     paths-ignore:
       - 'ui/**'
       - 'api/**'
+      - '.github/**'
   pull_request:
     branches:
       - "master"
@@ -30,6 +31,7 @@ on:
     paths-ignore:
       - 'ui/**'
       - 'api/**'
+      - '.github/**'
   schedule:
     - cron: '00 12 * * *'
 
@@ -50,16 +52,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/sdk-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/sdk-pull-request.yml

@@ -21,11 +21,11 @@ jobs:
         python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@v45
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files: ./**
           files_ignore: |
@@ -34,6 +34,7 @@ jobs:
             permissions/**
             api/**
             ui/**
+            prowler/CHANGELOG.md
             README.md
             mkdocs.yml
             .backportrc.json
@@ -50,7 +51,7 @@ jobs:
 
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
@@ -106,15 +107,143 @@ jobs:
         run: |
           /tmp/hadolint Dockerfile --ignore=DL3013
 
-      - name: Test with pytest
+      # Test AWS
+      - name: AWS - Check if any file has changed
+        id: aws-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/aws/**
+            ./tests/providers/aws/**
+            .poetry.lock
+
+      - name: AWS - Test
+        if: steps.aws-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/aws --cov-report=xml:aws_coverage.xml tests/providers/aws
+
+      # Test Azure
+      - name: Azure - Check if any file has changed
+        id: azure-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/azure/**
+            ./tests/providers/azure/**
+            .poetry.lock
+
+      - name: Azure - Test
+        if: steps.azure-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/azure --cov-report=xml:azure_coverage.xml tests/providers/azure
+
+      # Test GCP
+      - name: GCP - Check if any file has changed
+        id: gcp-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/gcp/**
+            ./tests/providers/gcp/**
+            .poetry.lock
+
+      - name: GCP - Test
+        if: steps.gcp-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/gcp --cov-report=xml:gcp_coverage.xml tests/providers/gcp
+
+      # Test Kubernetes
+      - name: Kubernetes - Check if any file has changed
+        id: kubernetes-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/kubernetes/**
+            ./tests/providers/kubernetes/**
+            .poetry.lock
+
+      - name: Kubernetes - Test
+        if: steps.kubernetes-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/kubernetes --cov-report=xml:kubernetes_coverage.xml tests/providers/kubernetes
+
+      # Test GitHub
+      - name: GitHub - Check if any file has changed
+        id: github-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/github/**
+            ./tests/providers/github/**
+            .poetry.lock
+
+      - name: GitHub - Test
+        if: steps.github-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/github --cov-report=xml:github_coverage.xml tests/providers/github
+
+      # Test NHN
+      - name: NHN - Check if any file has changed
+        id: nhn-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/nhn/**
+            ./tests/providers/nhn/**
+            .poetry.lock
+
+      - name: NHN - Test
+        if: steps.nhn-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/nhn --cov-report=xml:nhn_coverage.xml tests/providers/nhn
+
+      # Test M365
+      - name: M365 - Check if any file has changed
+        id: m365-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/m365/**
+            ./tests/providers/m365/**
+            .poetry.lock
+
+      - name: M365 - Test
+        if: steps.m365-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/m365 --cov-report=xml:m365_coverage.xml tests/providers/m365
+
+      # Test IaC
+      - name: IaC - Check if any file has changed
+        id: iac-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/iac/**
+            ./tests/providers/iac/**
+            .poetry.lock
+
+      - name: IaC - Test
+        if: steps.iac-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/iac --cov-report=xml:iac_coverage.xml tests/providers/iac
+
+      # Common Tests
+      - name: Lib - Test
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
-          poetry run pytest -n auto --cov=./prowler --cov-report=xml tests
+          poetry run pytest -n auto --cov=./prowler/lib --cov-report=xml:lib_coverage.xml tests/lib
 
+      - name: Config - Test
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/config --cov-report=xml:config_coverage.xml tests/config
+
+      # Codecov
       - name: Upload coverage reports to Codecov
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           flags: prowler
+          files: ./aws_coverage.xml,./azure_coverage.xml,./gcp_coverage.xml,./kubernetes_coverage.xml,./github_coverage.xml,./nhn_coverage.xml,./m365_coverage.xml,./lib_coverage.xml,./config_coverage.xml

.github/workflows/sdk-pypi-release.yml

@@ -7,7 +7,7 @@ on:
 env:
   RELEASE_TAG: ${{ github.event.release.tag_name }}
   PYTHON_VERSION: 3.11
-  CACHE: "poetry"
+  # CACHE: "poetry"
 
 jobs:
   repository-check:
@@ -64,17 +64,17 @@ jobs:
               ;;
           esac
 
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Install dependencies
         run: |
-          pipx install poetry==1.8.5
+          pipx install poetry==2.1.1
 
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          cache: ${{ env.CACHE }}
+          # cache: ${{ env.CACHE }}
 
       - name: Build Prowler package
         run: |

.github/workflows/sdk-refresh-aws-services-regions.yml

@@ -4,7 +4,7 @@ name: SDK - Refresh AWS services' regions
 
 on:
   schedule:
-    - cron: "0 9 * * *" #runs at 09:00 UTC everyday
+    - cron: "0 9 * * 1" # runs at 09:00 UTC every Monday
 
 env:
   GITHUB_BRANCH: "master"
@@ -23,12 +23,12 @@ jobs:
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
       # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           ref: ${{ env.GITHUB_BRANCH }}
 
       - name: setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: 3.9 #install the python needed
 
@@ -38,7 +38,7 @@ jobs:
           pip install boto3
 
       - name: Configure AWS Credentials -- DEV
-        uses: aws-actions/configure-aws-credentials@v4
+        uses: aws-actions/configure-aws-credentials@b47578312673ae6fa5b5096b330d9fbac3d116df # v4.2.1
         with:
           aws-region: ${{ env.AWS_REGION_DEV }}
           role-to-assume: ${{ secrets.DEV_IAM_ROLE_ARN }}
@@ -50,12 +50,13 @@ jobs:
 
       # Create pull request
       - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v7
+        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
         with:
+          author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
           token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
           commit-message: "feat(regions_update): Update regions for AWS services"
           branch: "aws-services-regions-updated-${{ github.sha }}"
-          labels: "status/waiting-for-revision, severity/low, provider/aws, backport-to-v3"
+          labels: "status/waiting-for-revision, severity/low, provider/aws"
           title: "chore(regions_update): Changes in regions for AWS services"
           body: |
             ### Description

.github/workflows/ui-build-lint-push-containers.yml

@@ -61,7 +61,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Set short git commit SHA
         id: vars
@@ -70,18 +70,18 @@ jobs:
           echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           build-args: |
@@ -96,7 +96,7 @@ jobs:
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           build-args: |
@@ -110,7 +110,7 @@ jobs:
 
       - name: Trigger deployment
         if: github.event_name == 'push'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
         with:
           token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
           repository: ${{ secrets.CLOUD_DISPATCH }}

.github/workflows/ui-codeql.yml

@@ -44,16 +44,16 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v3
+        uses: github/codeql-action/init@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
         with:
           languages: ${{ matrix.language }}
           config-file: ./.github/codeql/ui-codeql-config.yml
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v3
+        uses: github/codeql-action/analyze@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
         with:
           category: "/language:${{matrix.language}}"

.github/workflows/ui-pull-request.yml

@@ -27,11 +27,11 @@ jobs:
         node-version: [20.x]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           persist-credentials: false
       - name: Setup Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: ${{ matrix.node-version }}
       - name: Install dependencies
@@ -46,11 +46,11 @@ jobs:
   test-container-build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
       - name: Build Container
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.UI_WORKING_DIR }}
           # Always build using `prod` target

.gitignore

@@ -42,6 +42,9 @@ junit-reports/
 # VSCode files
 .vscode/
 
+# Cursor files
+.cursorignore
+
 # Terraform
 .terraform*
 *.tfstate
@@ -50,6 +53,7 @@ junit-reports/
 # .env
 ui/.env*
 api/.env*
+.env.local
 
 # Coverage
 .coverage*

.pre-commit-config.yaml

@@ -115,7 +115,7 @@ repos:
       - id: safety
         name: safety
         description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
-        entry: bash -c 'safety check --ignore 70612,66963'
+        entry: bash -c 'safety check --ignore 70612,66963,74429,76352,76353'
         language: system
 
       - id: vulture

Dockerfile

@@ -1,24 +1,43 @@
-FROM python:3.12.9-alpine3.20
+FROM python:3.12.10-slim-bookworm AS build
 
 LABEL maintainer="https://github.com/prowler-cloud/prowler"
+LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
 
-# Update system dependencies and install essential tools
-#hadolint ignore=DL3018
-RUN apk --no-cache upgrade && apk --no-cache add curl git gcc python3-dev musl-dev linux-headers
+ARG POWERSHELL_VERSION=7.5.0
+
+# hadolint ignore=DL3008
+RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install PowerShell
+RUN ARCH=$(uname -m) && \
+    if [ "$ARCH" = "x86_64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-x64.tar.gz -O /tmp/powershell.tar.gz ; \
+    elif [ "$ARCH" = "aarch64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-arm64.tar.gz -O /tmp/powershell.tar.gz ; \
+    else \
+        echo "Unsupported architecture: $ARCH" && exit 1 ; \
+    fi && \
+    mkdir -p /opt/microsoft/powershell/7 && \
+    tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7 && \
+    chmod +x /opt/microsoft/powershell/7/pwsh && \
+    ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh && \
+    rm /tmp/powershell.tar.gz
+
+# Add prowler user
+RUN addgroup --gid 1000 prowler && \
+    adduser --uid 1000 --gid 1000 --disabled-password --gecos "" prowler
 
-# Create non-root user
-RUN mkdir -p /home/prowler && \
-    echo 'prowler:x:1000:1000:prowler:/home/prowler:' > /etc/passwd && \
-    echo 'prowler:x:1000:' > /etc/group && \
-    chown -R prowler:prowler /home/prowler
 USER prowler
 
-# Copy necessary files
 WORKDIR /home/prowler
+
+# Copy necessary files
 COPY prowler/  /home/prowler/prowler/
 COPY dashboard/ /home/prowler/dashboard/
 COPY pyproject.toml /home/prowler
 COPY README.md /home/prowler/
+COPY prowler/providers/m365/lib/powershell/m365_powershell.py /home/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py
 
 # Install Python dependencies
 ENV HOME='/home/prowler'
@@ -34,6 +53,9 @@ RUN pip install --no-cache-dir --upgrade pip && \
 RUN poetry install --compile && \
     rm -rf ~/.cache/pip
 
+# Install PowerShell modules
+RUN poetry run python prowler/providers/m365/lib/powershell/m365_powershell.py
+
 # Remove deprecated dash dependencies
 RUN pip uninstall dash-html-components -y && \
     pip uninstall dash-core-components -y

README.md

@@ -3,7 +3,7 @@
   <img align="center" src="https://github.com/prowler-cloud/prowler/blob/master/docs/img/prowler-logo-white.png#gh-dark-mode-only" width="50%" height="50%">
 </p>
 <p align="center">
-  <b><i>Prowler Open Source</b> is as dynamic and adaptable as the environment they’re meant to protect. Trusted by the leaders in security.
+  <b><i>Prowler</b> is the Open Cloud Security platform trusted by thousands to automate security and compliance in any cloud environment. With hundreds of ready-to-use checks and compliance frameworks, Prowler delivers real-time, customizable monitoring and seamless integrations, making cloud security simple, scalable, and cost-effective for organizations of any size.
 </p>
 <p align="center">
 <b>Learn more at <a href="https://prowler.com">prowler.com</i></b>
@@ -43,15 +43,29 @@
 
 # Description
 
-**Prowler** is an Open Source security tool to perform AWS, Azure, Google Cloud and Kubernetes security best practices assessments, audits, incident response, continuous monitoring, hardening and forensics readiness, and also remediations! We have Prowler CLI (Command Line Interface) that we call Prowler Open Source and a service on top of it that we call <a href="https://prowler.com">Prowler Cloud</a>.
+**Prowler** is an open-source security tool designed to assess and enforce security best practices across AWS, Azure, Google Cloud, and Kubernetes. It supports tasks such as security audits, incident response, continuous monitoring, system hardening, forensic readiness, and remediation processes.
+
+Prowler includes hundreds of built-in controls to ensure compliance with standards and frameworks, including:
+
+- **Industry Standards:** CIS, NIST 800, NIST CSF, and CISA
+- **Regulatory Compliance and Governance:** RBI, FedRAMP, and PCI-DSS
+- **Frameworks for Sensitive Data and Privacy:** GDPR, HIPAA, and FFIEC
+- **Frameworks for Organizational Governance and Quality Control:** SOC2 and GXP
+- **AWS-Specific Frameworks:** AWS Foundational Technical Review (FTR) and AWS Well-Architected Framework (Security Pillar)
+- **National Security Standards:** ENS (Spanish National Security Scheme)
+- **Custom Security Frameworks:** Tailored to your needs
+
+## Prowler CLI and Prowler Cloud
+
+Prowler offers a Command Line Interface (CLI), known as Prowler Open Source, and an additional service built on top of it, called <a href="https://prowler.com">Prowler Cloud</a>.
 
 ## Prowler App
 
-Prowler App is a web application that allows you to run Prowler in your cloud provider accounts and visualize the results in a user-friendly interface.
+Prowler App is a web-based application that simplifies running Prowler across your cloud provider accounts. It provides a user-friendly interface to visualize the results and streamline your security assessments.
 
 ![Prowler App](docs/img/overview.png)
 
->More details at [Prowler App Documentation](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-app-installation)
+>For more details, refer to the [Prowler App Documentation](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-app-installation)
 
 ## Prowler CLI
 
@@ -60,6 +74,7 @@ prowler <provider>
 ```
 ![Prowler CLI Execution](docs/img/short-display.png)
 
+
 ## Prowler Dashboard
 
 ```console
@@ -67,25 +82,34 @@ prowler dashboard
 ```
 ![Prowler Dashboard](docs/img/dashboard.png)
 
-It contains hundreds of controls covering CIS, NIST 800, NIST CSF, CISA, RBI, FedRAMP, PCI-DSS, GDPR, HIPAA, FFIEC, SOC2, GXP, AWS Well-Architected Framework Security Pillar, AWS Foundational Technical Review (FTR), ENS (Spanish National Security Scheme) and your custom security frameworks.
+# Prowler at a Glance
 
 | Provider | Checks | Services | [Compliance Frameworks](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/compliance/) | [Categories](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/misc/#categories) |
 |---|---|---|---|---|
-| AWS | 564 | 82 | 33 | 10 |
-| GCP | 77 | 13 | 6 | 3 |
-| Azure | 140 | 18 | 7 | 3 |
-| Kubernetes | 83 | 7 | 4 | 7 |
-| Microsoft365 | 5 | 2 | 1 | 0 |
+| AWS | 567 | 82 | 36 | 10 |
+| GCP | 79 | 13 | 10 | 3 |
+| Azure | 142 | 18 | 10 | 3 |
+| Kubernetes | 83 | 7 | 5 | 7 |
+| GitHub | 16 | 2 | 1 | 0 |
+| M365 | 69 | 7 | 3 | 2 |
+| NHN (Unofficial) | 6 | 2 | 1 | 0 |
 
-> You can list the checks, services, compliance frameworks and categories with `prowler <provider> --list-checks`, `prowler <provider> --list-services`, `prowler <provider> --list-compliance` and `prowler <provider> --list-categories`.
+> [!Note]
+> The numbers in the table are updated periodically.
+
+> [!Tip]
+> For the most accurate and up-to-date information about checks, services, frameworks, and categories, visit [**Prowler Hub**](https://hub.prowler.com).
+
+> [!Note]
+> Use the following commands to list Prowler's available checks, services, compliance frameworks, and categories: `prowler <provider> --list-checks`, `prowler <provider> --list-services`, `prowler <provider> --list-compliance` and `prowler <provider> --list-categories`.
 
 # 💻 Installation
 
 ## Prowler App
 
-Prowler App can be installed in different ways, depending on your environment:
+Prowler App offers flexible installation methods tailored to various environments:
 
-> See how to use Prowler App in the [Prowler App Usage Guide](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/prowler-app/).
+> For detailed instructions on using Prowler App, refer to the [Prowler App Usage Guide](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/prowler-app/).
 
 ### Docker Compose
 
@@ -101,8 +125,16 @@ curl -LO https://raw.githubusercontent.com/prowler-cloud/prowler/refs/heads/mast
 docker compose up -d
 ```
 
-> Containers are built for `linux/amd64`. If your workstation's architecture is different, please set `DOCKER_DEFAULT_PLATFORM=linux/amd64` in your environment or use the `--platform linux/amd64` flag in the docker command.
-> Enjoy Prowler App at http://localhost:3000 by signing up with your email and password.
+> Containers are built for `linux/amd64`.
+
+### Configuring Your Workstation for Prowler App
+
+If your workstation's architecture is incompatible, you can resolve this by:
+
+- **Setting the environment variable**: `DOCKER_DEFAULT_PLATFORM=linux/amd64`
+- **Using the following flag in your Docker command**: `--platform linux/amd64`
+
+> Once configured, access the Prowler App at http://localhost:3000. Sign up using your email and password to get started.
 
 ### From GitHub
 
@@ -128,12 +160,12 @@ python manage.py migrate --database admin
 gunicorn -c config/guniconf.py config.wsgi:application
 ```
 > [!IMPORTANT]
-> Starting from Poetry v2.0.0, `poetry shell` has been deprecated in favor of `poetry env activate`.
+> As of Poetry v2.0.0, the `poetry shell` command has been deprecated. Use `poetry env activate` instead for environment activation.
 >
-> If your poetry version is below 2.0.0 you must keep using `poetry shell` to activate your environment.
-> In case you have any doubts, consult the Poetry environment activation guide: https://python-poetry.org/docs/managing-environments/#activating-the-environment
+> If your Poetry version is below v2.0.0, continue using `poetry shell` to activate your environment.
+> For further guidance, refer to the Poetry Environment Activation Guide https://python-poetry.org/docs/managing-environments/#activating-the-environment.
 
-> Now, you can access the API documentation at http://localhost:8080/api/v1/docs.
+> After completing the setup, access the API documentation at http://localhost:8080/api/v1/docs.
 
 **Commands to run the API Worker**
 
@@ -171,29 +203,31 @@ npm run build
 npm start
 ```
 
-> Enjoy Prowler App at http://localhost:3000 by signing up with your email and password.
+> Once configured, access the Prowler App at http://localhost:3000. Sign up using your email and password to get started.
 
 ## Prowler CLI
 ### Pip package
-Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/), thus can be installed using pip with Python > 3.9.1, < 3.13:
+Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/). Consequently, it can be installed using pip with Python >3.9.1, <3.13:
 
 ```console
 pip install prowler
 prowler -v
 ```
->More details at [https://docs.prowler.com](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-cli-installation)
+>For further guidance, refer to [https://docs.prowler.com](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-cli-installation)
 
 ### Containers
 
-The available versions of Prowler CLI are the following:
+**Available Versions of Prowler CLI**
 
-- `latest`: in sync with `master` branch (bear in mind that it is not a stable version)
-- `v4-latest`: in sync with `v4` branch (bear in mind that it is not a stable version)
-- `v3-latest`: in sync with `v3` branch (bear in mind that it is not a stable version)
-- `<x.y.z>` (release): you can find the releases [here](https://github.com/prowler-cloud/prowler/releases), those are stable releases.
-- `stable`: this tag always point to the latest release.
-- `v4-stable`: this tag always point to the latest release for v4.
-- `v3-stable`: this tag always point to the latest release for v3.
+The following versions of Prowler CLI are available, depending on your requirements:
+
+- `latest`: Synchronizes with the `master` branch. Note that this version is not stable.
+- `v4-latest`: Synchronizes with the `v4` branch. Note that this version is not stable.
+- `v3-latest`: Synchronizes with the `v3` branch. Note that this version is not stable.
+- `<x.y.z>` (release): Stable releases corresponding to specific versions. You can find the complete list of releases [here](https://github.com/prowler-cloud/prowler/releases).
+- `stable`: Always points to the latest release.
+- `v4-stable`: Always points to the latest release for v4.
+- `v3-stable`: Always points to the latest release for v3.
 
 The container images are available here:
 - Prowler CLI:
@@ -205,35 +239,56 @@ The container images are available here:
 
 ### From GitHub
 
-Python > 3.9.1, < 3.13 is required with pip and poetry:
+Python >3.9.1, <3.13 is required with pip and Poetry:
 
 ``` console
 git clone https://github.com/prowler-cloud/prowler
 cd prowler
 eval $(poetry env activate)
 poetry install
-python prowler.py -v
+python prowler-cli.py -v
 ```
 > [!IMPORTANT]
-> Starting from Poetry v2.0.0, `poetry shell` has been deprecated in favor of `poetry env activate`.
->
-> If your poetry version is below 2.0.0 you must keep using `poetry shell` to activate your environment.
-> In case you have any doubts, consult the Poetry environment activation guide: https://python-poetry.org/docs/managing-environments/#activating-the-environment
+> To clone Prowler on Windows, configure Git to support long file paths by running the following command: `git config core.longpaths true`.
 
-> If you want to clone Prowler from Windows, use `git config core.longpaths true` to allow long file paths.
-# 📐✏️ High level architecture
+> [!IMPORTANT]
+> As of Poetry v2.0.0, the `poetry shell` command has been deprecated. Use `poetry env activate` instead for environment activation.
+>
+> If your Poetry version is below v2.0.0, continue using `poetry shell` to activate your environment.
+> For further guidance, refer to the Poetry Environment Activation Guide https://python-poetry.org/docs/managing-environments/#activating-the-environment.
+
+# ✏️ High level architecture
 
 ## Prowler App
-The **Prowler App** consists of three main components:
+**Prowler App** is composed of three key components:
 
-- **Prowler UI**: A user-friendly web interface for running Prowler and viewing results, powered by Next.js.
-- **Prowler API**: The backend API that executes Prowler scans and stores the results, built with Django REST Framework.
-- **Prowler SDK**: A Python SDK that integrates with the Prowler CLI for advanced functionality.
+- **Prowler UI**: A web-based interface, built with Next.js, providing a user-friendly experience for executing Prowler scans and visualizing results.
+- **Prowler API**: A backend service, developed with Django REST Framework, responsible for running Prowler scans and storing the generated results.
+- **Prowler SDK**: A Python SDK designed to extend the functionality of the Prowler CLI for advanced capabilities.
 
 ![Prowler App Architecture](docs/img/prowler-app-architecture.png)
 
 ## Prowler CLI
-You can run Prowler from your workstation, a Kubernetes Job, a Google Compute Engine, an Azure VM, an EC2 instance, Fargate or any other container, CloudShell and many more.
+
+**Running Prowler**
+
+Prowler can be executed across various environments, offering flexibility to meet your needs. It can be run from:
+
+- Your own workstation
+
+- A Kubernetes Job
+
+- Google Compute Engine
+
+- Azure Virtual Machines (VMs)
+
+- Amazon EC2 instances
+
+- AWS Fargate or other container platforms
+
+- CloudShell
+
+And many more environments.
 
 ![Architecture](docs/img/architecture.png)
 
@@ -241,23 +296,36 @@ You can run Prowler from your workstation, a Kubernetes Job, a Google Compute En
 
 ## General
 - `Allowlist` now is called `Mutelist`.
-- The `--quiet` option has been deprecated, now use the `--status` flag to select the finding's status you want to get from PASS, FAIL or MANUAL.
-- All `INFO` finding's status has changed to `MANUAL`.
-- The CSV output format is common for all the providers.
+- The `--quiet` option has been deprecated. Use the `--status` flag to filter findings based on their status: PASS, FAIL, or MANUAL.
+- All findings with an `INFO` status have been reclassified as `MANUAL`.
+- The CSV output format is standardized across all providers.
 
-We have deprecated some of our outputs formats:
-- The native JSON is replaced for the JSON [OCSF](https://schema.ocsf.io/) v1.1.0, common for all the providers.
+**Deprecated Output Formats**
+
+The following formats are now deprecated:
+- Native JSON has been replaced with JSON in [OCSF] v1.1.0 format, which is standardized across all providers (https://schema.ocsf.io/).
 
 ## AWS
-- Deprecate the AWS flag --sts-endpoint-region since we use AWS STS regional tokens.
-- To send only FAILS to AWS Security Hub, now use either `--send-sh-only-fails` or `--security-hub --status FAIL`.
+
+**AWS Flag Deprecation**
+
+The flag --sts-endpoint-region has been deprecated due to the adoption of AWS STS regional tokens.
+
+**Sending FAIL Results to AWS Security Hub**
+
+- To send only FAILS to AWS Security Hub, use one of the following options: `--send-sh-only-fails` or `--security-hub --status FAIL`.
 
 
 # 📖 Documentation
 
-Install, Usage, Tutorials and Developer Guide is at https://docs.prowler.com/
+**Documentation Resources**
+
+For installation instructions, usage details, tutorials, and the Developer Guide, visit https://docs.prowler.com/
 
 # 📃 License
 
-Prowler is licensed as Apache License 2.0 as specified in each file. You may obtain a copy of the License at
-<http://www.apache.org/licenses/LICENSE-2.0>
+**Prowler License Information**
+
+Prowler is licensed under the Apache License 2.0, as indicated in each file within the repository. Obtaining a Copy of the License
+
+A copy of the License is available at <http://www.apache.org/licenses/LICENSE-2.0>

api/.env.example

@@ -53,3 +53,6 @@ DJANGO_GOOGLE_OAUTH_CALLBACK_URL=""
 DJANGO_GITHUB_OAUTH_CLIENT_ID=""
 DJANGO_GITHUB_OAUTH_CLIENT_SECRET=""
 DJANGO_GITHUB_OAUTH_CALLBACK_URL=""
+
+# Deletion Task Batch Size
+DJANGO_DELETION_BATCH_SIZE=5000

api/.gitignore

@@ -1,168 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.pyc
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-/_data/
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-*.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-.idea/
-
-# VSCode
-.vscode/

api/.pre-commit-config.yaml

@@ -1,91 +0,0 @@
-repos:
-  ## GENERAL
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
-    hooks:
-      - id: check-merge-conflict
-      - id: check-yaml
-        args: ["--unsafe"]
-      - id: check-json
-      - id: end-of-file-fixer
-      - id: trailing-whitespace
-      - id: no-commit-to-branch
-      - id: pretty-format-json
-        args: ["--autofix", "--no-sort-keys", "--no-ensure-ascii"]
-        exclude: 'src/backend/api/fixtures/dev/.*\.json$'
-
-  ## TOML
-  - repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
-    rev: v2.13.0
-    hooks:
-      - id: pretty-format-toml
-        args: [--autofix]
-        files: pyproject.toml
-
-  ## BASH
-  - repo: https://github.com/koalaman/shellcheck-precommit
-    rev: v0.10.0
-    hooks:
-      - id: shellcheck
-        exclude: contrib
-  ## PYTHON
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    # Ruff version.
-    rev: v0.5.0
-    hooks:
-      # Run the linter.
-      - id: ruff
-        args: [ --fix ]
-      # Run the formatter.
-      - id: ruff-format
-
-  - repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
-    hooks:
-      - id: poetry-check
-        args: ["--directory=src"]
-      - id: poetry-lock
-        args: ["--no-update", "--directory=src"]
-
-  - repo: https://github.com/hadolint/hadolint
-    rev: v2.13.0-beta
-    hooks:
-      - id: hadolint
-        args: ["--ignore=DL3013", "Dockerfile"]
-
-  - repo: local
-    hooks:
-      - id: pylint
-        name: pylint
-        entry: bash -c 'poetry run pylint --disable=W,C,R,E -j 0 -rn -sn src/'
-        language: system
-        files: '.*\.py'
-
-      - id: trufflehog
-        name: TruffleHog
-        description: Detect secrets in your data.
-        entry: bash -c 'trufflehog --no-update git file://. --only-verified --fail'
-        # For running trufflehog in docker, use the following entry instead:
-        # entry: bash -c 'docker run -v "$(pwd):/workdir" -i --rm trufflesecurity/trufflehog:latest git file:///workdir --only-verified --fail'
-        language: system
-        stages: ["commit", "push"]
-
-      - id: bandit
-        name: bandit
-        description: "Bandit is a tool for finding common security issues in Python code"
-        entry: bash -c 'poetry run bandit -q -lll -x '*_test.py,./contrib/,./.venv/' -r .'
-        language: system
-        files: '.*\.py'
-
-      - id: safety
-        name: safety
-        description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
-        entry: bash -c 'poetry run safety check --ignore 70612,66963'
-        language: system
-
-      - id: vulture
-        name: vulture
-        description: "Vulture finds unused code in Python programs."
-        entry: bash -c 'poetry run vulture --exclude "contrib,.venv,tests,conftest.py" --min-confidence 100 .'
-        language: system
-        files: '.*\.py'

api/CHANGELOG.md

@@ -2,13 +2,130 @@
 
 All notable changes to the **Prowler API** are documented in this file.
 
+## [v1.9.0] (Prowler UNRELEASED)
+
+### Added
+- SSO with SAML support [(#7822)](https://github.com/prowler-cloud/prowler/pull/7822)
+- Support GCP Service Account key [(#7824)](https://github.com/prowler-cloud/prowler/pull/7824)
+- `GET /compliance-overviews` endpoints to retrieve compliance metadata and specific requirements statuses [(#7877)](https://github.com/prowler-cloud/prowler/pull/7877)
+- Lighthouse configuration support [(#7848)](https://github.com/prowler-cloud/prowler/pull/7848)
+
+### Changed
+- Reworked `GET /compliance-overviews` to return proper requirement metrics [(#7877)](https://github.com/prowler-cloud/prowler/pull/7877)
+
+### Fixed
+- Add missing mapping for ISO 27001 compliance for M365 provider [(#8069)](https://github.com/prowler-cloud/prowler/pull/8069)
+
 ---
 
-## [v1.6.0] (Prowler UNRELEASED)
+## [v1.8.5] (Prowler v5.7.5)
+
+### Fixed
+- Normalize provider UID to ensure safe and unique export directory paths [(#8007)](https://github.com/prowler-cloud/prowler/pull/8007).
+- Blank resource types in `/metadata` endpoints [(#8027)](https://github.com/prowler-cloud/prowler/pull/8027)
+
+---
+
+## [v1.8.4] (Prowler v5.7.4)
+
+### Removed
+- Reverted RLS transaction handling and DB custom backend [(#7994)](https://github.com/prowler-cloud/prowler/pull/7994)
+
+---
+
+## [v1.8.3] (Prowler v5.7.3)
+
+### Added
+- Database backend to handle already closed connections [(#7935)](https://github.com/prowler-cloud/prowler/pull/7935)
+
+### Changed
+- Renamed field encrypted_password to password for M365 provider [(#7784)](https://github.com/prowler-cloud/prowler/pull/7784)
+
+### Fixed
+- Transaction persistence with RLS operations [(#7916)](https://github.com/prowler-cloud/prowler/pull/7916)
+- Reverted the change `get_with_retry` to use the original `get` method for retrieving tasks [(#7932)](https://github.com/prowler-cloud/prowler/pull/7932)
+
+---
+
+## [v1.8.2] (Prowler v5.7.2)
+
+### Fixed
+- Task lookup to use task_kwargs instead of task_args for scan report resolution [(#7830)](https://github.com/prowler-cloud/prowler/pull/7830)
+- Kubernetes UID validation to allow valid context names [(#7871)](https://github.com/prowler-cloud/prowler/pull/7871)
+- Connection status verification before launching a scan [(#7831)](https://github.com/prowler-cloud/prowler/pull/7831)
+- Race condition when creating background tasks [(#7876)](https://github.com/prowler-cloud/prowler/pull/7876)
+- Error when modifying or retrieving tenants due to missing user UUID in transaction context [(#7890)](https://github.com/prowler-cloud/prowler/pull/7890)
+
+---
+
+## [v1.8.1] (Prowler v5.7.1)
+
+### Fixed
+- Added database index to improve performance on finding lookup [(#7800)](https://github.com/prowler-cloud/prowler/pull/7800)
+
+---
+
+## [v1.8.0] (Prowler v5.7.0)
+
+### Added
+- Huge improvements to `/findings/metadata` and resource related filters for findings [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
+- Improvements to `/overviews` endpoints [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
+- Queue to perform backfill background tasks [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
+- New endpoints to retrieve latest findings and metadata [(#7743)](https://github.com/prowler-cloud/prowler/pull/7743)
+- Export support for Prowler ThreatScore in M365 [(7783)](https://github.com/prowler-cloud/prowler/pull/7783)
+
+---
+
+## [v1.7.0] (Prowler v5.6.0)
 
 ### Added
 
-- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167).
+- M365 as a new provider [(#7563)](https://github.com/prowler-cloud/prowler/pull/7563)
+- `compliance/` folder and ZIP‐export functionality for all compliance reports [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653)
+- API endpoint to fetch and download any specific compliance file by name [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653)
+
+---
+
+## [v1.6.0] (Prowler v5.5.0)
+
+### Added
+
+- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167)
+- HTTP Security Headers [(#7289)](https://github.com/prowler-cloud/prowler/pull/7289)
+- New endpoint to get the compliance overviews metadata [(#7333)](https://github.com/prowler-cloud/prowler/pull/7333)
+- Support for muted findings [(#7378)](https://github.com/prowler-cloud/prowler/pull/7378)
+- Missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318)
+
+---
+
+## [v1.5.4] (Prowler v5.4.4)
+
+### Fixed
+- Bug with periodic tasks when trying to delete a provider [(#7466)](https://github.com/prowler-cloud/prowler/pull/7466)
+
+---
+
+## [v1.5.3] (Prowler v5.4.3)
+
+### Fixed
+- Duplicated scheduled scans handling [(#7401)](https://github.com/prowler-cloud/prowler/pull/7401)
+- Environment variable to configure the deletion task batch size [(#7423)](https://github.com/prowler-cloud/prowler/pull/7423)
+
+---
+
+## [v1.5.2] (Prowler v5.4.2)
+
+### Changed
+- Refactored deletion logic and implemented retry mechanism for deletion tasks [(#7349)](https://github.com/prowler-cloud/prowler/pull/7349)
+
+---
+
+## [v1.5.1] (Prowler v5.4.1)
+
+### Fixed
+- Handle response in case local files are missing [(#7183)](https://github.com/prowler-cloud/prowler/pull/7183)
+- Race condition when deleting export files after the S3 upload [(#7172)](https://github.com/prowler-cloud/prowler/pull/7172)
+- Handle exception when a provider has no secret in test connection [(#7283)](https://github.com/prowler-cloud/prowler/pull/7283)
 
 ---
 
@@ -16,20 +133,20 @@ All notable changes to the **Prowler API** are documented in this file.
 
 ### Added
 - Social login integration with Google and GitHub [(#6906)](https://github.com/prowler-cloud/prowler/pull/6906)
-- Add API scan report system, now all scans launched from the API will generate a compressed file with the report in OCSF, CSV and HTML formats [(#6878)](https://github.com/prowler-cloud/prowler/pull/6878).
+- API scan report system, now all scans launched from the API will generate a compressed file with the report in OCSF, CSV and HTML formats [(#6878)](https://github.com/prowler-cloud/prowler/pull/6878)
 - Configurable Sentry integration [(#6874)](https://github.com/prowler-cloud/prowler/pull/6874)
 
 ### Changed
-- Optimized `GET /findings` endpoint to improve response time and size [(#7019)](https://github.com/prowler-cloud/prowler/pull/7019).
+- Optimized `GET /findings` endpoint to improve response time and size [(#7019)](https://github.com/prowler-cloud/prowler/pull/7019)
 
 ---
 
 ## [v1.4.0] (Prowler v5.3.0)
 
 ### Changed
-- Daily scheduled scan instances are now created beforehand with `SCHEDULED` state [(#6700)](https://github.com/prowler-cloud/prowler/pull/6700).
-- Findings endpoints now require at least one date filter [(#6800)](https://github.com/prowler-cloud/prowler/pull/6800).
-- Findings metadata endpoint received a performance improvement [(#6863)](https://github.com/prowler-cloud/prowler/pull/6863).
-- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869).
+- Daily scheduled scan instances are now created beforehand with `SCHEDULED` state [(#6700)](https://github.com/prowler-cloud/prowler/pull/6700)
+- Findings endpoints now require at least one date filter [(#6800)](https://github.com/prowler-cloud/prowler/pull/6800)
+- Findings metadata endpoint received a performance improvement [(#6863)](https://github.com/prowler-cloud/prowler/pull/6863)
+- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869)
 
 ---

api/Dockerfile

@@ -1,13 +1,45 @@
-FROM python:3.12.8-alpine3.20 AS build
+FROM python:3.12.10-slim-bookworm AS build
 
 LABEL maintainer="https://github.com/prowler-cloud/api"
 
-# hadolint ignore=DL3018
-RUN apk --no-cache add gcc python3-dev musl-dev linux-headers curl-dev
+ARG POWERSHELL_VERSION=7.5.0
+ENV POWERSHELL_VERSION=${POWERSHELL_VERSION}
+
+# hadolint ignore=DL3008
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    wget \
+    libicu72 \
+    gcc \
+    g++ \
+    make \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libxmlsec1-openssl \
+    pkg-config \
+    libtool \
+    libxslt1-dev \
+    python3-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install PowerShell
+RUN ARCH=$(uname -m) && \
+    if [ "$ARCH" = "x86_64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-x64.tar.gz -O /tmp/powershell.tar.gz ; \
+    elif [ "$ARCH" = "aarch64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-arm64.tar.gz -O /tmp/powershell.tar.gz ; \
+    else \
+        echo "Unsupported architecture: $ARCH" && exit 1 ; \
+    fi && \
+    mkdir -p /opt/microsoft/powershell/7 && \
+    tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7 && \
+    chmod +x /opt/microsoft/powershell/7/pwsh && \
+    ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh && \
+    rm /tmp/powershell.tar.gz
+
+# Add prowler user
+RUN addgroup --gid 1000 prowler && \
+    adduser --uid 1000 --gid 1000 --disabled-password --gecos "" prowler
 
-RUN apk --no-cache upgrade && \
-    addgroup -g 1000 prowler && \
-    adduser -D -u 1000 -G prowler prowler
 USER prowler
 
 WORKDIR /home/prowler
@@ -17,28 +49,26 @@ COPY pyproject.toml ./
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir poetry
 
-COPY src/backend/  ./backend/
-
 ENV PATH="/home/prowler/.local/bin:$PATH"
 
 # Add `--no-root` to avoid installing the current project as a package
 RUN poetry install --no-root && \
     rm -rf ~/.cache/pip
 
+RUN poetry run python "$(poetry env info --path)/src/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py"
+
+# Prevents known compatibility error between lxml and libxml2/libxmlsec versions.
+# See: https://github.com/xmlsec/python-xmlsec/issues/320
+RUN poetry run pip install --force-reinstall --no-binary lxml lxml
+
+COPY src/backend/ ./backend/
 COPY docker-entrypoint.sh ./docker-entrypoint.sh
 
 WORKDIR /home/prowler/backend
 
 # Development image
-# hadolint ignore=DL3006
 FROM build AS dev
 
-USER 0
-# hadolint ignore=DL3018
-RUN apk --no-cache add curl vim
-
-USER prowler
-
 ENTRYPOINT ["../docker-entrypoint.sh", "dev"]
 
 # Production image

api/README.md

@@ -235,6 +235,7 @@ To view the logs for any component (e.g., Django, Celery worker), you can use th
 
 ```console
 docker logs -f $(docker ps --format "{{.Names}}" | grep 'api-')
+```
 
 ## Applying migrations
 

api/docker-compose.yml

@@ -1,125 +0,0 @@
-services:
-  api:
-    build:
-      dockerfile: Dockerfile
-    image: prowler-api
-    env_file:
-      - path: ./.env
-        required: false
-    ports:
-      - "${DJANGO_PORT:-8000}:${DJANGO_PORT:-8000}"
-    profiles:
-      - prod
-    depends_on:
-      postgres:
-        condition: service_healthy
-      valkey:
-        condition: service_healthy
-    entrypoint:
-      - "../docker-entrypoint.sh"
-      - "prod"
-
-  api-dev:
-    build:
-      dockerfile: Dockerfile
-      target: dev
-    image: prowler-api-dev
-    environment:
-      - DJANGO_SETTINGS_MODULE=config.django.devel
-      - DJANGO_LOGGING_FORMATTER=human_readable
-    env_file:
-      - path: ./.env
-        required: false
-    ports:
-      - "${DJANGO_PORT:-8080}:${DJANGO_PORT:-8080}"
-    volumes:
-      - "./src/backend:/home/prowler/backend"
-      - "./pyproject.toml:/home/prowler/pyproject.toml"
-    profiles:
-      - dev
-    depends_on:
-      postgres:
-        condition: service_healthy
-      valkey:
-        condition: service_healthy
-    entrypoint:
-      - "../docker-entrypoint.sh"
-      - "dev"
-
-  postgres:
-    image: postgres:16.3-alpine
-    ports:
-      - "${POSTGRES_PORT:-5432}:${POSTGRES_PORT:-5432}"
-    hostname: "postgres-db"
-    volumes:
-      - ./_data/postgres:/var/lib/postgresql/data
-    environment:
-      - POSTGRES_USER=${POSTGRES_ADMIN_USER:-prowler}
-      - POSTGRES_PASSWORD=${POSTGRES_ADMIN_PASSWORD:-S3cret}
-      - POSTGRES_DB=${POSTGRES_DB:-prowler_db}
-    env_file:
-      - path: ./.env
-        required: false
-    healthcheck:
-      test: ["CMD-SHELL", "sh -c 'pg_isready -U ${POSTGRES_ADMIN_USER:-prowler} -d ${POSTGRES_DB:-prowler_db}'"]
-      interval: 5s
-      timeout: 5s
-      retries: 5
-
-  valkey:
-    image: valkey/valkey:7-alpine3.19
-    ports:
-      - "${VALKEY_PORT:-6379}:6379"
-    hostname: "valkey"
-    volumes:
-      - ./_data/valkey:/data
-    env_file:
-      - path: ./.env
-        required: false
-    healthcheck:
-      test: ["CMD-SHELL", "sh -c 'valkey-cli ping'"]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-
-  worker:
-    build:
-      dockerfile: Dockerfile
-    image: prowler-worker
-    environment:
-      - DJANGO_SETTINGS_MODULE=${DJANGO_SETTINGS_MODULE:-config.django.production}
-    env_file:
-      - path: ./.env
-        required: false
-    profiles:
-      - dev
-      - prod
-    depends_on:
-      valkey:
-        condition: service_healthy
-      postgres:
-        condition: service_healthy
-    entrypoint:
-      - "../docker-entrypoint.sh"
-      - "worker"
-
-  worker-beat:
-    build:
-      dockerfile: Dockerfile
-    image: prowler-worker
-    environment:
-      - DJANGO_SETTINGS_MODULE=${DJANGO_SETTINGS_MODULE:-config.django.production}
-    env_file:
-      - path: ./.env
-        required: false
-    profiles:
-      - dev
-      - prod
-    depends_on:
-      valkey:
-        condition: service_healthy
-      postgres:
-        condition: service_healthy
-    entrypoint:
-      - "../docker-entrypoint.sh"
-      - "beat"

api/docker-entrypoint.sh

@@ -3,6 +3,10 @@
 
 apply_migrations() {
   echo "Applying database migrations..."
+
+  # Fix Inconsistent migration history after adding sites app
+  poetry run python manage.py check_and_fix_socialaccount_sites_migration --database admin
+
   poetry run python manage.py migrate --database admin
 }
 
@@ -28,7 +32,7 @@ start_prod_server() {
 
 start_worker() {
   echo "Starting the worker..."
-  poetry run python -m celery -A config.celery worker -l "${DJANGO_LOGGING_LEVEL:-info}" -Q celery,scans,scan-reports,deletion -E --max-tasks-per-child 1
+  poetry run python -m celery -A config.celery worker -l "${DJANGO_LOGGING_LEVEL:-info}" -Q celery,scans,scan-reports,deletion,backfill -E --max-tasks-per-child 1
 }
 
 start_worker_beat() {

api/pyproject.toml

@@ -7,7 +7,8 @@ authors = [{name = "Prowler Engineering", email = "engineering@prowler.com"}]
 dependencies = [
   "celery[pytest] (>=5.4.0,<6.0.0)",
   "dj-rest-auth[with_social,jwt] (==7.0.1)",
-  "django==5.1.7",
+  "django==5.1.10",
+  "django-allauth[saml] (>=65.8.0,<66.0.0)",
   "django-celery-beat (>=2.7.0,<3.0.0)",
   "django-celery-results (>=2.5.1,<3.0.0)",
   "django-cors-headers==4.4.0",
@@ -26,7 +27,8 @@ dependencies = [
   "psycopg2-binary==2.9.9",
   "pytest-celery[redis] (>=1.0.1,<2.0.0)",
   "sentry-sdk[django] (>=2.20.0,<3.0.0)",
-  "uuid6==2024.7.10"
+  "uuid6==2024.7.10",
+  "openai (>=1.82.0,<2.0.0)"
 ]
 description = "Prowler's API (Django/DRF)"
 license = "Apache-2.0"
@@ -34,7 +36,7 @@ name = "prowler-api"
 package-mode = false
 # Needed for the SDK compatibility
 requires-python = ">=3.11,<3.13"
-version = "1.5.0"
+version = "1.9.0"
 
 [project.scripts]
 celery = "src.backend.config.settings.celery"
@@ -45,6 +47,7 @@ coverage = "7.5.4"
 django-silk = "5.3.2"
 docker = "7.1.0"
 freezegun = "1.5.1"
+marshmallow = ">=3.15.0,<4.0.0"
 mypy = "1.10.1"
 pylint = "3.2.5"
 pytest = "8.2.2"

api/src/backend/api/adapters.py

@@ -3,7 +3,14 @@ from django.db import transaction
 
 from api.db_router import MainRouter
 from api.db_utils import rls_transaction
-from api.models import Membership, Role, Tenant, User, UserRoleRelationship
+from api.models import (
+    Membership,
+    Role,
+    SAMLConfiguration,
+    Tenant,
+    User,
+    UserRoleRelationship,
+)
 
 
 class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
@@ -17,6 +24,8 @@ class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
     def pre_social_login(self, request, sociallogin):
         # Link existing accounts with the same email address
         email = sociallogin.account.extra_data.get("email")
+        if sociallogin.account.provider == "saml":
+            email = sociallogin.user.email
         if email:
             existing_user = self.get_user_by_email(email)
             if existing_user:
@@ -29,29 +38,86 @@ class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
         """
         with transaction.atomic(using=MainRouter.admin_db):
             user = super().save_user(request, sociallogin, form)
-            user.save(using=MainRouter.admin_db)
+            provider = sociallogin.account.provider
+            extra = sociallogin.account.extra_data
 
-            tenant = Tenant.objects.using(MainRouter.admin_db).create(
-                name=f"{user.email.split('@')[0]} default tenant"
-            )
-            with rls_transaction(str(tenant.id)):
-                Membership.objects.using(MainRouter.admin_db).create(
-                    user=user, tenant=tenant, role=Membership.RoleChoices.OWNER
+            if provider == "saml":
+                # Handle SAML-specific logic
+                user.first_name = extra.get("firstName", [""])[0]
+                user.last_name = extra.get("lastName", [""])[0]
+                user.company_name = extra.get("organization", [""])[0]
+                user.name = f"{user.first_name} {user.last_name}".strip()
+                user.save(using=MainRouter.admin_db)
+
+                email_domain = user.email.split("@")[-1]
+                tenant = (
+                    SAMLConfiguration.objects.using(MainRouter.admin_db)
+                    .get(email_domain=email_domain)
+                    .tenant
                 )
-                role = Role.objects.using(MainRouter.admin_db).create(
-                    name="admin",
-                    tenant_id=tenant.id,
-                    manage_users=True,
-                    manage_account=True,
-                    manage_billing=True,
-                    manage_providers=True,
-                    manage_integrations=True,
-                    manage_scans=True,
-                    unlimited_visibility=True,
-                )
-                UserRoleRelationship.objects.using(MainRouter.admin_db).create(
-                    user=user,
-                    role=role,
-                    tenant_id=tenant.id,
+
+                with rls_transaction(str(tenant.id)):
+                    role_name = extra.get("userType", ["saml_default_role"])[0].strip()
+
+                    try:
+                        role = Role.objects.using(MainRouter.admin_db).get(
+                            name=role_name, tenant_id=tenant.id
+                        )
+                    except Role.DoesNotExist:
+                        role = Role.objects.using(MainRouter.admin_db).create(
+                            name=role_name,
+                            tenant_id=tenant.id,
+                            manage_users=False,
+                            manage_account=False,
+                            manage_billing=False,
+                            manage_providers=False,
+                            manage_integrations=False,
+                            manage_scans=False,
+                            unlimited_visibility=False,
+                        )
+
+                    Membership.objects.using(MainRouter.admin_db).create(
+                        user=user,
+                        tenant=tenant,
+                        role=Membership.RoleChoices.MEMBER,
+                    )
+
+                    UserRoleRelationship.objects.using(MainRouter.admin_db).create(
+                        user=user,
+                        role=role,
+                        tenant_id=tenant.id,
+                    )
+
+            else:
+                # Handle other providers (e.g., GitHub, Google)
+                user.save(using=MainRouter.admin_db)
+                social_account_name = extra.get("name")
+                if social_account_name:
+                    user.name = social_account_name
+                    user.save(using=MainRouter.admin_db)
+
+                tenant = Tenant.objects.using(MainRouter.admin_db).create(
+                    name=f"{user.email.split('@')[0]} default tenant"
                 )
+                with rls_transaction(str(tenant.id)):
+                    Membership.objects.using(MainRouter.admin_db).create(
+                        user=user, tenant=tenant, role=Membership.RoleChoices.OWNER
+                    )
+                    role = Role.objects.using(MainRouter.admin_db).create(
+                        name="admin",
+                        tenant_id=tenant.id,
+                        manage_users=True,
+                        manage_account=True,
+                        manage_billing=True,
+                        manage_providers=True,
+                        manage_integrations=True,
+                        manage_scans=True,
+                        unlimited_visibility=True,
+                    )
+                    UserRoleRelationship.objects.using(MainRouter.admin_db).create(
+                        user=user,
+                        role=role,
+                        tenant_id=tenant.id,
+                    )
+
         return user

api/src/backend/api/base_views.py

@@ -109,16 +109,6 @@ class BaseTenantViewset(BaseViewSet):
                 pass  # Tenant might not exist, handle gracefully
 
     def initial(self, request, *args, **kwargs):
-        if (
-            request.resolver_match.url_name != "tenant-detail"
-            and request.method != "DELETE"
-        ):
-            user_id = str(request.user.id)
-
-            with rls_transaction(value=user_id, parameter=POSTGRES_USER_VAR):
-                return super().initial(request, *args, **kwargs)
-
-        # TODO: DRY this when we have time
         if request.auth is None:
             raise NotAuthenticated
 
@@ -126,8 +116,8 @@ class BaseTenantViewset(BaseViewSet):
         if tenant_id is None:
             raise NotAuthenticated("Tenant ID is not present in token")
 
-        with rls_transaction(tenant_id):
-            self.request.tenant_id = tenant_id
+        user_id = str(request.user.id)
+        with rls_transaction(value=user_id, parameter=POSTGRES_USER_VAR):
             return super().initial(request, *args, **kwargs)
 
 

api/src/backend/api/compliance.py

@@ -1,12 +1,38 @@
 from types import MappingProxyType
 
+from api.models import Provider
+from prowler.config.config import get_available_compliance_frameworks
 from prowler.lib.check.compliance_models import Compliance
 from prowler.lib.check.models import CheckMetadata
 
-from api.models import Provider
-
 PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE = {}
 PROWLER_CHECKS = {}
+AVAILABLE_COMPLIANCE_FRAMEWORKS = {}
+
+
+def get_compliance_frameworks(provider_type: Provider.ProviderChoices) -> list[str]:
+    """
+    Retrieve and cache the list of available compliance frameworks for a specific cloud provider.
+
+    This function lazily loads and caches the available compliance frameworks (e.g., CIS, MITRE, ISO)
+    for each provider type (AWS, Azure, GCP, etc.) on first access. Subsequent calls for the same
+    provider will return the cached result.
+
+    Args:
+        provider_type (Provider.ProviderChoices): The cloud provider type for which to retrieve
+            available compliance frameworks (e.g., "aws", "azure", "gcp", "m365").
+
+    Returns:
+        list[str]: A list of framework identifiers (e.g., "cis_1.4_aws", "mitre_attack_azure") available
+        for the given provider.
+    """
+    global AVAILABLE_COMPLIANCE_FRAMEWORKS
+    if provider_type not in AVAILABLE_COMPLIANCE_FRAMEWORKS:
+        AVAILABLE_COMPLIANCE_FRAMEWORKS[provider_type] = (
+            get_available_compliance_frameworks(provider_type)
+        )
+
+    return AVAILABLE_COMPLIANCE_FRAMEWORKS[provider_type]
 
 
 def get_prowler_provider_checks(provider_type: Provider.ProviderChoices):
@@ -164,10 +190,16 @@ def generate_compliance_overview_template(prowler_compliance: dict):
                 total_checks = len(requirement.Checks)
                 checks_dict = {check: None for check in requirement.Checks}
 
+                req_status_val = "MANUAL" if total_checks == 0 else "PASS"
+
                 # Build requirement dictionary
                 requirement_dict = {
                     "name": requirement.Name or requirement.Id,
                     "description": requirement.Description,
+                    "tactics": getattr(requirement, "Tactics", []),
+                    "subtechniques": getattr(requirement, "SubTechniques", []),
+                    "platforms": getattr(requirement, "Platforms", []),
+                    "technique_url": getattr(requirement, "TechniqueURL", ""),
                     "attributes": [
                         dict(attribute) for attribute in requirement.Attributes
                     ],
@@ -178,20 +210,18 @@ def generate_compliance_overview_template(prowler_compliance: dict):
                         "manual": 0,
                         "total": total_checks,
                     },
-                    "status": "PASS",
+                    "status": req_status_val,
                 }
 
-                # Update requirements status
-                if total_checks == 0:
+                # Update requirements status counts for the framework
+                if req_status_val == "MANUAL":
                     requirements_status["manual"] += 1
+                elif req_status_val == "PASS":
+                    requirements_status["passed"] += 1
 
                 # Add requirement to compliance requirements
                 compliance_requirements[requirement.Id] = requirement_dict
 
-            # Calculate pending requirements
-            pending_requirements = total_requirements - requirements_status["manual"]
-            requirements_status["passed"] = pending_requirements
-
             # Build compliance dictionary
             compliance_dict = {
                 "framework": compliance_data.Framework,

api/src/backend/api/db_utils.py

@@ -1,3 +1,4 @@
+import re
 import secrets
 import uuid
 from contextlib import contextmanager
@@ -6,6 +7,7 @@ from datetime import datetime, timedelta, timezone
 from django.conf import settings
 from django.contrib.auth.models import BaseUserManager
 from django.db import connection, models, transaction
+from django_celery_beat.models import PeriodicTask
 from psycopg2 import connect as psycopg2_connect
 from psycopg2.extensions import AsIs, new_type, register_adapter, register_type
 from rest_framework_json_api.serializers import ValidationError
@@ -105,11 +107,12 @@ def generate_random_token(length: int = 14, symbols: str | None = None) -> str:
     return "".join(secrets.choice(symbols or _symbols) for _ in range(length))
 
 
-def batch_delete(queryset, batch_size=5000):
+def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_SIZE):
     """
     Deletes objects in batches and returns the total number of deletions and a summary.
 
     Args:
+        tenant_id (str): Tenant ID the queryset belongs to.
         queryset (QuerySet): The queryset of objects to delete.
         batch_size (int): The number of objects to delete in each batch.
 
@@ -120,15 +123,16 @@ def batch_delete(queryset, batch_size=5000):
     deletion_summary = {}
 
     while True:
-        # Get a batch of IDs to delete
-        batch_ids = set(
-            queryset.values_list("id", flat=True).order_by("id")[:batch_size]
-        )
-        if not batch_ids:
-            # No more objects to delete
-            break
+        with rls_transaction(tenant_id, POSTGRES_TENANT_VAR):
+            # Get a batch of IDs to delete
+            batch_ids = set(
+                queryset.values_list("id", flat=True).order_by("id")[:batch_size]
+            )
+            if not batch_ids:
+                # No more objects to delete
+                break
 
-        deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
+            deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
 
         total_deleted += deleted_count
         for model_label, count in deleted_info.items():
@@ -137,6 +141,40 @@ def batch_delete(queryset, batch_size=5000):
     return total_deleted, deletion_summary
 
 
+def delete_related_daily_task(provider_id: str):
+    """
+    Deletes the periodic task associated with a specific provider.
+
+    Args:
+        provider_id (str): The unique identifier for the provider
+                           whose related periodic task should be deleted.
+    """
+    task_name = f"scan-perform-scheduled-{provider_id}"
+    PeriodicTask.objects.filter(name=task_name).delete()
+
+
+def create_objects_in_batches(
+    tenant_id: str, model, objects: list, batch_size: int = 500
+):
+    """
+    Bulk-create model instances in repeated, per-tenant RLS transactions.
+
+    All chunks execute in their own transaction, so no single transaction
+    grows too large.
+
+    Args:
+        tenant_id (str): UUID string of the tenant under which to set RLS.
+        model: Django model class whose `.objects.bulk_create()` will be called.
+        objects (list): List of model instances (unsaved) to bulk-create.
+        batch_size (int): Maximum number of objects per bulk_create call.
+    """
+    total = len(objects)
+    for i in range(0, total, batch_size):
+        chunk = objects[i : i + batch_size]
+        with rls_transaction(value=tenant_id, parameter=POSTGRES_TENANT_VAR):
+            model.objects.bulk_create(chunk, batch_size)
+
+
 # Postgres Enums
 
 
@@ -212,6 +250,167 @@ def register_enum(apps, schema_editor, enum_class):  # noqa: F841
         register_adapter(enum_class, enum_adapter)
 
 
+def _should_create_index_on_partition(
+    partition_name: str, all_partitions: bool = False
+) -> bool:
+    """
+    Determine if we should create an index on this partition.
+
+    Args:
+        partition_name: The name of the partition (e.g., "findings_2025_aug", "findings_default")
+        all_partitions: If True, create on all partitions. If False, only current/future partitions.
+
+    Returns:
+        bool: True if index should be created on this partition, False otherwise.
+    """
+    if all_partitions:
+        return True
+
+    # Extract date from partition name if it follows the pattern
+    # Partition names look like: findings_2025_aug, findings_2025_jul, etc.
+    date_pattern = r"(\d{4})_([a-z]{3})$"
+    match = re.search(date_pattern, partition_name)
+
+    if not match:
+        # If we can't parse the date, include it to be safe (e.g., default partition)
+        return True
+
+    try:
+        year_str, month_abbr = match.groups()
+        year = int(year_str)
+
+        # Map month abbreviations to numbers
+        month_map = {
+            "jan": 1,
+            "feb": 2,
+            "mar": 3,
+            "apr": 4,
+            "may": 5,
+            "jun": 6,
+            "jul": 7,
+            "aug": 8,
+            "sep": 9,
+            "oct": 10,
+            "nov": 11,
+            "dec": 12,
+        }
+
+        month = month_map.get(month_abbr.lower())
+        if month is None:
+            # Unknown month abbreviation, include it to be safe
+            return True
+
+        partition_date = datetime(year, month, 1, tzinfo=timezone.utc)
+
+        # Get current month start
+        now = datetime.now(timezone.utc)
+        current_month_start = now.replace(
+            day=1, hour=0, minute=0, second=0, microsecond=0
+        )
+
+        # Include current month and future partitions
+        return partition_date >= current_month_start
+
+    except (ValueError, TypeError):
+        # If date parsing fails, include it to be safe
+        return True
+
+
+def create_index_on_partitions(
+    apps,  # noqa: F841
+    schema_editor,
+    parent_table: str,
+    index_name: str,
+    columns: str,
+    method: str = "BTREE",
+    where: str = "",
+    all_partitions: bool = True,
+):
+    """
+    Create an index on existing partitions of `parent_table`.
+
+    Args:
+        parent_table: The name of the root table (e.g. "findings").
+        index_name: A short name for the index (will be prefixed per-partition).
+        columns: The parenthesized column list, e.g. "tenant_id, scan_id, status".
+        method: The index method—BTREE, GIN, etc. Defaults to BTREE.
+        where: Optional WHERE clause (without the leading "WHERE"), e.g. "status = 'FAIL'".
+        all_partitions: Whether to create indexes on all partitions or just current/future ones.
+                       Defaults to False (current/future only) to avoid maintenance overhead
+                       on old partitions where the index may not be needed.
+
+    Examples:
+        # Create index only on current and future partitions (recommended for new indexes)
+        create_index_on_partitions(
+            apps, schema_editor,
+            parent_table="findings",
+            index_name="new_performance_idx",
+            columns="tenant_id, status, severity",
+            all_partitions=False  # Default behavior
+        )
+
+        # Create index on all partitions (use when migrating existing critical indexes)
+        create_index_on_partitions(
+            apps, schema_editor,
+            parent_table="findings",
+            index_name="critical_existing_idx",
+            columns="tenant_id, scan_id",
+            all_partitions=True
+        )
+    """
+    with connection.cursor() as cursor:
+        cursor.execute(
+            """
+            SELECT inhrelid::regclass::text
+            FROM pg_inherits
+            WHERE inhparent = %s::regclass
+            """,
+            [parent_table],
+        )
+        partitions = [row[0] for row in cursor.fetchall()]
+
+    where_sql = f" WHERE {where}" if where else ""
+    for partition in partitions:
+        if _should_create_index_on_partition(partition, all_partitions):
+            idx_name = f"{partition.replace('.', '_')}_{index_name}"
+            sql = (
+                f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {idx_name} "
+                f"ON {partition} USING {method} ({columns})"
+                f"{where_sql};"
+            )
+            schema_editor.execute(sql)
+
+
+def drop_index_on_partitions(
+    apps,  # noqa: F841
+    schema_editor,
+    parent_table: str,
+    index_name: str,
+):
+    """
+    Drop the per-partition indexes that were created by create_index_on_partitions.
+
+    Args:
+        parent_table: The name of the root table (e.g. "findings").
+        index_name: The same short name used when creating them.
+    """
+    with connection.cursor() as cursor:
+        cursor.execute(
+            """
+            SELECT inhrelid::regclass::text
+            FROM pg_inherits
+            WHERE inhparent = %s::regclass
+            """,
+            [parent_table],
+        )
+        partitions = [row[0] for row in cursor.fetchall()]
+
+    for partition in partitions:
+        idx_name = f"{partition.replace('.', '_')}_{index_name}"
+        sql = f"DROP INDEX CONCURRENTLY IF EXISTS {idx_name};"
+        schema_editor.execute(sql)
+
+
 # Postgres enum definition for member role
 
 

api/src/backend/api/exceptions.py

@@ -3,7 +3,7 @@ from rest_framework import status
 from rest_framework.exceptions import APIException
 from rest_framework_json_api.exceptions import exception_handler
 from rest_framework_json_api.serializers import ValidationError
-from rest_framework_simplejwt.exceptions import TokenError, InvalidToken
+from rest_framework_simplejwt.exceptions import InvalidToken, TokenError
 
 
 class ModelValidationError(ValidationError):
@@ -32,6 +32,31 @@ class InvitationTokenExpiredException(APIException):
     default_code = "token_expired"
 
 
+# Task Management Exceptions (non-HTTP)
+class TaskManagementError(Exception):
+    """Base exception for task management errors."""
+
+    def __init__(self, task=None):
+        self.task = task
+        super().__init__()
+
+
+class TaskFailedException(TaskManagementError):
+    """Raised when a task has failed."""
+
+
+class TaskNotFoundException(TaskManagementError):
+    """Raised when a task is not found."""
+
+
+class TaskInProgressException(TaskManagementError):
+    """Raised when a task is running but there's no related Task object to return."""
+
+    def __init__(self, task_result=None):
+        self.task_result = task_result
+        super().__init__()
+
+
 def custom_exception_handler(exc, context):
     if isinstance(exc, django_validation_error):
         if hasattr(exc, "error_dict"):
@@ -39,7 +64,12 @@ def custom_exception_handler(exc, context):
         else:
             exc = ValidationError(detail=exc.messages[0], code=exc.code)
     elif isinstance(exc, (TokenError, InvalidToken)):
-        exc.detail["messages"] = [
-            message_item["message"] for message_item in exc.detail["messages"]
-        ]
+        if (
+            hasattr(exc, "detail")
+            and isinstance(exc.detail, dict)
+            and "messages" in exc.detail
+        ):
+            exc.detail["messages"] = [
+                message_item["message"] for message_item in exc.detail["messages"]
+            ]
     return exception_handler(exc, context)

api/src/backend/api/filters.py

@@ -22,7 +22,7 @@ from api.db_utils import (
     StatusEnumField,
 )
 from api.models import (
-    ComplianceOverview,
+    ComplianceRequirementOverview,
     Finding,
     Integration,
     Invitation,
@@ -81,6 +81,114 @@ class ChoiceInFilter(BaseInFilter, ChoiceFilter):
     pass
 
 
+class CommonFindingFilters(FilterSet):
+    # We filter providers from the scan in findings
+    provider = UUIDFilter(field_name="scan__provider__id", lookup_expr="exact")
+    provider__in = UUIDInFilter(field_name="scan__provider__id", lookup_expr="in")
+    provider_type = ChoiceFilter(
+        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
+    )
+    provider_type__in = ChoiceInFilter(
+        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
+    )
+    provider_uid = CharFilter(field_name="scan__provider__uid", lookup_expr="exact")
+    provider_uid__in = CharInFilter(field_name="scan__provider__uid", lookup_expr="in")
+    provider_uid__icontains = CharFilter(
+        field_name="scan__provider__uid", lookup_expr="icontains"
+    )
+    provider_alias = CharFilter(field_name="scan__provider__alias", lookup_expr="exact")
+    provider_alias__in = CharInFilter(
+        field_name="scan__provider__alias", lookup_expr="in"
+    )
+    provider_alias__icontains = CharFilter(
+        field_name="scan__provider__alias", lookup_expr="icontains"
+    )
+
+    updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
+
+    uid = CharFilter(field_name="uid")
+    delta = ChoiceFilter(choices=Finding.DeltaChoices.choices)
+    status = ChoiceFilter(choices=StatusChoices.choices)
+    severity = ChoiceFilter(choices=SeverityChoices)
+    impact = ChoiceFilter(choices=SeverityChoices)
+    muted = BooleanFilter(
+        help_text="If this filter is not provided, muted and non-muted findings will be returned."
+    )
+
+    resources = UUIDInFilter(field_name="resource__id", lookup_expr="in")
+
+    region = CharFilter(method="filter_resource_region")
+    region__in = CharInFilter(field_name="resource_regions", lookup_expr="overlap")
+    region__icontains = CharFilter(
+        field_name="resource_regions", lookup_expr="icontains"
+    )
+
+    service = CharFilter(method="filter_resource_service")
+    service__in = CharInFilter(field_name="resource_services", lookup_expr="overlap")
+    service__icontains = CharFilter(
+        field_name="resource_services", lookup_expr="icontains"
+    )
+
+    resource_uid = CharFilter(field_name="resources__uid")
+    resource_uid__in = CharInFilter(field_name="resources__uid", lookup_expr="in")
+    resource_uid__icontains = CharFilter(
+        field_name="resources__uid", lookup_expr="icontains"
+    )
+
+    resource_name = CharFilter(field_name="resources__name")
+    resource_name__in = CharInFilter(field_name="resources__name", lookup_expr="in")
+    resource_name__icontains = CharFilter(
+        field_name="resources__name", lookup_expr="icontains"
+    )
+
+    resource_type = CharFilter(method="filter_resource_type")
+    resource_type__in = CharInFilter(field_name="resource_types", lookup_expr="overlap")
+    resource_type__icontains = CharFilter(
+        field_name="resources__type", lookup_expr="icontains"
+    )
+
+    # Temporarily disabled until we implement tag filtering in the UI
+    # resource_tag_key = CharFilter(field_name="resources__tags__key")
+    # resource_tag_key__in = CharInFilter(
+    #     field_name="resources__tags__key", lookup_expr="in"
+    # )
+    # resource_tag_key__icontains = CharFilter(
+    #     field_name="resources__tags__key", lookup_expr="icontains"
+    # )
+    # resource_tag_value = CharFilter(field_name="resources__tags__value")
+    # resource_tag_value__in = CharInFilter(
+    #     field_name="resources__tags__value", lookup_expr="in"
+    # )
+    # resource_tag_value__icontains = CharFilter(
+    #     field_name="resources__tags__value", lookup_expr="icontains"
+    # )
+    # resource_tags = CharInFilter(
+    #     method="filter_resource_tag",
+    #     lookup_expr="in",
+    #     help_text="Filter by resource tags `key:value` pairs.\nMultiple values may be "
+    #     "separated by commas.",
+    # )
+
+    def filter_resource_service(self, queryset, name, value):
+        return queryset.filter(resource_services__contains=[value])
+
+    def filter_resource_region(self, queryset, name, value):
+        return queryset.filter(resource_regions__contains=[value])
+
+    def filter_resource_type(self, queryset, name, value):
+        return queryset.filter(resource_types__contains=[value])
+
+    def filter_resource_tag(self, queryset, name, value):
+        overall_query = Q()
+        for key_value_pair in value:
+            tag_key, tag_value = key_value_pair.split(":", 1)
+            overall_query |= Q(
+                resources__tags__key__icontains=tag_key,
+                resources__tags__value__icontains=tag_value,
+            )
+        return queryset.filter(overall_query).distinct()
+
+
 class TenantFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
     updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
@@ -257,91 +365,7 @@ class ResourceFilter(ProviderRelationshipFilterSet):
         return queryset.filter(tags__text_search=value)
 
 
-class FindingFilter(FilterSet):
-    # We filter providers from the scan in findings
-    provider = UUIDFilter(field_name="scan__provider__id", lookup_expr="exact")
-    provider__in = UUIDInFilter(field_name="scan__provider__id", lookup_expr="in")
-    provider_type = ChoiceFilter(
-        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
-    )
-    provider_type__in = ChoiceInFilter(
-        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
-    )
-    provider_uid = CharFilter(field_name="scan__provider__uid", lookup_expr="exact")
-    provider_uid__in = CharInFilter(field_name="scan__provider__uid", lookup_expr="in")
-    provider_uid__icontains = CharFilter(
-        field_name="scan__provider__uid", lookup_expr="icontains"
-    )
-    provider_alias = CharFilter(field_name="scan__provider__alias", lookup_expr="exact")
-    provider_alias__in = CharInFilter(
-        field_name="scan__provider__alias", lookup_expr="in"
-    )
-    provider_alias__icontains = CharFilter(
-        field_name="scan__provider__alias", lookup_expr="icontains"
-    )
-
-    updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
-
-    uid = CharFilter(field_name="uid")
-    delta = ChoiceFilter(choices=Finding.DeltaChoices.choices)
-    status = ChoiceFilter(choices=StatusChoices.choices)
-    severity = ChoiceFilter(choices=SeverityChoices)
-    impact = ChoiceFilter(choices=SeverityChoices)
-
-    resources = UUIDInFilter(field_name="resource__id", lookup_expr="in")
-
-    region = CharFilter(field_name="resources__region")
-    region__in = CharInFilter(field_name="resources__region", lookup_expr="in")
-    region__icontains = CharFilter(
-        field_name="resources__region", lookup_expr="icontains"
-    )
-
-    service = CharFilter(field_name="resources__service")
-    service__in = CharInFilter(field_name="resources__service", lookup_expr="in")
-    service__icontains = CharFilter(
-        field_name="resources__service", lookup_expr="icontains"
-    )
-
-    resource_uid = CharFilter(field_name="resources__uid")
-    resource_uid__in = CharInFilter(field_name="resources__uid", lookup_expr="in")
-    resource_uid__icontains = CharFilter(
-        field_name="resources__uid", lookup_expr="icontains"
-    )
-
-    resource_name = CharFilter(field_name="resources__name")
-    resource_name__in = CharInFilter(field_name="resources__name", lookup_expr="in")
-    resource_name__icontains = CharFilter(
-        field_name="resources__name", lookup_expr="icontains"
-    )
-
-    resource_type = CharFilter(field_name="resources__type")
-    resource_type__in = CharInFilter(field_name="resources__type", lookup_expr="in")
-    resource_type__icontains = CharFilter(
-        field_name="resources__type", lookup_expr="icontains"
-    )
-
-    # Temporarily disabled until we implement tag filtering in the UI
-    # resource_tag_key = CharFilter(field_name="resources__tags__key")
-    # resource_tag_key__in = CharInFilter(
-    #     field_name="resources__tags__key", lookup_expr="in"
-    # )
-    # resource_tag_key__icontains = CharFilter(
-    #     field_name="resources__tags__key", lookup_expr="icontains"
-    # )
-    # resource_tag_value = CharFilter(field_name="resources__tags__value")
-    # resource_tag_value__in = CharInFilter(
-    #     field_name="resources__tags__value", lookup_expr="in"
-    # )
-    # resource_tag_value__icontains = CharFilter(
-    #     field_name="resources__tags__value", lookup_expr="icontains"
-    # )
-    # resource_tags = CharInFilter(
-    #     method="filter_resource_tag",
-    #     lookup_expr="in",
-    #     help_text="Filter by resource tags `key:value` pairs.\nMultiple values may be "
-    #     "separated by commas.",
-    # )
-
+class FindingFilter(CommonFindingFilters):
     scan = UUIDFilter(method="filter_scan_id")
     scan__in = UUIDInFilter(method="filter_scan_id_in")
 
@@ -382,6 +406,15 @@ class FindingFilter(FilterSet):
             },
         }
 
+    def filter_resource_type(self, queryset, name, value):
+        return queryset.filter(resource_types__contains=[value])
+
+    def filter_resource_region(self, queryset, name, value):
+        return queryset.filter(resource_regions__contains=[value])
+
+    def filter_resource_service(self, queryset, name, value):
+        return queryset.filter(resource_services__contains=[value])
+
     def filter_queryset(self, queryset):
         if not (self.data.get("scan") or self.data.get("scan__in")) and not (
             self.data.get("inserted_at")
@@ -500,16 +533,6 @@ class FindingFilter(FilterSet):
 
         return queryset.filter(id__lt=end)
 
-    def filter_resource_tag(self, queryset, name, value):
-        overall_query = Q()
-        for key_value_pair in value:
-            tag_key, tag_value = key_value_pair.split(":", 1)
-            overall_query |= Q(
-                resources__tags__key__icontains=tag_key,
-                resources__tags__value__icontains=tag_value,
-            )
-        return queryset.filter(overall_query).distinct()
-
     @staticmethod
     def maybe_date_to_datetime(value):
         dt = value
@@ -518,6 +541,31 @@ class FindingFilter(FilterSet):
         return dt
 
 
+class LatestFindingFilter(CommonFindingFilters):
+    class Meta:
+        model = Finding
+        fields = {
+            "id": ["exact", "in"],
+            "uid": ["exact", "in"],
+            "delta": ["exact", "in"],
+            "status": ["exact", "in"],
+            "severity": ["exact", "in"],
+            "impact": ["exact", "in"],
+            "check_id": ["exact", "in", "icontains"],
+        }
+        filter_overrides = {
+            FindingDeltaEnumField: {
+                "filter_class": CharFilter,
+            },
+            StatusEnumField: {
+                "filter_class": CharFilter,
+            },
+            SeverityEnumField: {
+                "filter_class": CharFilter,
+            },
+        }
+
+
 class ProviderSecretFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
     updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
@@ -589,12 +637,11 @@ class RoleFilter(FilterSet):
 
 class ComplianceOverviewFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
-    provider_type = ChoiceFilter(choices=Provider.ProviderChoices.choices)
-    provider_type__in = ChoiceInFilter(choices=Provider.ProviderChoices.choices)
-    scan_id = UUIDFilter(field_name="scan__id")
+    scan_id = UUIDFilter(field_name="scan_id")
+    region = CharFilter(field_name="region")
 
     class Meta:
-        model = ComplianceOverview
+        model = ComplianceRequirementOverview
         fields = {
             "inserted_at": ["date", "gte", "lte"],
             "compliance_id": ["exact", "icontains"],
@@ -614,12 +661,6 @@ class ScanSummaryFilter(FilterSet):
         field_name="scan__provider__provider", choices=Provider.ProviderChoices.choices
     )
     region = CharFilter(field_name="region")
-    muted_findings = BooleanFilter(method="filter_muted_findings")
-
-    def filter_muted_findings(self, queryset, name, value):
-        if not value:
-            return queryset.exclude(muted__gt=0)
-        return queryset
 
     class Meta:
         model = ScanSummary
@@ -630,8 +671,6 @@ class ScanSummaryFilter(FilterSet):
 
 
 class ServiceOverviewFilter(ScanSummaryFilter):
-    muted_findings = None
-
     def is_valid(self):
         # Check if at least one of the inserted_at filters is present
         inserted_at_filters = [

api/src/backend/api/management/commands/check_and_fix_socialaccount_sites_migration.py

@@ -0,0 +1,80 @@
+from django.contrib.sites.models import Site
+from django.core.management.base import BaseCommand
+from django.db import DEFAULT_DB_ALIAS, connection, connections, transaction
+from django.db.migrations.recorder import MigrationRecorder
+
+
+def table_exists(table_name):
+    with connection.cursor() as cursor:
+        cursor.execute(
+            """
+                SELECT EXISTS (
+                    SELECT 1 FROM information_schema.tables
+                    WHERE table_name = %s
+                )
+            """,
+            [table_name],
+        )
+        return cursor.fetchone()[0]
+
+
+class Command(BaseCommand):
+    help = "Fix migration inconsistency between socialaccount and sites"
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "--database",
+            default=DEFAULT_DB_ALIAS,
+            help="Specifies the database to operate on.",
+        )
+
+    def handle(self, *args, **options):
+        db = options["database"]
+        connection = connections[db]
+        recorder = MigrationRecorder(connection)
+
+        applied = set(recorder.applied_migrations())
+
+        has_social = ("socialaccount", "0001_initial") in applied
+
+        with connection.cursor() as cursor:
+            cursor.execute(
+                """
+                SELECT EXISTS (
+                    SELECT FROM information_schema.tables
+                    WHERE table_name = 'django_site'
+                );
+            """
+            )
+            site_table_exists = cursor.fetchone()[0]
+
+        if has_social and not site_table_exists:
+            self.stdout.write(
+                f"Detected inconsistency in '{db}'. Creating 'django_site' table manually..."
+            )
+
+            with transaction.atomic(using=db):
+                with connection.schema_editor() as schema_editor:
+                    schema_editor.create_model(Site)
+
+                recorder.record_applied("sites", "0001_initial")
+                recorder.record_applied("sites", "0002_alter_domain_unique")
+
+            self.stdout.write(
+                "Fixed: 'django_site' table created and migrations registered."
+            )
+
+            # Ensure the relationship table also exists
+            if not table_exists("socialaccount_socialapp_sites"):
+                self.stdout.write(
+                    "Detected missing 'socialaccount_socialapp_sites' table. Creating manually..."
+                )
+                with connection.schema_editor() as schema_editor:
+                    from allauth.socialaccount.models import SocialApp
+
+                    schema_editor.create_model(
+                        SocialApp._meta.get_field("sites").remote_field.through
+                    )
+                self.stdout.write(
+                    "Fixed: 'socialaccount_socialapp_sites' table created."
+                )

api/src/backend/api/management/commands/findings.py

@@ -12,6 +12,7 @@ from api.models import (
     Provider,
     Resource,
     ResourceFindingMapping,
+    ResourceScanSummary,
     Scan,
     StatusChoices,
 )
@@ -133,6 +134,7 @@ class Command(BaseCommand):
                         region=random.choice(possible_regions),
                         service=random.choice(possible_services),
                         type=random.choice(possible_types),
+                        inserted_at="2024-10-01T00:00:00Z",
                     )
                 )
 
@@ -181,6 +183,10 @@ class Command(BaseCommand):
                             "servicename": assigned_resource.service,
                             "resourcetype": assigned_resource.type,
                         },
+                        resource_types=[assigned_resource.type],
+                        resource_regions=[assigned_resource.region],
+                        resource_services=[assigned_resource.service],
+                        inserted_at="2024-10-01T00:00:00Z",
                     )
                 )
 
@@ -197,12 +203,22 @@ class Command(BaseCommand):
 
             # Create ResourceFindingMapping
             mappings = []
-            for index, f in enumerate(findings):
+            scan_resource_cache: set[tuple] = set()
+            for index, finding_instance in enumerate(findings):
+                resource_instance = resources[findings_resources_mapping[index]]
                 mappings.append(
                     ResourceFindingMapping(
                         tenant_id=tenant_id,
-                        resource=resources[findings_resources_mapping[index]],
-                        finding=f,
+                        resource=resource_instance,
+                        finding=finding_instance,
+                    )
+                )
+                scan_resource_cache.add(
+                    (
+                        str(resource_instance.id),
+                        resource_instance.service,
+                        resource_instance.region,
+                        resource_instance.type,
                     )
                 )
 
@@ -220,6 +236,38 @@ class Command(BaseCommand):
                     "Resource-finding mappings created successfully.\n\n"
                 )
             )
+
+            with rls_transaction(tenant_id):
+                scan.progress = 99
+                scan.save()
+
+            self.stdout.write(self.style.WARNING("Creating finding filter values..."))
+            resource_scan_summaries = [
+                ResourceScanSummary(
+                    tenant_id=tenant_id,
+                    scan_id=str(scan.id),
+                    resource_id=resource_id,
+                    service=service,
+                    region=region,
+                    resource_type=resource_type,
+                )
+                for resource_id, service, region, resource_type in scan_resource_cache
+            ]
+            num_batches = ceil(len(resource_scan_summaries) / batch_size)
+            with rls_transaction(tenant_id):
+                for i in tqdm(
+                    range(0, len(resource_scan_summaries), batch_size),
+                    total=num_batches,
+                ):
+                    with rls_transaction(tenant_id):
+                        ResourceScanSummary.objects.bulk_create(
+                            resource_scan_summaries[i : i + batch_size],
+                            ignore_conflicts=True,
+                        )
+
+            self.stdout.write(
+                self.style.SUCCESS("Finding filter values created successfully.\n\n")
+            )
         except Exception as e:
             self.stdout.write(self.style.ERROR(f"Failed to populate test data: {e}"))
             scan_state = "failed"

api/src/backend/api/migrations/0014_integrations.py

@@ -50,12 +50,6 @@ class Migration(migrations.Migration):
                 ),
                 ("configuration", models.JSONField(default=dict)),
                 ("_credentials", models.BinaryField(db_column="credentials")),
-                (
-                    "providers",
-                    models.ManyToManyField(
-                        related_name="integrations", to="api.provider", blank=True
-                    ),
-                ),
                 (
                     "tenant",
                     models.ForeignKey(
@@ -124,4 +118,14 @@ class Migration(migrations.Migration):
                 statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
             ),
         ),
+        migrations.AddField(
+            model_name="integration",
+            name="providers",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="integrations",
+                through="api.IntegrationProviderRelationship",
+                to="api.provider",
+            ),
+        ),
     ]

api/src/backend/api/migrations/0015_finding_muted.py

@@ -0,0 +1,26 @@
+# Generated by Django 5.1.5 on 2025-03-25 11:29
+
+from django.db import migrations, models
+
+import api.db_utils
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0014_integrations"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="muted",
+            field=models.BooleanField(default=False),
+        ),
+        migrations.AlterField(
+            model_name="finding",
+            name="status",
+            field=api.db_utils.StatusEnumField(
+                choices=[("FAIL", "Fail"), ("PASS", "Pass"), ("MANUAL", "Manual")]
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0016_finding_compliance_resource_details_and_more.py

@@ -0,0 +1,32 @@
+# Generated by Django 5.1.5 on 2025-03-31 10:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0015_finding_muted"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="compliance",
+            field=models.JSONField(blank=True, default=dict, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="details",
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="metadata",
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="partition",
+            field=models.TextField(blank=True, null=True),
+        ),
+    ]

api/src/backend/api/migrations/0017_m365_provider.py

@@ -0,0 +1,32 @@
+# Generated by Django 5.1.7 on 2025-04-16 08:47
+
+from django.db import migrations
+
+import api.db_utils
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0016_finding_compliance_resource_details_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="provider",
+            name="provider",
+            field=api.db_utils.ProviderEnumField(
+                choices=[
+                    ("aws", "AWS"),
+                    ("azure", "Azure"),
+                    ("gcp", "GCP"),
+                    ("kubernetes", "Kubernetes"),
+                    ("m365", "M365"),
+                ],
+                default="aws",
+            ),
+        ),
+        migrations.RunSQL(
+            "ALTER TYPE provider ADD VALUE IF NOT EXISTS 'm365';",
+            reverse_sql=migrations.RunSQL.noop,
+        ),
+    ]

api/src/backend/api/migrations/0018_resource_scan_summaries.py

@@ -0,0 +1,81 @@
+# Generated by Django 5.1.7 on 2025-05-05 10:01
+
+import uuid
+
+import django.db.models.deletion
+import uuid6
+from django.db import migrations, models
+
+import api.rls
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0017_m365_provider"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ResourceScanSummary",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("scan_id", models.UUIDField(db_index=True, default=uuid6.uuid7)),
+                ("resource_id", models.UUIDField(db_index=True, default=uuid.uuid4)),
+                ("service", models.CharField(max_length=100)),
+                ("region", models.CharField(max_length=100)),
+                ("resource_type", models.CharField(max_length=100)),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "resource_scan_summaries",
+                "indexes": [
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "service"],
+                        name="rss_tenant_scan_svc_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "region"],
+                        name="rss_tenant_scan_reg_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "resource_type"],
+                        name="rss_tenant_scan_type_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "region", "service"],
+                        name="rss_tenant_scan_reg_svc_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "service", "resource_type"],
+                        name="rss_tenant_scan_svc_type_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "region", "resource_type"],
+                        name="rss_tenant_scan_reg_type_idx",
+                    ),
+                ],
+                "unique_together": {("tenant_id", "scan_id", "resource_id")},
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="resourcescansummary",
+            constraint=api.rls.RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_resourcescansummary",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0019_finding_denormalize_resource_fields.py

@@ -0,0 +1,42 @@
+import django.contrib.postgres.fields
+import django.contrib.postgres.indexes
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0018_resource_scan_summaries"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="resource_regions",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=100),
+                blank=True,
+                null=True,
+                size=None,
+            ),
+        ),
+        migrations.AddField(
+            model_name="finding",
+            name="resource_services",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=100),
+                blank=True,
+                null=True,
+                size=None,
+            ),
+        ),
+        migrations.AddField(
+            model_name="finding",
+            name="resource_types",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=100),
+                blank=True,
+                null=True,
+                size=None,
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0020_findings_new_performance_indexes_partitions.py

@@ -0,0 +1,86 @@
+from functools import partial
+
+from django.db import migrations
+
+from api.db_utils import create_index_on_partitions, drop_index_on_partitions
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0019_finding_denormalize_resource_fields"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_service_idx",
+                columns="resource_services",
+                method="GIN",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_service_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_region_idx",
+                columns="resource_regions",
+                method="GIN",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_region_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_rtype_idx",
+                columns="resource_types",
+                method="GIN",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="gin_find_rtype_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_uid_idx",
+            ),
+            reverse_code=partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_uid_idx",
+                columns="uid",
+                method="BTREE",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_filter_idx",
+            ),
+            reverse_code=partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_filter_idx",
+                columns="scan_id, impact, severity, status, check_id, delta",
+                method="BTREE",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0021_findings_new_performance_indexes_parent.py

@@ -0,0 +1,37 @@
+import django.contrib.postgres.indexes
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0020_findings_new_performance_indexes_partitions"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="finding",
+            index=django.contrib.postgres.indexes.GinIndex(
+                fields=["resource_services"], name="gin_find_service_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="finding",
+            index=django.contrib.postgres.indexes.GinIndex(
+                fields=["resource_regions"], name="gin_find_region_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="finding",
+            index=django.contrib.postgres.indexes.GinIndex(
+                fields=["resource_types"], name="gin_find_rtype_idx"
+            ),
+        ),
+        migrations.RemoveIndex(
+            model_name="finding",
+            name="findings_uid_idx",
+        ),
+        migrations.RemoveIndex(
+            model_name="finding",
+            name="findings_filter_idx",
+        ),
+    ]

api/src/backend/api/migrations/0022_scan_summaries_performance_indexes.py

@@ -0,0 +1,38 @@
+# Generated by Django 5.1.8 on 2025-05-12 10:04
+
+from django.contrib.postgres.operations import AddIndexConcurrently
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0021_findings_new_performance_indexes_parent"),
+        ("django_celery_beat", "0019_alter_periodictasks_options"),
+    ]
+
+    operations = [
+        AddIndexConcurrently(
+            model_name="scan",
+            index=models.Index(
+                condition=models.Q(("state", "completed")),
+                fields=["tenant_id", "provider_id", "state", "-inserted_at"],
+                name="scans_prov_state_ins_desc_idx",
+            ),
+        ),
+        AddIndexConcurrently(
+            model_name="scansummary",
+            index=models.Index(
+                fields=["tenant_id", "scan_id", "service"],
+                name="ss_tenant_scan_service_idx",
+            ),
+        ),
+        AddIndexConcurrently(
+            model_name="scansummary",
+            index=models.Index(
+                fields=["tenant_id", "scan_id", "severity"],
+                name="ss_tenant_scan_severity_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0023_resources_lookup_optimization.py

@@ -0,0 +1,28 @@
+# Generated by Django 5.1.8 on 2025-05-12 10:18
+
+from django.contrib.postgres.operations import AddIndexConcurrently
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0022_scan_summaries_performance_indexes"),
+    ]
+
+    operations = [
+        AddIndexConcurrently(
+            model_name="resource",
+            index=models.Index(
+                fields=["tenant_id", "id"], name="resources_tenant_id_idx"
+            ),
+        ),
+        AddIndexConcurrently(
+            model_name="resource",
+            index=models.Index(
+                fields=["tenant_id", "provider_id"],
+                name="resources_tenant_provider_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0024_findings_uid_index_partitions.py

@@ -0,0 +1,29 @@
+from functools import partial
+
+from django.db import migrations
+
+from api.db_utils import create_index_on_partitions, drop_index_on_partitions
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0023_resources_lookup_optimization"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_uid_inserted_idx",
+                columns="tenant_id, uid, inserted_at DESC",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_uid_inserted_idx",
+            ),
+        )
+    ]

api/src/backend/api/migrations/0025_findings_uid_index_parent.py

@@ -0,0 +1,17 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0024_findings_uid_index_partitions"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                fields=["tenant_id", "uid", "-inserted_at"],
+                name="find_tenant_uid_inserted_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0026_provider_secret_gcp_service_account.py

@@ -0,0 +1,14 @@
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0025_findings_uid_index_parent"),
+    ]
+
+    operations = [
+        migrations.RunSQL(
+            "ALTER TYPE provider_secret_type ADD VALUE IF NOT EXISTS 'service_account';",
+            reverse_sql=migrations.RunSQL.noop,
+        ),
+    ]

api/src/backend/api/migrations/0027_compliance_requirement_overviews.py

@@ -0,0 +1,124 @@
+# Generated by Django 5.1.8 on 2025-05-21 11:37
+
+import uuid
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+import api.db_utils
+import api.rls
+from api.rls import RowLevelSecurityConstraint
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0026_provider_secret_gcp_service_account"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ComplianceRequirementOverview",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        primary_key=True,
+                        serialize=False,
+                    ),
+                ),
+                ("inserted_at", models.DateTimeField(auto_now_add=True)),
+                ("compliance_id", models.TextField(blank=False)),
+                ("framework", models.TextField(blank=False)),
+                ("version", models.TextField(blank=True)),
+                ("description", models.TextField(blank=True)),
+                ("region", models.TextField(blank=False)),
+                ("requirement_id", models.TextField(blank=False)),
+                (
+                    "requirement_status",
+                    api.db_utils.StatusEnumField(
+                        choices=[
+                            ("FAIL", "Fail"),
+                            ("PASS", "Pass"),
+                            ("MANUAL", "Manual"),
+                        ]
+                    ),
+                ),
+                ("passed_checks", models.IntegerField(default=0)),
+                ("failed_checks", models.IntegerField(default=0)),
+                ("total_checks", models.IntegerField(default=0)),
+                (
+                    "scan",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="compliance_requirements_overviews",
+                        related_query_name="compliance_requirements_overview",
+                        to="api.scan",
+                    ),
+                ),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "compliance_requirements_overviews",
+                "abstract": False,
+                "indexes": [
+                    models.Index(
+                        fields=["tenant_id", "scan_id"], name="cro_tenant_scan_idx"
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "compliance_id"],
+                        name="cro_scan_comp_idx",
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "scan_id", "compliance_id", "region"],
+                        name="cro_scan_comp_reg_idx",
+                    ),
+                    models.Index(
+                        fields=[
+                            "tenant_id",
+                            "scan_id",
+                            "compliance_id",
+                            "requirement_id",
+                        ],
+                        name="cro_scan_comp_req_idx",
+                    ),
+                    models.Index(
+                        fields=[
+                            "tenant_id",
+                            "scan_id",
+                            "compliance_id",
+                            "requirement_id",
+                            "region",
+                        ],
+                        name="cro_scan_comp_req_reg_idx",
+                    ),
+                ],
+                "constraints": [
+                    models.UniqueConstraint(
+                        fields=(
+                            "tenant_id",
+                            "scan_id",
+                            "compliance_id",
+                            "requirement_id",
+                            "region",
+                        ),
+                        name="unique_tenant_compliance_requirement_overview",
+                    )
+                ],
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="ComplianceRequirementOverview",
+            constraint=RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_compliancerequirementoverview",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0028_findings_check_index_partitions.py

@@ -0,0 +1,29 @@
+from functools import partial
+
+from django.db import migrations
+
+from api.db_utils import create_index_on_partitions, drop_index_on_partitions
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0027_compliance_requirement_overviews"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_check_idx",
+                columns="tenant_id, scan_id, check_id",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_check_idx",
+            ),
+        )
+    ]

api/src/backend/api/migrations/0029_findings_check_index_parent.py

@@ -0,0 +1,17 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0028_findings_check_index_partitions"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                fields=["tenant_id", "scan_id", "check_id"],
+                name="find_tenant_scan_check_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0030_samlconfigurations.py

@@ -0,0 +1,120 @@
+# Generated by Django 5.1.8 on 2025-05-15 09:54
+
+import uuid
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+import api.rls
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0029_findings_check_index_parent"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="SAMLDomainIndex",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("email_domain", models.CharField(max_length=254, unique=True)),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "saml_domain_index",
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="samldomainindex",
+            constraint=models.UniqueConstraint(
+                fields=("email_domain", "tenant"),
+                name="unique_resources_by_email_domain",
+            ),
+        ),
+        migrations.AddConstraint(
+            model_name="samldomainindex",
+            constraint=api.rls.BaseSecurityConstraint(
+                name="statements_on_samldomainindex",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+        migrations.CreateModel(
+            name="SAMLConfiguration",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        primary_key=True,
+                        serialize=False,
+                    ),
+                ),
+                (
+                    "email_domain",
+                    models.CharField(
+                        help_text="Email domain used to identify the tenant, e.g. prowlerdemo.com",
+                        max_length=254,
+                        unique=True,
+                    ),
+                ),
+                (
+                    "metadata_xml",
+                    models.TextField(
+                        help_text="Raw IdP metadata XML to configure SingleSignOnService, certificates, etc."
+                    ),
+                ),
+                ("created_at", models.DateTimeField(auto_now_add=True)),
+                ("updated_at", models.DateTimeField(auto_now=True)),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "saml_configurations",
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="samlconfiguration",
+            constraint=api.rls.RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_samlconfiguration",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+        migrations.AddConstraint(
+            model_name="samlconfiguration",
+            constraint=models.UniqueConstraint(
+                fields=("tenant",), name="unique_samlconfig_per_tenant"
+            ),
+        ),
+        migrations.AlterField(
+            model_name="integration",
+            name="integration_type",
+            field=api.db_utils.IntegrationTypeEnumField(
+                choices=[
+                    ("amazon_s3", "Amazon S3"),
+                    ("aws_security_hub", "AWS Security Hub"),
+                    ("jira", "JIRA"),
+                    ("slack", "Slack"),
+                ]
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0031_lighthouseconfiguration.py

@@ -0,0 +1,106 @@
+# Generated by Django 5.1.10 on 2025-06-12 12:45
+
+import uuid
+
+import django.core.validators
+import django.db.models.deletion
+from django.db import migrations, models
+
+import api.rls
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0030_samlconfigurations"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="LighthouseConfiguration",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        primary_key=True,
+                        serialize=False,
+                    ),
+                ),
+                ("inserted_at", models.DateTimeField(auto_now_add=True)),
+                ("updated_at", models.DateTimeField(auto_now=True)),
+                (
+                    "name",
+                    models.CharField(
+                        help_text="Name of the configuration",
+                        max_length=100,
+                        validators=[django.core.validators.MinLengthValidator(3)],
+                    ),
+                ),
+                (
+                    "api_key",
+                    models.BinaryField(
+                        help_text="Encrypted API key for the LLM service"
+                    ),
+                ),
+                (
+                    "model",
+                    models.CharField(
+                        choices=[
+                            ("gpt-4o-2024-11-20", "GPT-4o v2024-11-20"),
+                            ("gpt-4o-2024-08-06", "GPT-4o v2024-08-06"),
+                            ("gpt-4o-2024-05-13", "GPT-4o v2024-05-13"),
+                            ("gpt-4o", "GPT-4o Default"),
+                            ("gpt-4o-mini-2024-07-18", "GPT-4o Mini v2024-07-18"),
+                            ("gpt-4o-mini", "GPT-4o Mini Default"),
+                        ],
+                        help_text="Must be one of the supported model names",
+                        max_length=50,
+                    ),
+                ),
+                (
+                    "temperature",
+                    models.FloatField(default=0, help_text="Must be between 0 and 1"),
+                ),
+                (
+                    "max_tokens",
+                    models.IntegerField(
+                        default=4000, help_text="Must be between 500 and 5000"
+                    ),
+                ),
+                (
+                    "business_context",
+                    models.TextField(
+                        blank=True,
+                        default="",
+                        help_text="Additional business context for this AI model configuration",
+                    ),
+                ),
+                ("is_active", models.BooleanField(default=True)),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "lighthouse_configurations",
+                "abstract": False,
+                "constraints": [
+                    models.UniqueConstraint(
+                        fields=("tenant_id",),
+                        name="unique_lighthouse_config_per_tenant",
+                    ),
+                ],
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="lighthouseconfiguration",
+            constraint=api.rls.RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_lighthouseconfiguration",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+    ]

api/src/backend/api/models.py

@@ -1,12 +1,20 @@
 import json
+import logging
 import re
+import xml.etree.ElementTree as ET
 from uuid import UUID, uuid4
 
-from cryptography.fernet import Fernet
+from allauth.socialaccount.models import SocialApp
+from config.custom_logging import BackendLogger
+from config.settings.social_login import SOCIALACCOUNT_PROVIDERS
+from cryptography.fernet import Fernet, InvalidToken
 from django.conf import settings
 from django.contrib.auth.models import AbstractBaseUser
+from django.contrib.postgres.fields import ArrayField
 from django.contrib.postgres.indexes import GinIndex
 from django.contrib.postgres.search import SearchVector, SearchVectorField
+from django.contrib.sites.models import Site
+from django.core.exceptions import ValidationError
 from django.core.validators import MinLengthValidator
 from django.db import models
 from django.db.models import Q
@@ -18,6 +26,7 @@ from psqlextra.models import PostgresPartitionedModel
 from psqlextra.types import PostgresPartitioningMethod
 from uuid6 import uuid7
 
+from api.db_router import MainRouter
 from api.db_utils import (
     CustomUserManager,
     FindingDeltaEnumField,
@@ -48,6 +57,8 @@ fernet = Fernet(settings.SECRETS_ENCRYPTION_KEY.encode())
 # Convert Prowler Severity enum to Django TextChoices
 SeverityChoices = enum_to_choices(Severity)
 
+logger = logging.getLogger(BackendLogger.API)
+
 
 class StatusChoices(models.TextChoices):
     """
@@ -59,7 +70,6 @@ class StatusChoices(models.TextChoices):
     FAIL = "FAIL", _("Fail")
     PASS = "PASS", _("Pass")
     MANUAL = "MANUAL", _("Manual")
-    MUTED = "MUTED", _("Muted")
 
 
 class StateChoices(models.TextChoices):
@@ -192,6 +202,7 @@ class Provider(RowLevelSecurityProtectedModel):
         AZURE = "azure", _("Azure")
         GCP = "gcp", _("GCP")
         KUBERNETES = "kubernetes", _("Kubernetes")
+        M365 = "m365", _("M365")
 
     @staticmethod
     def validate_aws_uid(value):
@@ -215,6 +226,19 @@ class Provider(RowLevelSecurityProtectedModel):
                 pointer="/data/attributes/uid",
             )
 
+    @staticmethod
+    def validate_m365_uid(value):
+        if not re.match(
+            r"""^(?!-)[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?(?:\.(?!-)[A-Za-z0-9]"""
+            r"""(?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?)*\.[A-Za-z]{2,}$""",
+            value,
+        ):
+            raise ModelValidationError(
+                detail="M365 domain ID must be a valid domain.",
+                code="m365-uid",
+                pointer="/data/attributes/uid",
+            )
+
     @staticmethod
     def validate_gcp_uid(value):
         if not re.match(r"^[a-z][a-z0-9-]{5,29}$", value):
@@ -228,7 +252,7 @@ class Provider(RowLevelSecurityProtectedModel):
     @staticmethod
     def validate_kubernetes_uid(value):
         if not re.match(
-            r"^[a-z0-9][A-Za-z0-9_.:\/-]{1,250}$",
+            r"^[a-zA-Z0-9][a-zA-Z0-9._@:\/-]{1,250}$",
             value,
         ):
             raise ModelValidationError(
@@ -416,6 +440,7 @@ class Scan(RowLevelSecurityProtectedModel):
         PeriodicTask, on_delete=models.CASCADE, null=True, blank=True
     )
     output_location = models.CharField(blank=True, null=True, max_length=200)
+
     # TODO: mutelist foreign key
 
     class Meta(RowLevelSecurityProtectedModel.Meta):
@@ -438,6 +463,11 @@ class Scan(RowLevelSecurityProtectedModel):
                 fields=["tenant_id", "provider_id", "state", "inserted_at"],
                 name="scans_prov_state_insert_idx",
             ),
+            models.Index(
+                fields=["tenant_id", "provider_id", "state", "-inserted_at"],
+                condition=Q(state=StateChoices.COMPLETED),
+                name="scans_prov_state_ins_desc_idx",
+            ),
         ]
 
     class JSONAPIMeta:
@@ -519,6 +549,11 @@ class Resource(RowLevelSecurityProtectedModel):
         editable=False,
     )
 
+    metadata = models.TextField(blank=True, null=True)
+    details = models.TextField(blank=True, null=True)
+    partition = models.TextField(blank=True, null=True)
+
+    # Relationships
     tags = models.ManyToManyField(
         ResourceTag,
         verbose_name="Tags associated with the resource, by provider",
@@ -559,6 +594,11 @@ class Resource(RowLevelSecurityProtectedModel):
                 name="resource_tenant_metadata_idx",
             ),
             GinIndex(fields=["text_search"], name="gin_resources_search_idx"),
+            models.Index(fields=["tenant_id", "id"], name="resources_tenant_id_idx"),
+            models.Index(
+                fields=["tenant_id", "provider_id"],
+                name="resources_tenant_provider_idx",
+            ),
         ]
 
         constraints = [
@@ -656,6 +696,23 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
     tags = models.JSONField(default=dict, null=True, blank=True)
     check_id = models.CharField(max_length=100, blank=False, null=False)
     check_metadata = models.JSONField(default=dict, null=False)
+    muted = models.BooleanField(default=False, null=False)
+    compliance = models.JSONField(default=dict, null=True, blank=True)
+
+    # Denormalize resource data for performance
+    resource_regions = ArrayField(
+        models.CharField(max_length=100), blank=True, null=True
+    )
+    resource_services = ArrayField(
+        models.CharField(max_length=100),
+        blank=True,
+        null=True,
+    )
+    resource_types = ArrayField(
+        models.CharField(max_length=100),
+        blank=True,
+        null=True,
+    )
 
     # Relationships
     scan = models.ForeignKey(to=Scan, related_name="findings", on_delete=models.CASCADE)
@@ -697,18 +754,6 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
         ]
 
         indexes = [
-            models.Index(fields=["uid"], name="findings_uid_idx"),
-            models.Index(
-                fields=[
-                    "scan_id",
-                    "impact",
-                    "severity",
-                    "status",
-                    "check_id",
-                    "delta",
-                ],
-                name="findings_filter_idx",
-            ),
             models.Index(fields=["tenant_id", "id"], name="findings_tenant_and_id_idx"),
             GinIndex(fields=["text_search"], name="gin_findings_search_idx"),
             models.Index(fields=["tenant_id", "scan_id"], name="find_tenant_scan_idx"),
@@ -720,19 +765,46 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
                 condition=Q(delta="new"),
                 name="find_delta_new_idx",
             ),
+            models.Index(
+                fields=["tenant_id", "uid", "-inserted_at"],
+                name="find_tenant_uid_inserted_idx",
+            ),
+            GinIndex(fields=["resource_services"], name="gin_find_service_idx"),
+            GinIndex(fields=["resource_regions"], name="gin_find_region_idx"),
+            GinIndex(fields=["resource_types"], name="gin_find_rtype_idx"),
+            models.Index(
+                fields=["tenant_id", "scan_id", "check_id"],
+                name="find_tenant_scan_check_idx",
+            ),
         ]
 
     class JSONAPIMeta:
         resource_name = "findings"
 
     def add_resources(self, resources: list[Resource] | None):
-        # Add new relationships with the tenant_id field
+        if not resources:
+            return
+
+        self.resource_regions = self.resource_regions or []
+        self.resource_services = self.resource_services or []
+        self.resource_types = self.resource_types or []
+
+        # Deduplication
+        regions = set(self.resource_regions)
+        services = set(self.resource_services)
+        types = set(self.resource_types)
+
         for resource in resources:
             ResourceFindingMapping.objects.update_or_create(
                 resource=resource, finding=self, tenant_id=self.tenant_id
             )
+            regions.add(resource.region)
+            services.add(resource.service)
+            types.add(resource.type)
 
-        # Save the instance
+        self.resource_regions = list(regions)
+        self.resource_services = list(services)
+        self.resource_types = list(types)
         self.save()
 
 
@@ -792,6 +864,7 @@ class ProviderSecret(RowLevelSecurityProtectedModel):
     class TypeChoices(models.TextChoices):
         STATIC = "static", _("Key-value pairs")
         ROLE = "role", _("Role assumption")
+        SERVICE_ACCOUNT = "service_account", _("GCP Service Account Key")
 
     id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
     inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
@@ -1084,6 +1157,78 @@ class ComplianceOverview(RowLevelSecurityProtectedModel):
         resource_name = "compliance-overviews"
 
 
+class ComplianceRequirementOverview(RowLevelSecurityProtectedModel):
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
+    inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
+    compliance_id = models.TextField(blank=False)
+    framework = models.TextField(blank=False)
+    version = models.TextField(blank=True)
+    description = models.TextField(blank=True)
+    region = models.TextField(blank=False)
+
+    requirement_id = models.TextField(blank=False)
+    requirement_status = StatusEnumField(choices=StatusChoices)
+    passed_checks = models.IntegerField(default=0)
+    failed_checks = models.IntegerField(default=0)
+    total_checks = models.IntegerField(default=0)
+
+    scan = models.ForeignKey(
+        Scan,
+        on_delete=models.CASCADE,
+        related_name="compliance_requirements_overviews",
+        related_query_name="compliance_requirements_overview",
+    )
+
+    class Meta(RowLevelSecurityProtectedModel.Meta):
+        db_table = "compliance_requirements_overviews"
+
+        constraints = [
+            models.UniqueConstraint(
+                fields=(
+                    "tenant_id",
+                    "scan_id",
+                    "compliance_id",
+                    "requirement_id",
+                    "region",
+                ),
+                name="unique_tenant_compliance_requirement_overview",
+            ),
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "DELETE"],
+            ),
+        ]
+        indexes = [
+            models.Index(fields=["tenant_id", "scan_id"], name="cro_tenant_scan_idx"),
+            models.Index(
+                fields=["tenant_id", "scan_id", "compliance_id"],
+                name="cro_scan_comp_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "compliance_id", "region"],
+                name="cro_scan_comp_reg_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "compliance_id", "requirement_id"],
+                name="cro_scan_comp_req_idx",
+            ),
+            models.Index(
+                fields=[
+                    "tenant_id",
+                    "scan_id",
+                    "compliance_id",
+                    "requirement_id",
+                    "region",
+                ],
+                name="cro_scan_comp_req_reg_idx",
+            ),
+        ]
+
+    class JSONAPIMeta:
+        resource_name = "compliance-requirements-overviews"
+
+
 class ScanSummary(RowLevelSecurityProtectedModel):
     objects = ActiveProviderManager()
     all_objects = models.Manager()
@@ -1134,7 +1279,15 @@ class ScanSummary(RowLevelSecurityProtectedModel):
             models.Index(
                 fields=["tenant_id", "scan_id"],
                 name="scan_summaries_tenant_scan_idx",
-            )
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "service"],
+                name="ss_tenant_scan_service_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "severity"],
+                name="ss_tenant_scan_severity_idx",
+            ),
         ]
 
     class JSONAPIMeta:
@@ -1144,7 +1297,6 @@ class ScanSummary(RowLevelSecurityProtectedModel):
 class Integration(RowLevelSecurityProtectedModel):
     class IntegrationChoices(models.TextChoices):
         S3 = "amazon_s3", _("Amazon S3")
-        SAML = "saml", _("SAML")
         AWS_SECURITY_HUB = "aws_security_hub", _("AWS Security Hub")
         JIRA = "jira", _("JIRA")
         SLACK = "slack", _("Slack")
@@ -1216,3 +1368,394 @@ class IntegrationProviderRelationship(RowLevelSecurityProtectedModel):
                 statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
             ),
         ]
+
+
+class SAMLDomainIndex(models.Model):
+    """
+    Public index of SAML domains. No RLS. Used for fast lookup in SAML login flow.
+    """
+
+    email_domain = models.CharField(max_length=254, unique=True)
+    tenant = models.ForeignKey("Tenant", on_delete=models.CASCADE)
+
+    class Meta:
+        db_table = "saml_domain_index"
+
+        constraints = [
+            models.UniqueConstraint(
+                fields=("email_domain", "tenant"),
+                name="unique_resources_by_email_domain",
+            ),
+            BaseSecurityConstraint(
+                name="statements_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+
+
+class SAMLConfiguration(RowLevelSecurityProtectedModel):
+    """
+    Stores per-tenant SAML settings, including email domain and IdP metadata.
+    Automatically syncs to a SocialApp instance on save.
+
+    Note:
+    This model exists to provide a tenant-aware abstraction over SAML configuration.
+    It supports row-level security, custom validation, and metadata parsing, enabling
+    Prowler to expose a clean API and admin interface for managing SAML integrations.
+
+    Although Django Allauth uses the SocialApp model to store provider configuration,
+    it is not designed for multi-tenant use. SocialApp lacks support for tenant scoping,
+    email domain mapping, and structured metadata handling.
+
+    By managing SAMLConfiguration separately, we ensure:
+        - Strong isolation between tenants via RLS.
+        - Ownership of raw IdP metadata and its validation.
+        - An explicit link between SAML config and business-level identifiers (e.g. email domain).
+        - Programmatic transformation into the SocialApp format used by Allauth.
+
+    In short, this model acts as a secure and user-friendly layer over Allauth's lower-level primitives.
+    """
+
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
+    email_domain = models.CharField(
+        max_length=254,
+        unique=True,
+        help_text="Email domain used to identify the tenant, e.g. prowlerdemo.com",
+    )
+    metadata_xml = models.TextField(
+        help_text="Raw IdP metadata XML to configure SingleSignOnService, certificates, etc."
+    )
+    created_at = models.DateTimeField(auto_now_add=True)
+    updated_at = models.DateTimeField(auto_now=True)
+
+    class JSONAPIMeta:
+        resource_name = "saml-configurations"
+
+    class Meta:
+        db_table = "saml_configurations"
+
+        constraints = [
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+            # 1 config per tenant
+            models.UniqueConstraint(
+                fields=["tenant"],
+                name="unique_samlconfig_per_tenant",
+            ),
+        ]
+
+    def clean(self, old_email_domain=None):
+        # Domain must not contain @
+        if "@" in self.email_domain:
+            raise ValidationError({"email_domain": "Domain must not contain @"})
+
+        # Enforce at most one config per tenant
+        qs = SAMLConfiguration.objects.filter(tenant=self.tenant)
+        # Exclude ourselves in case of update
+        if self.pk:
+            qs = qs.exclude(pk=self.pk)
+        if qs.exists():
+            raise ValidationError(
+                {"tenant": "A SAML configuration already exists for this tenant."}
+            )
+
+        # The email domain must be unique in the entire system
+        qs = SAMLConfiguration.objects.using(MainRouter.admin_db).filter(
+            email_domain__iexact=self.email_domain
+        )
+        if qs.exists() and old_email_domain != self.email_domain:
+            raise ValidationError(
+                {"tenant": "There is a problem with your email domain."}
+            )
+
+    def save(self, *args, **kwargs):
+        self.email_domain = self.email_domain.strip().lower()
+        is_create = not SAMLConfiguration.objects.filter(pk=self.pk).exists()
+
+        if not is_create:
+            old = SAMLConfiguration.objects.get(pk=self.pk)
+            old_email_domain = old.email_domain
+            old_metadata_xml = old.metadata_xml
+        else:
+            old_email_domain = None
+            old_metadata_xml = None
+
+        self.clean(old_email_domain)
+        super().save(*args, **kwargs)
+
+        if is_create or (
+            old_email_domain != self.email_domain
+            or old_metadata_xml != self.metadata_xml
+        ):
+            self._sync_social_app(old_email_domain)
+
+        # Sync the public index
+        if not is_create and old_email_domain and old_email_domain != self.email_domain:
+            SAMLDomainIndex.objects.filter(email_domain=old_email_domain).delete()
+
+        # Create/update the new domain index
+        SAMLDomainIndex.objects.update_or_create(
+            email_domain=self.email_domain, defaults={"tenant": self.tenant}
+        )
+
+    def _parse_metadata(self):
+        """
+        Parse the raw IdP metadata XML and extract:
+            - entity_id
+            - sso_url
+            - slo_url (may be None)
+            - x509cert (required)
+        """
+        ns = {
+            "md": "urn:oasis:names:tc:SAML:2.0:metadata",
+            "ds": "http://www.w3.org/2000/09/xmldsig#",
+        }
+        try:
+            root = ET.fromstring(self.metadata_xml)
+        except ET.ParseError as e:
+            raise ValidationError({"metadata_xml": f"Invalid XML: {e}"})
+
+        # Entity ID
+        entity_id = root.attrib.get("entityID")
+
+        # SSO endpoint (must exist)
+        sso = root.find(".//md:IDPSSODescriptor/md:SingleSignOnService", ns)
+        if sso is None or "Location" not in sso.attrib:
+            raise ValidationError(
+                {"metadata_xml": "Missing SingleSignOnService in metadata."}
+            )
+        sso_url = sso.attrib["Location"]
+
+        # SLO endpoint (optional)
+        slo = root.find(".//md:IDPSSODescriptor/md:SingleLogoutService", ns)
+        slo_url = slo.attrib.get("Location") if slo is not None else None
+
+        # X.509 certificate (required)
+        cert = root.find(
+            './/md:KeyDescriptor[@use="signing"]/ds:KeyInfo/ds:X509Data/ds:X509Certificate',
+            ns,
+        )
+        if cert is None or not cert.text or not cert.text.strip():
+            raise ValidationError(
+                {
+                    "metadata_xml": 'Metadata must include a <ds:X509Certificate> under <KeyDescriptor use="signing">.'
+                }
+            )
+        x509cert = cert.text.strip()
+
+        return {
+            "entity_id": entity_id,
+            "sso_url": sso_url,
+            "slo_url": slo_url,
+            "x509cert": x509cert,
+        }
+
+    def _sync_social_app(self, previous_email_domain=None):
+        """
+        Create or update the corresponding SocialApp based on email_domain.
+        If the domain changed, update the matching SocialApp.
+        """
+        idp_settings = self._parse_metadata()
+        settings_dict = SOCIALACCOUNT_PROVIDERS["saml"].copy()
+        settings_dict["idp"] = idp_settings
+
+        current_site = Site.objects.get(id=settings.SITE_ID)
+
+        social_app_qs = SocialApp.objects.filter(
+            provider="saml", client_id=previous_email_domain or self.email_domain
+        )
+
+        if social_app_qs.exists():
+            social_app = social_app_qs.first()
+            social_app.client_id = self.email_domain
+            social_app.name = f"{self.tenant.name} SAML ({self.email_domain})"
+            social_app.settings = settings_dict
+            social_app.save()
+            social_app.sites.set([current_site])
+        else:
+            social_app = SocialApp.objects.create(
+                provider="saml",
+                client_id=self.email_domain,
+                name=f"{self.tenant.name} SAML ({self.email_domain})",
+                settings=settings_dict,
+            )
+            social_app.sites.set([current_site])
+
+
+class ResourceScanSummary(RowLevelSecurityProtectedModel):
+    scan_id = models.UUIDField(default=uuid7, db_index=True)
+    resource_id = models.UUIDField(default=uuid4, db_index=True)
+    service = models.CharField(max_length=100)
+    region = models.CharField(max_length=100)
+    resource_type = models.CharField(max_length=100)
+
+    class Meta:
+        db_table = "resource_scan_summaries"
+        unique_together = (("tenant_id", "scan_id", "resource_id"),)
+
+        indexes = [
+            # Single-dimension lookups:
+            models.Index(
+                fields=["tenant_id", "scan_id", "service"],
+                name="rss_tenant_scan_svc_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "region"],
+                name="rss_tenant_scan_reg_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "resource_type"],
+                name="rss_tenant_scan_type_idx",
+            ),
+            # Two-dimension cross-filters:
+            models.Index(
+                fields=["tenant_id", "scan_id", "region", "service"],
+                name="rss_tenant_scan_reg_svc_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "service", "resource_type"],
+                name="rss_tenant_scan_svc_type_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "scan_id", "region", "resource_type"],
+                name="rss_tenant_scan_reg_type_idx",
+            ),
+        ]
+
+        constraints = [
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+
+
+class LighthouseConfiguration(RowLevelSecurityProtectedModel):
+    """
+    Stores configuration and API keys for LLM services.
+    """
+
+    class ModelChoices(models.TextChoices):
+        GPT_4O_2024_11_20 = "gpt-4o-2024-11-20", _("GPT-4o v2024-11-20")
+        GPT_4O_2024_08_06 = "gpt-4o-2024-08-06", _("GPT-4o v2024-08-06")
+        GPT_4O_2024_05_13 = "gpt-4o-2024-05-13", _("GPT-4o v2024-05-13")
+        GPT_4O = "gpt-4o", _("GPT-4o Default")
+        GPT_4O_MINI_2024_07_18 = "gpt-4o-mini-2024-07-18", _("GPT-4o Mini v2024-07-18")
+        GPT_4O_MINI = "gpt-4o-mini", _("GPT-4o Mini Default")
+
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
+    inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
+    updated_at = models.DateTimeField(auto_now=True, editable=False)
+
+    name = models.CharField(
+        max_length=100,
+        validators=[MinLengthValidator(3)],
+        blank=False,
+        null=False,
+        help_text="Name of the configuration",
+    )
+    api_key = models.BinaryField(
+        blank=False, null=False, help_text="Encrypted API key for the LLM service"
+    )
+    model = models.CharField(
+        max_length=50,
+        choices=ModelChoices.choices,
+        blank=False,
+        null=False,
+        default=ModelChoices.GPT_4O_2024_08_06,
+        help_text="Must be one of the supported model names",
+    )
+    temperature = models.FloatField(default=0, help_text="Must be between 0 and 1")
+    max_tokens = models.IntegerField(
+        default=4000, help_text="Must be between 500 and 5000"
+    )
+    business_context = models.TextField(
+        blank=True,
+        null=False,
+        default="",
+        help_text="Additional business context for this AI model configuration",
+    )
+    is_active = models.BooleanField(default=True)
+
+    def __str__(self):
+        return self.name
+
+    def clean(self):
+        super().clean()
+
+        # Validate temperature
+        if not 0 <= self.temperature <= 1:
+            raise ModelValidationError(
+                detail="Temperature must be between 0 and 1",
+                code="invalid_temperature",
+                pointer="/data/attributes/temperature",
+            )
+
+        # Validate max_tokens
+        if not 500 <= self.max_tokens <= 5000:
+            raise ModelValidationError(
+                detail="Max tokens must be between 500 and 5000",
+                code="invalid_max_tokens",
+                pointer="/data/attributes/max_tokens",
+            )
+
+    @property
+    def api_key_decoded(self):
+        """Return the decrypted API key, or None if unavailable or invalid."""
+        if not self.api_key:
+            return None
+
+        try:
+            decrypted_key = fernet.decrypt(bytes(self.api_key))
+            return decrypted_key.decode()
+
+        except InvalidToken:
+            logger.warning("Invalid token while decrypting API key.")
+        except Exception as e:
+            logger.exception("Unexpected error while decrypting API key: %s", e)
+
+    @api_key_decoded.setter
+    def api_key_decoded(self, value):
+        """Store the encrypted API key."""
+        if not value:
+            raise ModelValidationError(
+                detail="API key is required",
+                code="invalid_api_key",
+                pointer="/data/attributes/api_key",
+            )
+
+        # Validate OpenAI API key format
+        openai_key_pattern = r"^sk-[\w-]+T3BlbkFJ[\w-]+$"
+        if not re.match(openai_key_pattern, value):
+            raise ModelValidationError(
+                detail="Invalid OpenAI API key format.",
+                code="invalid_api_key",
+                pointer="/data/attributes/api_key",
+            )
+        self.api_key = fernet.encrypt(value.encode())
+
+    def save(self, *args, **kwargs):
+        self.full_clean()
+        super().save(*args, **kwargs)
+
+    class Meta(RowLevelSecurityProtectedModel.Meta):
+        db_table = "lighthouse_configurations"
+
+        constraints = [
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+            # Add unique constraint for name within a tenant
+            models.UniqueConstraint(
+                fields=["tenant_id"], name="unique_lighthouse_config_per_tenant"
+            ),
+        ]
+
+    class JSONAPIMeta:
+        resource_name = "lighthouse-configurations"

api/src/backend/api/pagination.py

@@ -1,4 +1,4 @@
-from rest_framework_json_api.pagination import JsonApiPageNumberPagination
+from drf_spectacular_jsonapi.schemas.pagination import JsonApiPageNumberPagination
 
 
 class ComplianceOverviewPagination(JsonApiPageNumberPagination):

api/src/backend/api/signals.py

@@ -1,12 +1,12 @@
 from celery import states
 from celery.signals import before_task_publish
+from config.celery import celery_app
 from django.db.models.signals import post_delete
 from django.dispatch import receiver
-from django_celery_beat.models import PeriodicTask
 from django_celery_results.backends.database import DatabaseBackend
 
+from api.db_utils import delete_related_daily_task
 from api.models import Provider
-from config.celery import celery_app
 
 
 def create_task_result_on_publish(sender=None, headers=None, **kwargs):  # noqa: F841
@@ -31,5 +31,4 @@ before_task_publish.connect(
 @receiver(post_delete, sender=Provider)
 def delete_provider_scan_task(sender, instance, **kwargs):  # noqa: F841
     # Delete the associated periodic task when the provider is deleted
-    task_name = f"scan-perform-scheduled-{instance.id}"
-    PeriodicTask.objects.filter(name=task_name).delete()
+    delete_related_daily_task(instance.id)

api/src/backend/api/tests/test_adapters.py

@@ -0,0 +1,82 @@
+from unittest.mock import MagicMock
+
+import pytest
+from allauth.socialaccount.models import SocialLogin
+from django.contrib.auth import get_user_model
+
+from api.adapters import ProwlerSocialAccountAdapter
+from api.db_router import MainRouter
+from api.models import Membership, SAMLConfiguration, Tenant
+
+User = get_user_model()
+
+
+@pytest.mark.django_db
+class TestProwlerSocialAccountAdapter:
+    def test_get_user_by_email_returns_user(self, create_test_user):
+        adapter = ProwlerSocialAccountAdapter()
+        user = adapter.get_user_by_email(create_test_user.email)
+        assert user == create_test_user
+
+    def test_get_user_by_email_returns_none_for_unknown_email(self):
+        adapter = ProwlerSocialAccountAdapter()
+        assert adapter.get_user_by_email("notfound@example.com") is None
+
+    def test_pre_social_login_links_existing_user(self, create_test_user, rf):
+        adapter = ProwlerSocialAccountAdapter()
+
+        sociallogin = MagicMock(spec=SocialLogin)
+        sociallogin.account = MagicMock()
+        sociallogin.account.provider = "saml"
+        sociallogin.account.extra_data = {}
+        sociallogin.user = create_test_user
+        sociallogin.connect = MagicMock()
+
+        adapter.pre_social_login(rf.get("/"), sociallogin)
+
+        call_args = sociallogin.connect.call_args
+        assert call_args is not None
+
+        called_request, called_user = call_args[0]
+        assert called_request.path == "/"
+        assert called_user.email == create_test_user.email
+
+    def test_pre_social_login_no_link_if_email_missing(self, rf):
+        adapter = ProwlerSocialAccountAdapter()
+
+        sociallogin = MagicMock(spec=SocialLogin)
+        sociallogin.account = MagicMock()
+        sociallogin.account.provider = "github"
+        sociallogin.account.extra_data = {}
+        sociallogin.connect = MagicMock()
+
+        adapter.pre_social_login(rf.get("/"), sociallogin)
+
+        sociallogin.connect.assert_not_called()
+
+    def test_save_user_saml_flow(
+        self,
+        rf,
+        saml_setup,
+        saml_sociallogin,
+    ):
+        adapter = ProwlerSocialAccountAdapter()
+        request = rf.get("/")
+        saml_sociallogin.user.email = saml_setup["email"]
+
+        tenant = Tenant.objects.using(MainRouter.admin_db).get(
+            id=saml_setup["tenant_id"]
+        )
+        saml_config = SAMLConfiguration.objects.using(MainRouter.admin_db).get(
+            tenant=tenant
+        )
+        assert saml_config.email_domain == saml_setup["domain"]
+
+        user = adapter.save_user(request, saml_sociallogin)
+
+        assert user.email == saml_setup["email"]
+        assert (
+            Membership.objects.using(MainRouter.admin_db)
+            .filter(user=user, tenant=tenant)
+            .exists()
+        )

api/src/backend/api/tests/test_compliance.py

@@ -1,12 +1,12 @@
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 from api.compliance import (
+    generate_compliance_overview_template,
+    generate_scan_compliance,
     get_prowler_provider_checks,
     get_prowler_provider_compliance,
-    load_prowler_compliance,
     load_prowler_checks,
-    generate_scan_compliance,
-    generate_compliance_overview_template,
+    load_prowler_compliance,
 )
 from api.models import Provider
 
@@ -69,7 +69,7 @@ class TestCompliance:
 
         load_prowler_compliance()
 
-        from api.compliance import PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE, PROWLER_CHECKS
+        from api.compliance import PROWLER_CHECKS, PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE
 
         assert PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE == {
             "template_key": "template_value"
@@ -218,6 +218,10 @@ class TestCompliance:
             Description="Description of requirement 1",
             Attributes=[],
             Checks=["check1", "check2"],
+            Tactics=["tactic1"],
+            SubTechniques=["subtechnique1"],
+            Platforms=["platform1"],
+            TechniqueURL="https://example.com",
         )
         requirement2 = MagicMock(
             Id="requirement2",
@@ -225,6 +229,10 @@ class TestCompliance:
             Description="Description of requirement 2",
             Attributes=[],
             Checks=[],
+            Tactics=[],
+            SubTechniques=[],
+            Platforms=[],
+            TechniqueURL="",
         )
         compliance1 = MagicMock(
             Requirements=[requirement1, requirement2],
@@ -247,6 +255,10 @@ class TestCompliance:
                         "requirement1": {
                             "name": "Requirement 1",
                             "description": "Description of requirement 1",
+                            "tactics": ["tactic1"],
+                            "subtechniques": ["subtechnique1"],
+                            "platforms": ["platform1"],
+                            "technique_url": "https://example.com",
                             "attributes": [],
                             "checks": {"check1": None, "check2": None},
                             "checks_status": {
@@ -260,6 +272,10 @@ class TestCompliance:
                         "requirement2": {
                             "name": "Requirement 2",
                             "description": "Description of requirement 2",
+                            "tactics": [],
+                            "subtechniques": [],
+                            "platforms": [],
+                            "technique_url": "",
                             "attributes": [],
                             "checks": {},
                             "checks_status": {
@@ -268,7 +284,7 @@ class TestCompliance:
                                 "manual": 0,
                                 "total": 0,
                             },
-                            "status": "PASS",
+                            "status": "MANUAL",
                         },
                     },
                     "requirements_status": {

api/src/backend/api/tests/test_db_utils.py

@@ -3,9 +3,13 @@ from enum import Enum
 from unittest.mock import patch
 
 import pytest
+from django.conf import settings
+from freezegun import freeze_time
 
 from api.db_utils import (
+    _should_create_index_on_partition,
     batch_delete,
+    create_objects_in_batches,
     enum_to_choices,
     generate_random_token,
     one_week_from_now,
@@ -131,9 +135,95 @@ class TestBatchDelete:
         return provider_count
 
     @pytest.mark.django_db
-    def test_batch_delete(self, create_test_providers):
+    def test_batch_delete(self, tenants_fixture, create_test_providers):
+        tenant_id = str(tenants_fixture[0].id)
         _, summary = batch_delete(
-            Provider.objects.all(), batch_size=create_test_providers // 2
+            tenant_id, Provider.objects.all(), batch_size=create_test_providers // 2
         )
         assert Provider.objects.all().count() == 0
         assert summary == {"api.Provider": create_test_providers}
+
+
+class TestShouldCreateIndexOnPartition:
+    @freeze_time("2025-05-15 00:00:00Z")
+    @pytest.mark.parametrize(
+        "partition_name, all_partitions, expected",
+        [
+            ("any_name", True, True),
+            ("findings_default", True, True),
+            ("findings_2022_jan", True, True),
+            ("foo_bar", False, True),
+            ("findings_2025_MAY", False, True),
+            ("findings_2025_may", False, True),
+            ("findings_2025_jun", False, True),
+            ("findings_2025_apr", False, False),
+            ("findings_2025_xyz", False, True),
+        ],
+    )
+    def test_partition_inclusion_logic(self, partition_name, all_partitions, expected):
+        assert (
+            _should_create_index_on_partition(partition_name, all_partitions)
+            is expected
+        )
+
+    @freeze_time("2025-05-15 00:00:00Z")
+    def test_invalid_date_components(self):
+        # even if regex matches but int conversion fails, we fallback True
+        # (e.g. year too big, month number parse error)
+        bad_name = "findings_99999_jan"
+        assert _should_create_index_on_partition(bad_name, False) is True
+
+        bad_name2 = "findings_2025_abc"
+        # abc not in month_map → fallback True
+        assert _should_create_index_on_partition(bad_name2, False) is True
+
+
+@pytest.mark.django_db
+class TestCreateObjectsInBatches:
+    @pytest.fixture
+    def tenant(self, tenants_fixture):
+        return tenants_fixture[0]
+
+    def make_provider_instances(self, tenant, count):
+        """
+        Return a list of `count` unsaved Provider instances for the given tenant.
+        """
+        base_uid = 1000
+        return [
+            Provider(
+                tenant=tenant,
+                uid=str(base_uid + i),
+                provider=Provider.ProviderChoices.AWS,
+            )
+            for i in range(count)
+        ]
+
+    def test_exact_multiple_of_batch(self, tenant):
+        total = 6
+        batch_size = 3
+        objs = self.make_provider_instances(tenant, total)
+
+        create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
+
+        qs = Provider.objects.filter(tenant=tenant)
+        assert qs.count() == total
+
+    def test_non_multiple_of_batch(self, tenant):
+        total = 7
+        batch_size = 3
+        objs = self.make_provider_instances(tenant, total)
+
+        create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
+
+        qs = Provider.objects.filter(tenant=tenant)
+        assert qs.count() == total
+
+    def test_batch_size_default(self, tenant):
+        default_size = settings.DJANGO_DELETION_BATCH_SIZE
+        total = default_size + 2
+        objs = self.make_provider_instances(tenant, total)
+
+        create_objects_in_batches(str(tenant.id), Provider, objs)
+
+        qs = Provider.objects.filter(tenant=tenant)
+        assert qs.count() == total

api/src/backend/api/tests/test_mixins.py

@@ -0,0 +1,379 @@
+import json
+from uuid import uuid4
+
+import pytest
+from django_celery_results.models import TaskResult
+from rest_framework import status
+from rest_framework.response import Response
+
+from api.exceptions import (
+    TaskFailedException,
+    TaskInProgressException,
+    TaskNotFoundException,
+)
+from api.models import Task, User
+from api.rls import Tenant
+from api.v1.mixins import PaginateByPkMixin, TaskManagementMixin
+
+
+@pytest.mark.django_db
+class TestPaginateByPkMixin:
+    @pytest.fixture
+    def tenant(self):
+        return Tenant.objects.create(name="Test Tenant")
+
+    @pytest.fixture
+    def users(self, tenant):
+        # Create 5 users with proper email field
+        users = []
+        for i in range(5):
+            user = User.objects.create(email=f"user{i}@example.com", name=f"User {i}")
+            users.append(user)
+        return users
+
+    class DummyView(PaginateByPkMixin):
+        def __init__(self, page):
+            self._page = page
+
+        def paginate_queryset(self, qs):
+            return self._page
+
+        def get_serializer(self, queryset, many):
+            class S:
+                def __init__(self, data):
+                    # serialize to list of ids
+                    self.data = [obj.id for obj in data] if many else queryset.id
+
+            return S(queryset)
+
+        def get_paginated_response(self, data):
+            return Response({"results": data}, status=status.HTTP_200_OK)
+
+    def test_no_pagination(self, users):
+        base_qs = User.objects.all().order_by("id")
+        view = self.DummyView(page=None)
+        resp = view.paginate_by_pk(
+            request=None, base_queryset=base_qs, manager=User.objects
+        )
+        # since no pagination, should return all ids in order
+        expected = [u.id for u in base_qs]
+        assert isinstance(resp, Response)
+        assert resp.data == expected
+
+    def test_with_pagination(self, users):
+        base_qs = User.objects.all().order_by("id")
+        # simulate paging to first 2 ids
+        page = [base_qs[1].id, base_qs[3].id]
+        view = self.DummyView(page=page)
+        resp = view.paginate_by_pk(
+            request=None, base_queryset=base_qs, manager=User.objects
+        )
+        # should fetch only those two users, in the same order as page
+        assert resp.status_code == status.HTTP_200_OK
+        assert resp.data == {"results": page}
+
+
+@pytest.mark.django_db
+class TestTaskManagementMixin:
+    class DummyView(TaskManagementMixin):
+        pass
+
+    @pytest.fixture
+    def tenant(self):
+        return Tenant.objects.create(name="Test Tenant")
+
+    @pytest.fixture(autouse=True)
+    def cleanup(self):
+        Task.objects.all().delete()
+        TaskResult.objects.all().delete()
+
+    def test_no_task_and_no_taskresult_raises_not_found(self):
+        view = self.DummyView()
+        with pytest.raises(TaskNotFoundException):
+            view.check_task_status("task_xyz", {"foo": "bar"})
+
+    def test_no_task_and_no_taskresult_returns_none_when_not_raising(self):
+        view = self.DummyView()
+        result = view.check_task_status(
+            "task_xyz", {"foo": "bar"}, raise_on_not_found=False
+        )
+        assert result is None
+
+    def test_taskresult_pending_raises_in_progress(self):
+        task_kwargs = {"foo": "bar"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_xyz",
+            task_kwargs=json.dumps(task_kwargs),
+            status="PENDING",
+        )
+        view = self.DummyView()
+        with pytest.raises(TaskInProgressException) as excinfo:
+            view.check_task_status("task_xyz", task_kwargs, raise_on_not_found=False)
+        assert hasattr(excinfo.value, "task_result")
+        assert excinfo.value.task_result == tr
+
+    def test_taskresult_started_raises_in_progress(self):
+        task_kwargs = {"foo": "bar"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_xyz",
+            task_kwargs=json.dumps(task_kwargs),
+            status="STARTED",
+        )
+        view = self.DummyView()
+        with pytest.raises(TaskInProgressException) as excinfo:
+            view.check_task_status("task_xyz", task_kwargs, raise_on_not_found=False)
+        assert hasattr(excinfo.value, "task_result")
+        assert excinfo.value.task_result == tr
+
+    def test_taskresult_progress_raises_in_progress(self):
+        task_kwargs = {"foo": "bar"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_xyz",
+            task_kwargs=json.dumps(task_kwargs),
+            status="PROGRESS",
+        )
+        view = self.DummyView()
+        with pytest.raises(TaskInProgressException) as excinfo:
+            view.check_task_status("task_xyz", task_kwargs, raise_on_not_found=False)
+        assert hasattr(excinfo.value, "task_result")
+        assert excinfo.value.task_result == tr
+
+    def test_taskresult_failure_raises_failed(self):
+        task_kwargs = {"a": 1}
+        TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_fail",
+            task_kwargs=json.dumps(task_kwargs),
+            status="FAILURE",
+        )
+        view = self.DummyView()
+        with pytest.raises(TaskFailedException):
+            view.check_task_status("task_fail", task_kwargs, raise_on_not_found=False)
+
+    def test_taskresult_failure_returns_none_when_not_raising(self):
+        task_kwargs = {"a": 1}
+        TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_fail",
+            task_kwargs=json.dumps(task_kwargs),
+            status="FAILURE",
+        )
+        view = self.DummyView()
+        result = view.check_task_status(
+            "task_fail", task_kwargs, raise_on_failed=False, raise_on_not_found=False
+        )
+        assert result is None
+
+    def test_taskresult_success_returns_none(self):
+        task_kwargs = {"x": 2}
+        TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_ok",
+            task_kwargs=json.dumps(task_kwargs),
+            status="SUCCESS",
+        )
+        view = self.DummyView()
+        # should not raise, and returns None
+        assert (
+            view.check_task_status("task_ok", task_kwargs, raise_on_not_found=False)
+            is None
+        )
+
+    def test_taskresult_revoked_returns_none(self):
+        task_kwargs = {"x": 2}
+        TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="task_revoked",
+            task_kwargs=json.dumps(task_kwargs),
+            status="REVOKED",
+        )
+        view = self.DummyView()
+        # should not raise, and returns None
+        assert (
+            view.check_task_status(
+                "task_revoked", task_kwargs, raise_on_not_found=False
+            )
+            is None
+        )
+
+    def test_task_with_failed_status_raises_failed(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="FAILURE",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        with pytest.raises(TaskFailedException) as excinfo:
+            view.check_task_status("scan_task", task_kwargs)
+        # Check that the exception contains the expected task
+        assert hasattr(excinfo.value, "task")
+        assert excinfo.value.task == task
+
+    def test_task_with_cancelled_status_raises_failed(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="REVOKED",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        with pytest.raises(TaskFailedException) as excinfo:
+            view.check_task_status("scan_task", task_kwargs)
+        # Check that the exception contains the expected task
+        assert hasattr(excinfo.value, "task")
+        assert excinfo.value.task == task
+
+    def test_task_with_failed_status_returns_task_when_not_raising(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="FAILURE",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.check_task_status("scan_task", task_kwargs, raise_on_failed=False)
+        assert result == task
+
+    def test_task_with_completed_status_returns_none(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="SUCCESS",
+        )
+        Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.check_task_status("scan_task", task_kwargs)
+        assert result is None
+
+    def test_task_with_executing_status_returns_task(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="STARTED",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.check_task_status("scan_task", task_kwargs)
+        assert result is not None
+        assert result.pk == task.pk
+
+    def test_task_with_pending_status_returns_task(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="PENDING",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.check_task_status("scan_task", task_kwargs)
+        assert result is not None
+        assert result.pk == task.pk
+
+    def test_get_task_response_if_running_returns_none_for_completed_task(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="SUCCESS",
+        )
+        Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.get_task_response_if_running("scan_task", task_kwargs)
+        assert result is None
+
+    def test_get_task_response_if_running_returns_none_for_no_task(self):
+        view = self.DummyView()
+        result = view.get_task_response_if_running(
+            "nonexistent", {"foo": "bar"}, raise_on_not_found=False
+        )
+        assert result is None
+
+    def test_get_task_response_if_running_returns_202_for_executing_task(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="STARTED",
+        )
+        task = Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.get_task_response_if_running("scan_task", task_kwargs)
+
+        assert isinstance(result, Response)
+        assert result.status_code == status.HTTP_202_ACCEPTED
+        assert "Content-Location" in result.headers
+        # The response should contain the serialized task data
+        assert result.data is not None
+        assert "id" in result.data
+        assert str(result.data["id"]) == str(task.id)
+
+    def test_get_task_response_if_running_returns_none_for_available_task(self, tenant):
+        task_kwargs = {"provider_id": "test"}
+        tr = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs),
+            status="PENDING",
+        )
+        Task.objects.create(tenant=tenant, task_runner_task=tr)
+        view = self.DummyView()
+        result = view.get_task_response_if_running("scan_task", task_kwargs)
+        # PENDING maps to AVAILABLE, which is not EXECUTING, so should return None
+        assert result is None
+
+    def test_kwargs_filtering_works_correctly(self, tenant):
+        # Create tasks with different kwargs
+        task_kwargs_1 = {"provider_id": "test1", "scan_type": "full"}
+        task_kwargs_2 = {"provider_id": "test2", "scan_type": "quick"}
+
+        tr1 = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs_1),
+            status="STARTED",
+        )
+        tr2 = TaskResult.objects.create(
+            task_id=str(uuid4()),
+            task_name="scan_task",
+            task_kwargs=json.dumps(task_kwargs_2),
+            status="STARTED",
+        )
+
+        task1 = Task.objects.create(tenant=tenant, task_runner_task=tr1)
+        task2 = Task.objects.create(tenant=tenant, task_runner_task=tr2)
+
+        view = self.DummyView()
+
+        # Should find task1 when searching for its kwargs
+        result1 = view.check_task_status("scan_task", {"provider_id": "test1"})
+        assert result1 is not None
+        assert result1.pk == task1.pk
+
+        # Should find task2 when searching for its kwargs
+        result2 = view.check_task_status("scan_task", {"provider_id": "test2"})
+        assert result2 is not None
+        assert result2.pk == task2.pk
+
+        # Should not find anything when searching for non-existent kwargs
+        result3 = view.check_task_status(
+            "scan_task", {"provider_id": "test3"}, raise_on_not_found=False
+        )
+        assert result3 is None

api/src/backend/api/tests/test_models.py

@@ -1,6 +1,9 @@
 import pytest
+from allauth.socialaccount.models import SocialApp
+from django.core.exceptions import ValidationError
 
-from api.models import Resource, ResourceTag
+from api.db_router import MainRouter
+from api.models import Resource, ResourceTag, SAMLConfiguration, Tenant
 
 
 @pytest.mark.django_db
@@ -92,3 +95,177 @@ class TestResourceModel:
 
         assert len(resource.tags.filter(tenant_id=tenant_id)) == 0
         assert resource.get_tags(tenant_id=tenant_id) == {}
+
+
+# @pytest.mark.django_db
+# class TestFindingModel:
+#     def test_add_finding_with_long_uid(
+#         self, providers_fixture, scans_fixture, resources_fixture
+#     ):
+#         provider, *_ = providers_fixture
+#         tenant_id = provider.tenant_id
+
+#         long_uid = "1" * 500
+#         _ = Finding.objects.create(
+#             tenant_id=tenant_id,
+#             uid=long_uid,
+#             delta=Finding.DeltaChoices.NEW,
+#             check_metadata={},
+#             status=StatusChoices.PASS,
+#             status_extended="",
+#             severity="high",
+#             impact="high",
+#             raw_result={},
+#             check_id="test_check",
+#             scan=scans_fixture[0],
+#             first_seen_at=None,
+#             muted=False,
+#             compliance={},
+#         )
+#         assert Finding.objects.filter(uid=long_uid).exists()
+
+
+@pytest.mark.django_db
+class TestSAMLConfigurationModel:
+    VALID_METADATA = """<?xml version='1.0' encoding='UTF-8'?>
+    <md:EntityDescriptor entityID='TEST' xmlns:md='urn:oasis:names:tc:SAML:2.0:metadata'>
+    <md:IDPSSODescriptor WantAuthnRequestsSigned='false' protocolSupportEnumeration='urn:oasis:names:tc:SAML:2.0:protocol'>
+        <md:KeyDescriptor use='signing'>
+        <ds:KeyInfo xmlns:ds='http://www.w3.org/2000/09/xmldsig#'>
+            <ds:X509Data>
+            <ds:X509Certificate>FAKECERTDATA</ds:X509Certificate>
+            </ds:X509Data>
+        </ds:KeyInfo>
+        </md:KeyDescriptor>
+        <md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-POST' Location='https://idp.test/sso'/>
+    </md:IDPSSODescriptor>
+    </md:EntityDescriptor>
+    """
+
+    def test_creates_valid_configuration(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant A")
+        config = SAMLConfiguration.objects.using(MainRouter.admin_db).create(
+            email_domain="ssoexample.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant,
+        )
+
+        assert config.email_domain == "ssoexample.com"
+        assert SocialApp.objects.filter(client_id="ssoexample.com").exists()
+
+    def test_email_domain_with_at_symbol_fails(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant B")
+        config = SAMLConfiguration(
+            email_domain="invalid@domain.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config.clean()
+
+        errors = exc_info.value.message_dict
+        assert "email_domain" in errors
+        assert "Domain must not contain @" in errors["email_domain"][0]
+
+    def test_duplicate_email_domain_fails(self):
+        tenant1 = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant C1")
+        tenant2 = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant C2")
+
+        SAMLConfiguration.objects.using(MainRouter.admin_db).create(
+            email_domain="duplicate.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant1,
+        )
+
+        config = SAMLConfiguration(
+            email_domain="duplicate.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant2,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config.clean()
+
+        errors = exc_info.value.message_dict
+        assert "tenant" in errors
+        assert "There is a problem with your email domain." in errors["tenant"][0]
+
+    def test_duplicate_tenant_config_fails(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant D")
+
+        SAMLConfiguration.objects.using(MainRouter.admin_db).create(
+            email_domain="unique1.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant,
+        )
+
+        config = SAMLConfiguration(
+            email_domain="unique2.com",
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config.clean()
+
+        errors = exc_info.value.message_dict
+        assert "tenant" in errors
+        assert (
+            "A SAML configuration already exists for this tenant."
+            in errors["tenant"][0]
+        )
+
+    def test_invalid_metadata_xml_fails(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant E")
+        config = SAMLConfiguration(
+            email_domain="brokenxml.com",
+            metadata_xml="<bad<xml>",
+            tenant=tenant,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config._parse_metadata()
+
+        errors = exc_info.value.message_dict
+        assert "metadata_xml" in errors
+        assert "Invalid XML" in errors["metadata_xml"][0]
+        assert "not well-formed" in errors["metadata_xml"][0]
+
+    def test_metadata_missing_sso_fails(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant F")
+        xml = """<md:EntityDescriptor entityID="x" xmlns:md="urn:oasis:names:tc:SAML:2.0:metadata">
+                <md:IDPSSODescriptor></md:IDPSSODescriptor>
+                </md:EntityDescriptor>"""
+        config = SAMLConfiguration(
+            email_domain="nosso.com",
+            metadata_xml=xml,
+            tenant=tenant,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config._parse_metadata()
+
+        errors = exc_info.value.message_dict
+        assert "metadata_xml" in errors
+        assert "Missing SingleSignOnService" in errors["metadata_xml"][0]
+
+    def test_metadata_missing_certificate_fails(self):
+        tenant = Tenant.objects.using(MainRouter.admin_db).create(name="Tenant G")
+        xml = """<md:EntityDescriptor entityID="x" xmlns:md="urn:oasis:names:tc:SAML:2.0:metadata">
+                    <md:IDPSSODescriptor>
+                        <md:SingleSignOnService Binding="urn:oasis:names:tc:SAML:2.0:bindings:HTTP-Redirect" Location="https://example.com/sso"/>
+                    </md:IDPSSODescriptor>
+                </md:EntityDescriptor>"""
+        config = SAMLConfiguration(
+            email_domain="nocert.com",
+            metadata_xml=xml,
+            tenant=tenant,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config._parse_metadata()
+
+        errors = exc_info.value.message_dict
+        assert "metadata_xml" in errors
+        assert "X509Certificate" in errors["metadata_xml"][0]

api/src/backend/api/tests/test_sentry.py

@@ -0,0 +1,80 @@
+import logging
+from unittest.mock import MagicMock
+
+from config.settings.sentry import before_send
+
+
+def test_before_send_ignores_log_with_ignored_exception():
+    """Test that before_send ignores logs containing ignored exceptions."""
+    log_record = MagicMock()
+    log_record.msg = "Provider kubernetes is not connected"
+    log_record.levelno = logging.ERROR  # 40
+
+    hint = {"log_record": log_record}
+
+    event = MagicMock()
+
+    result = before_send(event, hint)
+
+    # Assert that the event was dropped (None returned)
+    assert result is None
+
+
+def test_before_send_ignores_exception_with_ignored_exception():
+    """Test that before_send ignores exceptions containing ignored exceptions."""
+    exc_info = (Exception, Exception("Provider kubernetes is not connected"), None)
+
+    hint = {"exc_info": exc_info}
+
+    event = MagicMock()
+
+    result = before_send(event, hint)
+
+    # Assert that the event was dropped (None returned)
+    assert result is None
+
+
+def test_before_send_passes_through_non_ignored_log():
+    """Test that before_send passes through logs that don't contain ignored exceptions."""
+    log_record = MagicMock()
+    log_record.msg = "Some other error message"
+    log_record.levelno = logging.ERROR  # 40
+
+    hint = {"log_record": log_record}
+
+    event = MagicMock()
+
+    result = before_send(event, hint)
+
+    # Assert that the event was passed through
+    assert result == event
+
+
+def test_before_send_passes_through_non_ignored_exception():
+    """Test that before_send passes through exceptions that don't contain ignored exceptions."""
+    exc_info = (Exception, Exception("Some other error message"), None)
+
+    hint = {"exc_info": exc_info}
+
+    event = MagicMock()
+
+    result = before_send(event, hint)
+
+    # Assert that the event was passed through
+    assert result == event
+
+
+def test_before_send_handles_warning_level():
+    """Test that before_send handles warning level logs."""
+    log_record = MagicMock()
+    log_record.msg = "Provider kubernetes is not connected"
+    log_record.levelno = logging.WARNING  # 30
+
+    hint = {"log_record": log_record}
+
+    event = MagicMock()
+
+    result = before_send(event, hint)
+
+    # Assert that the event was dropped (None returned)
+    assert result is None

api/src/backend/api/tests/test_utils.py

@@ -1,25 +1,25 @@
 from datetime import datetime, timedelta, timezone
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
+from rest_framework.exceptions import NotFound, ValidationError
+
+from api.db_router import MainRouter
+from api.exceptions import InvitationTokenExpiredException
+from api.models import Invitation, Provider
+from api.utils import (
+    get_prowler_provider_kwargs,
+    initialize_prowler_provider,
+    merge_dicts,
+    prowler_provider_connection_test,
+    return_prowler_provider,
+    validate_invitation,
+)
 from prowler.providers.aws.aws_provider import AwsProvider
 from prowler.providers.azure.azure_provider import AzureProvider
 from prowler.providers.gcp.gcp_provider import GcpProvider
 from prowler.providers.kubernetes.kubernetes_provider import KubernetesProvider
-from rest_framework.exceptions import ValidationError, NotFound
-
-from api.db_router import MainRouter
-from api.exceptions import InvitationTokenExpiredException
-from api.models import Invitation
-from api.models import Provider
-from api.utils import (
-    merge_dicts,
-    return_prowler_provider,
-    initialize_prowler_provider,
-    prowler_provider_connection_test,
-    get_prowler_provider_kwargs,
-)
-from api.utils import validate_invitation
+from prowler.providers.m365.m365_provider import M365Provider
 
 
 class TestMergeDicts:
@@ -105,6 +105,7 @@ class TestReturnProwlerProvider:
             (Provider.ProviderChoices.GCP.value, GcpProvider),
             (Provider.ProviderChoices.AZURE.value, AzureProvider),
             (Provider.ProviderChoices.KUBERNETES.value, KubernetesProvider),
+            (Provider.ProviderChoices.M365.value, M365Provider),
         ],
     )
     def test_return_prowler_provider(self, provider_type, expected_provider):
@@ -144,6 +145,18 @@ class TestProwlerProviderConnectionTest:
             key="value", provider_id="1234567890", raise_on_exception=False
         )
 
+    @pytest.mark.django_db
+    @patch("api.utils.return_prowler_provider")
+    def test_prowler_provider_connection_test_without_secret(
+        self, mock_return_prowler_provider, providers_fixture
+    ):
+        mock_return_prowler_provider.return_value = MagicMock()
+        connection = prowler_provider_connection_test(providers_fixture[0])
+
+        assert connection.is_connected is False
+        assert isinstance(connection.error, Provider.secret.RelatedObjectDoesNotExist)
+        assert str(connection.error) == "Provider has no secret."
+
 
 class TestGetProwlerProviderKwargs:
     @pytest.mark.parametrize(
@@ -165,6 +178,10 @@ class TestGetProwlerProviderKwargs:
                 Provider.ProviderChoices.KUBERNETES.value,
                 {"context": "provider_uid"},
             ),
+            (
+                Provider.ProviderChoices.M365.value,
+                {},
+            ),
         ],
     )
     def test_get_prowler_provider_kwargs(self, provider_type, expected_extra_kwargs):

api/src/backend/api/utils.py

@@ -1,16 +1,20 @@
 from datetime import datetime, timezone
 
 from allauth.socialaccount.providers.oauth2.client import OAuth2Client
+from django.contrib.postgres.aggregates import ArrayAgg
+from django.db.models import Subquery
 from rest_framework.exceptions import NotFound, ValidationError
 
 from api.db_router import MainRouter
 from api.exceptions import InvitationTokenExpiredException
-from api.models import Invitation, Provider
+from api.models import Invitation, Provider, Resource
+from api.v1.serializers import FindingMetadataSerializer
 from prowler.providers.aws.aws_provider import AwsProvider
 from prowler.providers.azure.azure_provider import AzureProvider
 from prowler.providers.common.models import Connection
 from prowler.providers.gcp.gcp_provider import GcpProvider
 from prowler.providers.kubernetes.kubernetes_provider import KubernetesProvider
+from prowler.providers.m365.m365_provider import M365Provider
 
 
 class CustomOAuth2Client(OAuth2Client):
@@ -51,14 +55,14 @@ def merge_dicts(default_dict: dict, replacement_dict: dict) -> dict:
 
 def return_prowler_provider(
     provider: Provider,
-) -> [AwsProvider | AzureProvider | GcpProvider | KubernetesProvider]:
+) -> [AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider]:
     """Return the Prowler provider class based on the given provider type.
 
     Args:
         provider (Provider): The provider object containing the provider type and associated secrets.
 
     Returns:
-        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider: The corresponding provider class.
+        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: The corresponding provider class.
 
     Raises:
         ValueError: If the provider type specified in `provider.provider` is not supported.
@@ -72,6 +76,8 @@ def return_prowler_provider(
             prowler_provider = AzureProvider
         case Provider.ProviderChoices.KUBERNETES.value:
             prowler_provider = KubernetesProvider
+        case Provider.ProviderChoices.M365.value:
+            prowler_provider = M365Provider
         case _:
             raise ValueError(f"Provider type {provider.provider} not supported")
     return prowler_provider
@@ -104,15 +110,15 @@ def get_prowler_provider_kwargs(provider: Provider) -> dict:
 
 def initialize_prowler_provider(
     provider: Provider,
-) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider:
+) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider:
     """Initialize a Prowler provider instance based on the given provider type.
 
     Args:
         provider (Provider): The provider object containing the provider type and associated secrets.
 
     Returns:
-        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider: An instance of the corresponding provider class
-            (`AwsProvider`, `AzureProvider`, `GcpProvider`, or `KubernetesProvider`) initialized with the
+        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: An instance of the corresponding provider class
+            (`AwsProvider`, `AzureProvider`, `GcpProvider`, `KubernetesProvider` or `M365Provider`) initialized with the
             provider's secrets.
     """
     prowler_provider = return_prowler_provider(provider)
@@ -130,7 +136,12 @@ def prowler_provider_connection_test(provider: Provider) -> Connection:
         Connection: A connection object representing the result of the connection test for the specified provider.
     """
     prowler_provider = return_prowler_provider(provider)
-    prowler_provider_kwargs = provider.secret.secret
+
+    try:
+        prowler_provider_kwargs = provider.secret.secret
+    except Provider.secret.RelatedObjectDoesNotExist as secret_error:
+        return Connection(is_connected=False, error=secret_error)
+
     return prowler_provider.test_connection(
         **prowler_provider_kwargs, provider_id=provider.uid, raise_on_exception=False
     )
@@ -197,3 +208,33 @@ def validate_invitation(
         )
 
     return invitation
+
+
+# ToRemove after removing the fallback mechanism in /findings/metadata
+def get_findings_metadata_no_aggregations(tenant_id: str, filtered_queryset):
+    filtered_ids = filtered_queryset.order_by().values("id")
+
+    relevant_resources = Resource.all_objects.filter(
+        tenant_id=tenant_id, findings__id__in=Subquery(filtered_ids)
+    ).only("service", "region", "type")
+
+    aggregation = relevant_resources.aggregate(
+        services=ArrayAgg("service", flat=True),
+        regions=ArrayAgg("region", flat=True),
+        resource_types=ArrayAgg("type", flat=True),
+    )
+
+    services = sorted(set(aggregation["services"] or []))
+    regions = sorted({region for region in aggregation["regions"] or [] if region})
+    resource_types = sorted(set(aggregation["resource_types"] or []))
+
+    result = {
+        "services": services,
+        "regions": regions,
+        "resource_types": resource_types,
+    }
+
+    serializer = FindingMetadataSerializer(data=result)
+    serializer.is_valid(raise_exception=True)
+
+    return serializer.data

api/src/backend/api/v1/mixins.py

@@ -0,0 +1,222 @@
+from django.urls import reverse
+from django_celery_results.models import TaskResult
+from rest_framework import status
+from rest_framework.response import Response
+
+from api.exceptions import (
+    TaskFailedException,
+    TaskInProgressException,
+    TaskNotFoundException,
+)
+from api.models import StateChoices, Task
+from api.v1.serializers import TaskSerializer
+
+
+class PaginateByPkMixin:
+    """
+    Mixin to paginate on a list of PKs (cheaper than heavy JOINs),
+    re-fetch the full objects with the desired select/prefetch,
+    re-sort them to preserve DB ordering, then serialize + return.
+    """
+
+    def paginate_by_pk(
+        self,
+        request,  # noqa: F841
+        base_queryset,
+        manager,
+        select_related: list[str] | None = None,
+        prefetch_related: list[str] | None = None,
+    ) -> Response:
+        pk_list = base_queryset.values_list("id", flat=True)
+        page = self.paginate_queryset(pk_list)
+        if page is None:
+            return Response(self.get_serializer(base_queryset, many=True).data)
+
+        queryset = manager.filter(id__in=page)
+        if select_related:
+            queryset = queryset.select_related(*select_related)
+        if prefetch_related:
+            queryset = queryset.prefetch_related(*prefetch_related)
+
+        queryset = sorted(queryset, key=lambda obj: page.index(obj.id))
+
+        serialized = self.get_serializer(queryset, many=True).data
+        return self.get_paginated_response(serialized)
+
+
+class TaskManagementMixin:
+    """
+    Mixin to manage task status checking.
+
+    This mixin provides functionality to check if a task with specific parameters
+    is running, completed, failed, or doesn't exist. It returns the task when running
+    and raises specific exceptions for failed/not found scenarios that can be handled
+    at the view level.
+    """
+
+    def check_task_status(
+        self,
+        task_name: str,
+        task_kwargs: dict,
+        raise_on_failed: bool = True,
+        raise_on_not_found: bool = True,
+    ) -> Task | None:
+        """
+        Check the status of a task with given name and kwargs.
+
+        This method first checks for a related Task object, and if not found,
+        checks TaskResult directly. If a TaskResult is found and running but
+        there's no related Task, it raises TaskInProgressException.
+
+        Args:
+            task_name (str): The name of the task to check
+            task_kwargs (dict): The kwargs to match against the task
+            raise_on_failed (bool): Whether to raise exception if task failed
+            raise_on_not_found (bool): Whether to raise exception if task not found
+
+        Returns:
+            Task | None: The task instance if found (regardless of state), None if not found and raise_on_not_found=False
+
+        Raises:
+            TaskFailedException: If task failed and raise_on_failed=True
+            TaskNotFoundException: If task not found and raise_on_not_found=True
+            TaskInProgressException: If task is running but no related Task object exists
+        """
+        # First, try to find a Task object with related TaskResult
+        try:
+            # Build the filter for task kwargs
+            task_filter = {
+                "task_runner_task__task_name": task_name,
+            }
+
+            # Add kwargs filters - we need to check if the task kwargs contain our parameters
+            for key, value in task_kwargs.items():
+                task_filter["task_runner_task__task_kwargs__contains"] = str(value)
+
+            task = (
+                Task.objects.filter(**task_filter)
+                .select_related("task_runner_task")
+                .order_by("-inserted_at")
+                .first()
+            )
+
+            if task:
+                # Get task state using the same logic as TaskSerializer
+                task_state_mapping = {
+                    "PENDING": StateChoices.AVAILABLE,
+                    "STARTED": StateChoices.EXECUTING,
+                    "PROGRESS": StateChoices.EXECUTING,
+                    "SUCCESS": StateChoices.COMPLETED,
+                    "FAILURE": StateChoices.FAILED,
+                    "REVOKED": StateChoices.CANCELLED,
+                }
+
+                celery_status = (
+                    task.task_runner_task.status if task.task_runner_task else None
+                )
+                task_state = task_state_mapping.get(
+                    celery_status or "", StateChoices.AVAILABLE
+                )
+
+                # Check task state and raise exceptions accordingly
+                if task_state in (StateChoices.FAILED, StateChoices.CANCELLED):
+                    if raise_on_failed:
+                        raise TaskFailedException(task=task)
+                    return task
+                elif task_state == StateChoices.COMPLETED:
+                    return None
+
+                return task
+
+        except Task.DoesNotExist:
+            pass
+
+        # If no Task found, check TaskResult directly
+        try:
+            # Build the filter for TaskResult
+            task_result_filter = {
+                "task_name": task_name,
+            }
+
+            # Add kwargs filters - check if the task kwargs contain our parameters
+            for key, value in task_kwargs.items():
+                task_result_filter["task_kwargs__contains"] = str(value)
+
+            task_result = (
+                TaskResult.objects.filter(**task_result_filter)
+                .order_by("-date_created")
+                .first()
+            )
+
+            if task_result:
+                # Check if the TaskResult indicates a running task
+                if task_result.status in ["PENDING", "STARTED", "PROGRESS"]:
+                    # Task is running but no related Task object exists
+                    raise TaskInProgressException(task_result=task_result)
+                elif task_result.status == "FAILURE":
+                    if raise_on_failed:
+                        raise TaskFailedException(task=None)
+                # For other statuses (SUCCESS, REVOKED), we don't have a Task to return,
+                # so we treat it as not found
+
+        except TaskResult.DoesNotExist:
+            pass
+
+        # No task found at all
+        if raise_on_not_found:
+            raise TaskNotFoundException()
+        return None
+
+    def get_task_response_if_running(
+        self,
+        task_name: str,
+        task_kwargs: dict,
+        raise_on_failed: bool = True,
+        raise_on_not_found: bool = True,
+    ) -> Response | None:
+        """
+        Get a 202 response with task details if the task is currently running.
+
+        This method is useful for endpoints that should return task status when
+        a background task is in progress, similar to the compliance overview endpoints.
+
+        Args:
+            task_name (str): The name of the task to check
+            task_kwargs (dict): The kwargs to match against the task
+
+        Returns:
+            Response | None: 202 response with task details if running, None otherwise
+        """
+        task = self.check_task_status(
+            task_name=task_name,
+            task_kwargs=task_kwargs,
+            raise_on_failed=raise_on_failed,
+            raise_on_not_found=raise_on_not_found,
+        )
+
+        if not task:
+            return None
+
+        # Get task state
+        task_state_mapping = {
+            "PENDING": StateChoices.AVAILABLE,
+            "STARTED": StateChoices.EXECUTING,
+            "PROGRESS": StateChoices.EXECUTING,
+            "SUCCESS": StateChoices.COMPLETED,
+            "FAILURE": StateChoices.FAILED,
+            "REVOKED": StateChoices.CANCELLED,
+        }
+
+        celery_status = task.task_runner_task.status if task.task_runner_task else None
+        task_state = task_state_mapping.get(celery_status or "", StateChoices.AVAILABLE)
+
+        if task_state == StateChoices.EXECUTING:
+            self.response_serializer_class = TaskSerializer
+            serializer = TaskSerializer(task)
+            return Response(
+                data=serializer.data,
+                status=status.HTTP_202_ACCEPTED,
+                headers={
+                    "Content-Location": reverse("task-detail", kwargs={"pk": task.id})
+                },
+            )

api/src/backend/api/v1/serializer_utils/providers.py

@@ -0,0 +1,183 @@
+from drf_spectacular.utils import extend_schema_field
+from rest_framework_json_api import serializers
+
+
+@extend_schema_field(
+    {
+        "oneOf": [
+            {
+                "type": "object",
+                "title": "AWS Static Credentials",
+                "properties": {
+                    "aws_access_key_id": {
+                        "type": "string",
+                        "description": "The AWS access key ID. Required for environments where no IAM role is being "
+                        "assumed and direct AWS access is needed.",
+                    },
+                    "aws_secret_access_key": {
+                        "type": "string",
+                        "description": "The AWS secret access key. Must accompany 'aws_access_key_id' to authorize "
+                        "access to AWS resources.",
+                    },
+                    "aws_session_token": {
+                        "type": "string",
+                        "description": "The session token associated with temporary credentials. Only needed for "
+                        "session-based or temporary AWS access.",
+                    },
+                },
+                "required": ["aws_access_key_id", "aws_secret_access_key"],
+            },
+            {
+                "type": "object",
+                "title": "AWS Assume Role",
+                "properties": {
+                    "role_arn": {
+                        "type": "string",
+                        "description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
+                        "assumption.",
+                    },
+                    "external_id": {
+                        "type": "string",
+                        "description": "An identifier to enhance security for role assumption.",
+                    },
+                    "aws_access_key_id": {
+                        "type": "string",
+                        "description": "The AWS access key ID. Only required if the environment lacks pre-configured "
+                        "AWS credentials.",
+                    },
+                    "aws_secret_access_key": {
+                        "type": "string",
+                        "description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
+                        "no AWS credentials are pre-configured.",
+                    },
+                    "aws_session_token": {
+                        "type": "string",
+                        "description": "The session token for temporary credentials, if applicable.",
+                    },
+                    "session_duration": {
+                        "type": "integer",
+                        "minimum": 900,
+                        "maximum": 43200,
+                        "default": 3600,
+                        "description": "The duration (in seconds) for the role session.",
+                    },
+                    "role_session_name": {
+                        "type": "string",
+                        "description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
+                        "The regex used to validate this parameter is a string of characters consisting of "
+                        "upper- and lower-case alphanumeric characters with no spaces. You can also include "
+                        "underscores or any of the following characters: =,.@-\n\n"
+                        "Examples:\n"
+                        "- MySession123\n"
+                        "- User_Session-1\n"
+                        "- Test.Session@2",
+                        "pattern": "^[a-zA-Z0-9=,.@_-]+$",
+                    },
+                },
+                "required": ["role_arn", "external_id"],
+            },
+            {
+                "type": "object",
+                "title": "Azure Static Credentials",
+                "properties": {
+                    "client_id": {
+                        "type": "string",
+                        "description": "The Azure application (client) ID for authentication in Azure AD.",
+                    },
+                    "client_secret": {
+                        "type": "string",
+                        "description": "The client secret associated with the application (client) ID, providing "
+                        "secure access.",
+                    },
+                    "tenant_id": {
+                        "type": "string",
+                        "description": "The Azure tenant ID, representing the directory where the application is "
+                        "registered.",
+                    },
+                },
+                "required": ["client_id", "client_secret", "tenant_id"],
+            },
+            {
+                "type": "object",
+                "title": "M365 Static Credentials",
+                "properties": {
+                    "client_id": {
+                        "type": "string",
+                        "description": "The Azure application (client) ID for authentication in Azure AD.",
+                    },
+                    "client_secret": {
+                        "type": "string",
+                        "description": "The client secret associated with the application (client) ID, providing "
+                        "secure access.",
+                    },
+                    "tenant_id": {
+                        "type": "string",
+                        "description": "The Azure tenant ID, representing the directory where the application is "
+                        "registered.",
+                    },
+                    "user": {
+                        "type": "email",
+                        "description": "User microsoft email address.",
+                    },
+                    "password": {
+                        "type": "string",
+                        "description": "User password.",
+                    },
+                },
+                "required": [
+                    "client_id",
+                    "client_secret",
+                    "tenant_id",
+                    "user",
+                    "password",
+                ],
+            },
+            {
+                "type": "object",
+                "title": "GCP Static Credentials",
+                "properties": {
+                    "client_id": {
+                        "type": "string",
+                        "description": "The client ID from Google Cloud, used to identify the application for GCP "
+                        "access.",
+                    },
+                    "client_secret": {
+                        "type": "string",
+                        "description": "The client secret associated with the GCP client ID, required for secure "
+                        "access.",
+                    },
+                    "refresh_token": {
+                        "type": "string",
+                        "description": "A refresh token that allows the application to obtain new access tokens for "
+                        "extended use.",
+                    },
+                },
+                "required": ["client_id", "client_secret", "refresh_token"],
+            },
+            {
+                "type": "object",
+                "title": "GCP Service Account Key",
+                "properties": {
+                    "service_account_key": {
+                        "type": "object",
+                        "description": "The service account key for GCP.",
+                    }
+                },
+                "required": ["service_account_key"],
+            },
+            {
+                "type": "object",
+                "title": "Kubernetes Static Credentials",
+                "properties": {
+                    "kubeconfig_content": {
+                        "type": "string",
+                        "description": "The content of the Kubernetes kubeconfig file, encoded as a string.",
+                    }
+                },
+                "required": ["kubeconfig_content"],
+            },
+        ]
+    }
+)
+class ProviderSecretField(serializers.JSONField):
+    pass

api/src/backend/api/v1/serializers.py

@@ -14,12 +14,12 @@ from rest_framework_simplejwt.serializers import TokenObtainPairSerializer
 from rest_framework_simplejwt.tokens import RefreshToken
 
 from api.models import (
-    ComplianceOverview,
     Finding,
     Integration,
     IntegrationProviderRelationship,
     Invitation,
     InvitationRoleRelationship,
+    LighthouseConfiguration,
     Membership,
     Provider,
     ProviderGroup,
@@ -29,8 +29,10 @@ from api.models import (
     ResourceTag,
     Role,
     RoleProviderGroupRelationship,
+    SAMLConfiguration,
     Scan,
     StateChoices,
+    StatusChoices,
     Task,
     User,
     UserRoleRelationship,
@@ -42,6 +44,7 @@ from api.v1.serializer_utils.integrations import (
     IntegrationCredentialField,
     S3ConfigSerializer,
 )
+from api.v1.serializer_utils.providers import ProviderSecretField
 
 # Tokens
 
@@ -851,6 +854,10 @@ class ScanSerializer(RLSSerializer):
             "url",
         ]
 
+    included_serializers = {
+        "provider": "api.v1.serializers.ProviderIncludeSerializer",
+    }
+
 
 class ScanIncludeSerializer(RLSSerializer):
     trigger = serializers.ChoiceField(
@@ -955,6 +962,15 @@ class ScanReportSerializer(serializers.Serializer):
         fields = ["id"]
 
 
+class ScanComplianceReportSerializer(serializers.Serializer):
+    id = serializers.CharField(source="scan")
+    name = serializers.CharField()
+
+    class Meta:
+        resource_name = "scan-reports"
+        fields = ["id", "name"]
+
+
 class ResourceTagSerializer(RLSSerializer):
     """
     Serializer for the ResourceTag model
@@ -1087,6 +1103,7 @@ class FindingSerializer(RLSSerializer):
             "inserted_at",
             "updated_at",
             "first_seen_at",
+            "muted",
             "url",
             # Relationships
             "scan",
@@ -1136,12 +1153,16 @@ class BaseWriteProviderSecretSerializer(BaseWriteSerializer):
                 serializer = GCPProviderSecret(data=secret)
             elif provider_type == Provider.ProviderChoices.KUBERNETES.value:
                 serializer = KubernetesProviderSecret(data=secret)
+            elif provider_type == Provider.ProviderChoices.M365.value:
+                serializer = M365ProviderSecret(data=secret)
             else:
                 raise serializers.ValidationError(
                     {"provider": f"Provider type not supported {provider_type}"}
                 )
         elif secret_type == ProviderSecret.TypeChoices.ROLE:
             serializer = AWSRoleAssumptionProviderSecret(data=secret)
+        elif secret_type == ProviderSecret.TypeChoices.SERVICE_ACCOUNT:
+            serializer = GCPServiceAccountProviderSecret(data=secret)
         else:
             raise serializers.ValidationError(
                 {"secret_type": f"Secret type not supported: {secret_type}"}
@@ -1175,6 +1196,17 @@ class AzureProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
+class M365ProviderSecret(serializers.Serializer):
+    client_id = serializers.CharField()
+    client_secret = serializers.CharField()
+    tenant_id = serializers.CharField()
+    user = serializers.EmailField()
+    password = serializers.CharField()
+
+    class Meta:
+        resource_name = "provider-secrets"
+
+
 class GCPProviderSecret(serializers.Serializer):
     client_id = serializers.CharField()
     client_secret = serializers.CharField()
@@ -1184,6 +1216,13 @@ class GCPProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
+class GCPServiceAccountProviderSecret(serializers.Serializer):
+    service_account_key = serializers.JSONField()
+
+    class Meta:
+        resource_name = "provider-secrets"
+
+
 class KubernetesProviderSecret(serializers.Serializer):
     kubeconfig_content = serializers.CharField()
 
@@ -1206,141 +1245,6 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
-@extend_schema_field(
-    {
-        "oneOf": [
-            {
-                "type": "object",
-                "title": "AWS Static Credentials",
-                "properties": {
-                    "aws_access_key_id": {
-                        "type": "string",
-                        "description": "The AWS access key ID. Required for environments where no IAM role is being "
-                        "assumed and direct AWS access is needed.",
-                    },
-                    "aws_secret_access_key": {
-                        "type": "string",
-                        "description": "The AWS secret access key. Must accompany 'aws_access_key_id' to authorize "
-                        "access to AWS resources.",
-                    },
-                    "aws_session_token": {
-                        "type": "string",
-                        "description": "The session token associated with temporary credentials. Only needed for "
-                        "session-based or temporary AWS access.",
-                    },
-                },
-                "required": ["aws_access_key_id", "aws_secret_access_key"],
-            },
-            {
-                "type": "object",
-                "title": "AWS Assume Role",
-                "properties": {
-                    "role_arn": {
-                        "type": "string",
-                        "description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
-                        "assumption.",
-                    },
-                    "external_id": {
-                        "type": "string",
-                        "description": "An identifier to enhance security for role assumption.",
-                    },
-                    "aws_access_key_id": {
-                        "type": "string",
-                        "description": "The AWS access key ID. Only required if the environment lacks pre-configured "
-                        "AWS credentials.",
-                    },
-                    "aws_secret_access_key": {
-                        "type": "string",
-                        "description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
-                        "no AWS credentials are pre-configured.",
-                    },
-                    "aws_session_token": {
-                        "type": "string",
-                        "description": "The session token for temporary credentials, if applicable.",
-                    },
-                    "session_duration": {
-                        "type": "integer",
-                        "minimum": 900,
-                        "maximum": 43200,
-                        "default": 3600,
-                        "description": "The duration (in seconds) for the role session.",
-                    },
-                    "role_session_name": {
-                        "type": "string",
-                        "description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
-                        "The regex used to validate this parameter is a string of characters consisting of "
-                        "upper- and lower-case alphanumeric characters with no spaces. You can also include "
-                        "underscores or any of the following characters: =,.@-\n\n"
-                        "Examples:\n"
-                        "- MySession123\n"
-                        "- User_Session-1\n"
-                        "- Test.Session@2",
-                        "pattern": "^[a-zA-Z0-9=,.@_-]+$",
-                    },
-                },
-                "required": ["role_arn", "external_id"],
-            },
-            {
-                "type": "object",
-                "title": "Azure Static Credentials",
-                "properties": {
-                    "client_id": {
-                        "type": "string",
-                        "description": "The Azure application (client) ID for authentication in Azure AD.",
-                    },
-                    "client_secret": {
-                        "type": "string",
-                        "description": "The client secret associated with the application (client) ID, providing "
-                        "secure access.",
-                    },
-                    "tenant_id": {
-                        "type": "string",
-                        "description": "The Azure tenant ID, representing the directory where the application is "
-                        "registered.",
-                    },
-                },
-                "required": ["client_id", "client_secret", "tenant_id"],
-            },
-            {
-                "type": "object",
-                "title": "GCP Static Credentials",
-                "properties": {
-                    "client_id": {
-                        "type": "string",
-                        "description": "The client ID from Google Cloud, used to identify the application for GCP "
-                        "access.",
-                    },
-                    "client_secret": {
-                        "type": "string",
-                        "description": "The client secret associated with the GCP client ID, required for secure "
-                        "access.",
-                    },
-                    "refresh_token": {
-                        "type": "string",
-                        "description": "A refresh token that allows the application to obtain new access tokens for "
-                        "extended use.",
-                    },
-                },
-                "required": ["client_id", "client_secret", "refresh_token"],
-            },
-            {
-                "type": "object",
-                "title": "Kubernetes Static Credentials",
-                "properties": {
-                    "kubeconfig_content": {
-                        "type": "string",
-                        "description": "The content of the Kubernetes kubeconfig file, encoded as a string.",
-                    }
-                },
-                "required": ["kubeconfig_content"],
-            },
-        ]
-    }
-)
-class ProviderSecretField(serializers.JSONField):
-    pass
-
-
 class ProviderSecretSerializer(RLSSerializer):
     """
     Serializer for the ProviderSecret model.
@@ -1777,124 +1681,64 @@ class RoleProviderGroupRelationshipSerializer(RLSSerializer, BaseWriteSerializer
 # Compliance overview
 
 
-class ComplianceOverviewSerializer(RLSSerializer):
+class ComplianceOverviewSerializer(serializers.Serializer):
     """
-    Serializer for the ComplianceOverview model.
+    Serializer for compliance requirement status aggregated by compliance framework.
+
+    This serializer is used to format aggregated compliance framework data,
+    providing counts of passed, failed, and manual requirements along with
+    an overall global status for each framework.
     """
 
-    requirements_status = serializers.SerializerMethodField(
-        read_only=True, method_name="get_requirements_status"
-    )
-    provider_type = serializers.SerializerMethodField(read_only=True)
+    # Add ID field which will be used for resource identification
+    id = serializers.CharField()
+    framework = serializers.CharField()
+    version = serializers.CharField()
+    requirements_passed = serializers.IntegerField()
+    requirements_failed = serializers.IntegerField()
+    requirements_manual = serializers.IntegerField()
+    total_requirements = serializers.IntegerField()
 
-    class Meta:
-        model = ComplianceOverview
-        fields = [
-            "id",
-            "inserted_at",
-            "compliance_id",
-            "framework",
-            "version",
-            "requirements_status",
-            "region",
-            "provider_type",
-            "scan",
-            "url",
-        ]
-
-    @extend_schema_field(
-        {
-            "type": "object",
-            "properties": {
-                "passed": {"type": "integer"},
-                "failed": {"type": "integer"},
-                "manual": {"type": "integer"},
-                "total": {"type": "integer"},
-            },
-        }
-    )
-    def get_requirements_status(self, obj):
-        return {
-            "passed": obj.requirements_passed,
-            "failed": obj.requirements_failed,
-            "manual": obj.requirements_manual,
-            "total": obj.total_requirements,
-        }
-
-    @extend_schema_field(serializers.CharField(allow_null=True))
-    def get_provider_type(self, obj):
-        """
-        Retrieves the provider_type from scan.provider.provider_type.
-        """
-        try:
-            return obj.scan.provider.provider
-        except AttributeError:
-            return None
+    class JSONAPIMeta:
+        resource_name = "compliance-overviews"
 
 
-class ComplianceOverviewFullSerializer(ComplianceOverviewSerializer):
-    requirements = serializers.SerializerMethodField(read_only=True)
+class ComplianceOverviewDetailSerializer(serializers.Serializer):
+    """
+    Serializer for detailed compliance requirement information.
 
-    class Meta(ComplianceOverviewSerializer.Meta):
-        fields = ComplianceOverviewSerializer.Meta.fields + [
-            "description",
-            "requirements",
-        ]
+    This serializer formats the aggregated requirement data, showing detailed status
+    and counts for each requirement across all regions.
+    """
 
-    @extend_schema_field(
-        {
-            "type": "object",
-            "properties": {
-                "requirement_id": {
-                    "type": "object",
-                    "properties": {
-                        "name": {"type": "string"},
-                        "checks": {
-                            "type": "object",
-                            "properties": {
-                                "check_name": {
-                                    "type": "object",
-                                    "properties": {
-                                        "status": {
-                                            "type": "string",
-                                            "enum": ["PASS", "FAIL", None],
-                                        },
-                                    },
-                                }
-                            },
-                            "description": "Each key in the 'checks' object is a check name, with values as "
-                            "'PASS', 'FAIL', or null.",
-                        },
-                        "status": {
-                            "type": "string",
-                            "enum": ["PASS", "FAIL", "MANUAL"],
-                        },
-                        "attributes": {
-                            "type": "array",
-                            "items": {
-                                "type": "object",
-                            },
-                        },
-                        "description": {"type": "string"},
-                        "checks_status": {
-                            "type": "object",
-                            "properties": {
-                                "total": {"type": "integer"},
-                                "pass": {"type": "integer"},
-                                "fail": {"type": "integer"},
-                                "manual": {"type": "integer"},
-                            },
-                        },
-                    },
-                }
-            },
-        }
-    )
-    def get_requirements(self, obj):
-        """
-        Returns the detailed structure of requirements.
-        """
-        return obj.requirements
+    id = serializers.CharField()
+    framework = serializers.CharField()
+    version = serializers.CharField()
+    description = serializers.CharField()
+    status = serializers.ChoiceField(choices=StatusChoices.choices)
+
+    class JSONAPIMeta:
+        resource_name = "compliance-requirements-details"
+
+
+class ComplianceOverviewAttributesSerializer(serializers.Serializer):
+    id = serializers.CharField()
+    framework_description = serializers.CharField()
+    name = serializers.CharField()
+    framework = serializers.CharField()
+    version = serializers.CharField()
+    description = serializers.CharField()
+    attributes = serializers.JSONField()
+
+    class JSONAPIMeta:
+        resource_name = "compliance-requirements-attributes"
+
+
+class ComplianceOverviewMetadataSerializer(serializers.Serializer):
+    regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
+
+    class JSONAPIMeta:
+        resource_name = "compliance-overviews-metadata"
 
 
 # Overviews
@@ -2219,3 +2063,156 @@ class IntegrationUpdateSerializer(BaseWriteIntegrationSerializer):
             IntegrationProviderRelationship.objects.bulk_create(new_relationships)
 
         return super().update(instance, validated_data)
+
+
+# SSO
+
+
+class SamlInitiateSerializer(serializers.Serializer):
+    email_domain = serializers.CharField()
+
+    class JSONAPIMeta:
+        resource_name = "saml-initiate"
+
+
+class SamlMetadataSerializer(serializers.Serializer):
+    class JSONAPIMeta:
+        resource_name = "saml-meta"
+
+
+class SAMLConfigurationSerializer(RLSSerializer):
+    class Meta:
+        model = SAMLConfiguration
+        fields = ["id", "email_domain", "metadata_xml", "created_at", "updated_at"]
+        read_only_fields = ["id", "created_at", "updated_at"]
+
+
+class LighthouseConfigSerializer(RLSSerializer):
+    """
+    Serializer for the LighthouseConfig model.
+    """
+
+    api_key = serializers.CharField(required=False)
+
+    class Meta:
+        model = LighthouseConfiguration
+        fields = [
+            "id",
+            "name",
+            "api_key",
+            "model",
+            "temperature",
+            "max_tokens",
+            "business_context",
+            "is_active",
+            "inserted_at",
+            "updated_at",
+            "url",
+        ]
+        extra_kwargs = {
+            "id": {"read_only": True},
+            "is_active": {"read_only": True},
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+        }
+
+    def to_representation(self, instance):
+        data = super().to_representation(instance)
+        # Check if api_key is specifically requested in fields param
+        fields_param = self.context.get("request", None) and self.context[
+            "request"
+        ].query_params.get("fields[lighthouse-config]", "")
+        if fields_param == "api_key":
+            # Return decrypted key if specifically requested
+            data["api_key"] = instance.api_key_decoded if instance.api_key else None
+        else:
+            # Return masked key for general requests
+            data["api_key"] = "*" * len(instance.api_key) if instance.api_key else None
+        return data
+
+
+class LighthouseConfigCreateSerializer(RLSSerializer, BaseWriteSerializer):
+    """Serializer for creating new Lighthouse configurations."""
+
+    api_key = serializers.CharField(write_only=True, required=True)
+
+    class Meta:
+        model = LighthouseConfiguration
+        fields = [
+            "id",
+            "name",
+            "api_key",
+            "model",
+            "temperature",
+            "max_tokens",
+            "business_context",
+            "is_active",
+            "inserted_at",
+            "updated_at",
+        ]
+        extra_kwargs = {
+            "id": {"read_only": True},
+            "is_active": {"read_only": True},
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+        }
+
+    def validate(self, attrs):
+        tenant_id = self.context.get("request").tenant_id
+        if LighthouseConfiguration.objects.filter(tenant_id=tenant_id).exists():
+            raise serializers.ValidationError(
+                {
+                    "tenant_id": "Lighthouse configuration already exists for this tenant."
+                }
+            )
+        return super().validate(attrs)
+
+    def create(self, validated_data):
+        api_key = validated_data.pop("api_key")
+        instance = super().create(validated_data)
+        instance.api_key_decoded = api_key
+        instance.save()
+        return instance
+
+    def to_representation(self, instance):
+        data = super().to_representation(instance)
+        # Always mask the API key in the response
+        data["api_key"] = "*" * len(instance.api_key) if instance.api_key else None
+        return data
+
+
+class LighthouseConfigUpdateSerializer(BaseWriteSerializer):
+    """
+    Serializer for updating LighthouseConfig instances.
+    """
+
+    api_key = serializers.CharField(write_only=True, required=False)
+
+    class Meta:
+        model = LighthouseConfiguration
+        fields = [
+            "id",
+            "name",
+            "api_key",
+            "model",
+            "temperature",
+            "max_tokens",
+            "business_context",
+            "is_active",
+        ]
+        extra_kwargs = {
+            "id": {"read_only": True},
+            "is_active": {"read_only": True},
+            "name": {"required": False},
+            "model": {"required": False},
+            "temperature": {"required": False},
+            "max_tokens": {"required": False},
+        }
+
+    def update(self, instance, validated_data):
+        api_key = validated_data.pop("api_key", None)
+        instance = super().update(instance, validated_data)
+        if api_key:
+            instance.api_key_decoded = api_key
+            instance.save()
+        return instance

api/src/backend/api/v1/urls.py

@@ -13,6 +13,7 @@ from api.v1.views import (
     IntegrationViewSet,
     InvitationAcceptViewSet,
     InvitationViewSet,
+    LighthouseConfigViewSet,
     MembershipViewSet,
     OverviewViewSet,
     ProviderGroupProvidersRelationshipView,
@@ -22,10 +23,13 @@ from api.v1.views import (
     ResourceViewSet,
     RoleProviderGroupRelationshipView,
     RoleViewSet,
+    SAMLConfigurationViewSet,
+    SAMLInitiateAPIView,
     ScanViewSet,
     ScheduleViewSet,
     SchemaView,
     TaskViewSet,
+    TenantFinishACSView,
     TenantMembersViewSet,
     TenantViewSet,
     UserRoleRelationshipView,
@@ -49,6 +53,12 @@ router.register(
 router.register(r"overviews", OverviewViewSet, basename="overview")
 router.register(r"schedules", ScheduleViewSet, basename="schedule")
 router.register(r"integrations", IntegrationViewSet, basename="integration")
+router.register(r"saml-config", SAMLConfigurationViewSet, basename="saml-config")
+router.register(
+    r"lighthouse-configurations",
+    LighthouseConfigViewSet,
+    basename="lighthouseconfiguration",
+)
 
 tenants_router = routers.NestedSimpleRouter(router, r"tenants", lookup="tenant")
 tenants_router.register(
@@ -112,6 +122,17 @@ urlpatterns = [
         ),
         name="provider_group-providers-relationship",
     ),
+    # API endpoint to start SAML SSO flow
+    path(
+        "auth/saml/initiate/", SAMLInitiateAPIView.as_view(), name="api_saml_initiate"
+    ),
+    # Allauth SAML endpoints for tenants
+    path("accounts/", include("allauth.urls")),
+    path(
+        "api/v1/accounts/saml/<organization_slug>/acs/finish/",
+        TenantFinishACSView.as_view(),
+        name="saml_finish_acs",
+    ),
     path("tokens/google", GoogleSocialLoginView.as_view(), name="token-google"),
     path("tokens/github", GithubSocialLoginView.as_view(), name="token-github"),
     path("", include(router.urls)),

api/src/backend/config/celery.py

@@ -1,6 +1,13 @@
+import warnings
+
 from celery import Celery, Task
 from config.env import env
 
+# Suppress specific warnings from django-rest-auth: https://github.com/iMerica/dj-rest-auth/issues/684
+warnings.filterwarnings(
+    "ignore", category=UserWarning, module="dj_rest_auth.registration.serializers"
+)
+
 BROKER_VISIBILITY_TIMEOUT = env.int("DJANGO_BROKER_VISIBILITY_TIMEOUT", default=86400)
 
 celery_app = Celery("tasks")
@@ -50,9 +57,9 @@ class RLSTask(Task):
 
         tenant_id = kwargs.get("tenant_id")
         with rls_transaction(tenant_id):
-            APITask.objects.create(
+            APITask.objects.update_or_create(
                 id=task_result_instance.task_id,
                 tenant_id=tenant_id,
-                task_runner_task=task_result_instance,
+                defaults={"task_runner_task": task_result_instance},
             )
         return result

api/src/backend/config/django/base.py

@@ -10,6 +10,7 @@ from config.settings.social_login import *  # noqa
 SECRET_KEY = env("SECRET_KEY", default="secret")
 DEBUG = env.bool("DJANGO_DEBUG", default=False)
 ALLOWED_HOSTS = ["localhost", "127.0.0.1"]
+SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
 
 # Application definition
 
@@ -26,16 +27,19 @@ INSTALLED_APPS = [
     "rest_framework",
     "corsheaders",
     "drf_spectacular",
+    "drf_spectacular_jsonapi",
     "django_guid",
     "rest_framework_json_api",
     "django_celery_results",
     "django_celery_beat",
     "rest_framework_simplejwt.token_blacklist",
     "allauth",
+    "django.contrib.sites",
     "allauth.account",
     "allauth.socialaccount",
     "allauth.socialaccount.providers.google",
     "allauth.socialaccount.providers.github",
+    "allauth.socialaccount.providers.saml",
     "dj_rest_auth.registration",
     "rest_framework.authtoken",
 ]
@@ -111,6 +115,7 @@ SPECTACULAR_SETTINGS = {
     "PREPROCESSING_HOOKS": [
         "drf_spectacular_jsonapi.hooks.fix_nested_path_parameters",
     ],
+    "TITLE": "API Reference - Prowler",
 }
 
 WSGI_APPLICATION = "config.wsgi.application"
@@ -236,3 +241,10 @@ DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = env.str(
 )
 DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = env.str("DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN", "")
 DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION", "")
+
+# HTTP Security Headers
+SECURE_CONTENT_TYPE_NOSNIFF = True
+X_FRAME_OPTIONS = "DENY"
+SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
+
+DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)

api/src/backend/config/settings/sentry.py

@@ -12,6 +12,8 @@ IGNORED_EXCEPTIONS = [
     "UnauthorizedOperation",
     "AuthFailure",
     "InvalidClientTokenId",
+    "AWSInvalidProviderIdError",
+    "InternalServerErrorException",
     "AccessDenied",
     "No Shodan API Key",  # Shodan Check
     "RequestLimitExceeded",  # For now we don't want to log the RequestLimitExceeded errors
@@ -33,6 +35,13 @@ IGNORED_EXCEPTIONS = [
     "ValidationException",
     "AWSSecretAccessKeyInvalidError",
     "InvalidAction",
+    "InvalidRequestException",
+    "RequestExpired",
+    "ConnectionClosedError",
+    "MaxRetryError",
+    "AWSAccessKeyIDInvalidError",
+    "AWSSessionTokenExpiredError",
+    "EndpointConnectionError",  # AWS Service is not available in a region
     "Pool is closed",  # The following comes from urllib3: eu-west-1 -- HTTPClientError[126]: An HTTP Client raised an unhandled exception: AWSHTTPSConnectionPool(host='hostname.s3.eu-west-1.amazonaws.com', port=443): Pool is closed.
     # Authentication Errors from GCP
     "ClientAuthenticationError",
@@ -41,6 +50,8 @@ IGNORED_EXCEPTIONS = [
     "Permission denied to get service",
     "API has not been used in project",
     "HttpError 404 when requesting",
+    "HttpError 403 when requesting",
+    "HttpError 400 when requesting",
     "GCPNoAccesibleProjectsError",
     # Authentication Errors from Azure
     "ClientAuthenticationError",
@@ -49,6 +60,7 @@ IGNORED_EXCEPTIONS = [
     "AzureNotValidClientIdError",
     "AzureNotValidClientSecretError",
     "AzureNotValidTenantIdError",
+    "AzureInvalidProviderIdError",
     "AzureTenantIdAndClientSecretNotBelongingToClientIdError",
     "AzureTenantIdAndClientIdNotBelongingToClientSecretError",
     "AzureClientIdAndClientSecretNotBelongingToTenantIdError",
@@ -67,9 +79,16 @@ def before_send(event, hint):
         log_msg = hint["log_record"].msg
         log_lvl = hint["log_record"].levelno
 
-        # Handle Error events and discard the rest
-        if log_lvl == 40 and any(ignored in log_msg for ignored in IGNORED_EXCEPTIONS):
-            return
+        # Handle Error and Critical events and discard the rest
+        if log_lvl <= 40 and any(ignored in log_msg for ignored in IGNORED_EXCEPTIONS):
+            return None  # Explicitly return None to drop the event
+
+    # Ignore exceptions with the ignored_exceptions
+    if "exc_info" in hint and hint["exc_info"]:
+        exc_value = str(hint["exc_info"][1])
+        if any(ignored in exc_value for ignored in IGNORED_EXCEPTIONS):
+            return None  # Explicitly return None to drop the event
+
     return event
 
 
@@ -85,4 +104,6 @@ sentry_sdk.init(
         # possible.
         "continuous_profiling_auto_start": True,
     },
+    attach_stacktrace=True,
+    ignore_errors=IGNORED_EXCEPTIONS,
 )

api/src/backend/config/settings/social_login.py

@@ -1,18 +1,17 @@
 from config.env import env
 
-# Google Oauth settings
-GOOGLE_OAUTH_CLIENT_ID = env("DJANGO_GOOGLE_OAUTH_CLIENT_ID", default="")
-GOOGLE_OAUTH_CLIENT_SECRET = env("DJANGO_GOOGLE_OAUTH_CLIENT_SECRET", default="")
-GOOGLE_OAUTH_CALLBACK_URL = env("DJANGO_GOOGLE_OAUTH_CALLBACK_URL", default="")
+# Provider Oauth settings
+GOOGLE_OAUTH_CLIENT_ID = env("SOCIAL_GOOGLE_OAUTH_CLIENT_ID", default="")
+GOOGLE_OAUTH_CLIENT_SECRET = env("SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET", default="")
+GOOGLE_OAUTH_CALLBACK_URL = env("SOCIAL_GOOGLE_OAUTH_CALLBACK_URL", default="")
 
-GITHUB_OAUTH_CLIENT_ID = env("DJANGO_GITHUB_OAUTH_CLIENT_ID", default="")
-GITHUB_OAUTH_CLIENT_SECRET = env("DJANGO_GITHUB_OAUTH_CLIENT_SECRET", default="")
-GITHUB_OAUTH_CALLBACK_URL = env("DJANGO_GITHUB_OAUTH_CALLBACK_URL", default="")
+GITHUB_OAUTH_CLIENT_ID = env("SOCIAL_GITHUB_OAUTH_CLIENT_ID", default="")
+GITHUB_OAUTH_CLIENT_SECRET = env("SOCIAL_GITHUB_OAUTH_CLIENT_SECRET", default="")
+GITHUB_OAUTH_CALLBACK_URL = env("SOCIAL_GITHUB_OAUTH_CALLBACK_URL", default="")
 
 # Allauth settings
 ACCOUNT_LOGIN_METHODS = {"email"}  # Use Email / Password authentication
-ACCOUNT_USERNAME_REQUIRED = False
-ACCOUNT_EMAIL_REQUIRED = True
+ACCOUNT_SIGNUP_FIELDS = ["email*", "password1*", "password2*"]
 ACCOUNT_EMAIL_VERIFICATION = "none"  # Do not require email confirmation
 ACCOUNT_USER_MODEL_USERNAME_FIELD = None
 REST_AUTH = {
@@ -25,6 +24,11 @@ SOCIALACCOUNT_EMAIL_AUTHENTICATION = True
 # Connect local account and social account if local account with that email address already exists
 SOCIALACCOUNT_EMAIL_AUTHENTICATION_AUTO_CONNECT = True
 SOCIALACCOUNT_ADAPTER = "api.adapters.ProwlerSocialAccountAdapter"
+
+# SAML keys
+SAML_PUBLIC_CERT = env("SAML_PUBLIC_CERT", default="")
+SAML_PRIVATE_KEY = env("SAML_PRIVATE_KEY", default="")
+
 SOCIALACCOUNT_PROVIDERS = {
     "google": {
         "APP": {
@@ -50,4 +54,18 @@ SOCIALACCOUNT_PROVIDERS = {
             "read:org",
         ],
     },
+    "saml": {
+        "use_nameid_for_email": True,
+        "sp": {
+            "entity_id": "urn:prowler.com:sp",
+        },
+        "advanced": {
+            "x509cert": SAML_PUBLIC_CERT,
+            "private_key": SAML_PRIVATE_KEY,
+            "name_id_format": "urn:oasis:names:tc:SAML:1.1:nameid-format:emailAddress",
+            "authn_request_signed": True,
+            "want_assertion_signed": True,
+            "want_message_signed": True,
+        },
+    },
 }

api/src/backend/conftest.py

@@ -1,8 +1,9 @@
 import logging
 from datetime import datetime, timedelta, timezone
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pytest
+from allauth.socialaccount.models import SocialLogin
 from django.conf import settings
 from django.db import connection as django_connection
 from django.db import connections as django_connections
@@ -10,14 +11,17 @@ from django.urls import reverse
 from django_celery_results.models import TaskResult
 from rest_framework import status
 from rest_framework.test import APIClient
+from tasks.jobs.backfill import backfill_resource_scan_summaries
 
 from api.db_utils import rls_transaction
 from api.models import (
     ComplianceOverview,
+    ComplianceRequirementOverview,
     Finding,
     Integration,
     IntegrationProviderRelationship,
     Invitation,
+    LighthouseConfiguration,
     Membership,
     Provider,
     ProviderGroup,
@@ -25,9 +29,12 @@ from api.models import (
     Resource,
     ResourceTag,
     Role,
+    SAMLConfiguration,
+    SAMLDomainIndex,
     Scan,
     ScanSummary,
     StateChoices,
+    StatusChoices,
     Task,
     User,
     UserRoleRelationship,
@@ -655,6 +662,7 @@ def findings_fixture(scans_fixture, resources_fixture):
             "Description": "test description orange juice",
         },
         first_seen_at="2024-01-02T00:00:00Z",
+        muted=True,
     )
 
     finding2.add_resources([resource2])
@@ -775,6 +783,131 @@ def compliance_overviews_fixture(scans_fixture, tenants_fixture):
     return compliance_overview1, compliance_overview2
 
 
+@pytest.fixture
+def compliance_requirements_overviews_fixture(scans_fixture, tenants_fixture):
+    """Fixture for ComplianceRequirementOverview objects used by the new ComplianceOverviewViewSet."""
+    tenant = tenants_fixture[0]
+    scan1, scan2, scan3 = scans_fixture
+
+    # Create ComplianceRequirementOverview objects for scan1
+    requirement_overview1 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="aws_account_security_onboarding_aws",
+        framework="AWS-Account-Security-Onboarding",
+        version="1.0",
+        description="Description for AWS Account Security Onboarding",
+        region="eu-west-1",
+        requirement_id="requirement1",
+        requirement_status=StatusChoices.PASS,
+        passed_checks=2,
+        failed_checks=0,
+        total_checks=2,
+    )
+
+    requirement_overview2 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="aws_account_security_onboarding_aws",
+        framework="AWS-Account-Security-Onboarding",
+        version="1.0",
+        description="Description for AWS Account Security Onboarding",
+        region="eu-west-1",
+        requirement_id="requirement2",
+        requirement_status=StatusChoices.PASS,
+        passed_checks=2,
+        failed_checks=0,
+        total_checks=2,
+    )
+
+    requirement_overview3 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="aws_account_security_onboarding_aws",
+        framework="AWS-Account-Security-Onboarding",
+        version="1.0",
+        description="Description for AWS Account Security Onboarding",
+        region="eu-west-2",
+        requirement_id="requirement1",
+        requirement_status=StatusChoices.PASS,
+        passed_checks=2,
+        failed_checks=0,
+        total_checks=2,
+    )
+
+    requirement_overview4 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="aws_account_security_onboarding_aws",
+        framework="AWS-Account-Security-Onboarding",
+        version="1.0",
+        description="Description for AWS Account Security Onboarding",
+        region="eu-west-2",
+        requirement_id="requirement2",
+        requirement_status=StatusChoices.FAIL,
+        passed_checks=1,
+        failed_checks=1,
+        total_checks=2,
+    )
+
+    requirement_overview5 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="aws_account_security_onboarding_aws",
+        framework="AWS-Account-Security-Onboarding",
+        version="1.0",
+        description="Description for AWS Account Security Onboarding (MANUAL)",
+        region="eu-west-2",
+        requirement_id="requirement3",
+        requirement_status=StatusChoices.MANUAL,
+        passed_checks=0,
+        failed_checks=0,
+        total_checks=0,
+    )
+
+    # Create a different compliance framework for testing
+    requirement_overview6 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="cis_1.4_aws",
+        framework="CIS-1.4-AWS",
+        version="1.4",
+        description="CIS AWS Foundations Benchmark v1.4.0",
+        region="eu-west-1",
+        requirement_id="cis_requirement1",
+        requirement_status=StatusChoices.FAIL,
+        passed_checks=0,
+        failed_checks=3,
+        total_checks=3,
+    )
+
+    # Create another compliance framework for testing MITRE ATT&CK
+    requirement_overview7 = ComplianceRequirementOverview.objects.create(
+        tenant=tenant,
+        scan=scan1,
+        compliance_id="mitre_attack_aws",
+        framework="MITRE-ATTACK",
+        version="1.0",
+        description="MITRE ATT&CK",
+        region="eu-west-1",
+        requirement_id="mitre_requirement1",
+        requirement_status=StatusChoices.FAIL,
+        passed_checks=0,
+        failed_checks=0,
+        total_checks=0,
+    )
+
+    return (
+        requirement_overview1,
+        requirement_overview2,
+        requirement_overview3,
+        requirement_overview4,
+        requirement_overview5,
+        requirement_overview6,
+        requirement_overview7,
+    )
+
+
 def get_api_tokens(
     api_client, user_email: str, user_password: str, tenant_id: str = None
 ) -> tuple[str, str]:
@@ -919,6 +1052,127 @@ def integrations_fixture(providers_fixture):
     return integration1, integration2
 
 
+@pytest.fixture
+def backfill_scan_metadata_fixture(scans_fixture, findings_fixture):
+    for scan_instance in scans_fixture:
+        tenant_id = scan_instance.tenant_id
+        scan_id = scan_instance.id
+        backfill_resource_scan_summaries(tenant_id=tenant_id, scan_id=scan_id)
+
+
+@pytest.fixture
+def lighthouse_config_fixture(authenticated_client, tenants_fixture):
+    return LighthouseConfiguration.objects.create(
+        tenant_id=tenants_fixture[0].id,
+        name="OpenAI",
+        api_key_decoded="sk-test1234567890T3BlbkFJtest1234567890",
+        model="gpt-4o",
+        temperature=0,
+        max_tokens=4000,
+        business_context="Test business context",
+        is_active=True,
+    )
+
+
+@pytest.fixture(scope="function")
+def latest_scan_finding(authenticated_client, providers_fixture, resources_fixture):
+    provider = providers_fixture[0]
+    tenant_id = str(providers_fixture[0].tenant_id)
+    resource = resources_fixture[0]
+    scan = Scan.objects.create(
+        name="latest completed scan",
+        provider=provider,
+        trigger=Scan.TriggerChoices.MANUAL,
+        state=StateChoices.COMPLETED,
+        tenant_id=tenant_id,
+    )
+    finding = Finding.objects.create(
+        tenant_id=tenant_id,
+        uid="test_finding_uid_1",
+        scan=scan,
+        delta="new",
+        status=Status.FAIL,
+        status_extended="test status extended ",
+        impact=Severity.critical,
+        impact_extended="test impact extended one",
+        severity=Severity.critical,
+        raw_result={
+            "status": Status.FAIL,
+            "impact": Severity.critical,
+            "severity": Severity.critical,
+        },
+        tags={"test": "dev-qa"},
+        check_id="test_check_id",
+        check_metadata={
+            "CheckId": "test_check_id",
+            "Description": "test description apple sauce",
+        },
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+
+    finding.add_resources([resource])
+    backfill_resource_scan_summaries(tenant_id, str(scan.id))
+    return finding
+
+
+@pytest.fixture
+def saml_setup(tenants_fixture):
+    tenant_id = tenants_fixture[0].id
+    domain = "example.com"
+
+    SAMLDomainIndex.objects.create(email_domain=domain, tenant_id=tenant_id)
+
+    metadata_xml = """<?xml version='1.0' encoding='UTF-8'?>
+    <md:EntityDescriptor entityID='TEST' xmlns:md='urn:oasis:names:tc:SAML:2.0:metadata'>
+    <md:IDPSSODescriptor WantAuthnRequestsSigned='false' protocolSupportEnumeration='urn:oasis:names:tc:SAML:2.0:protocol'>
+        <md:KeyDescriptor use='signing'>
+        <ds:KeyInfo xmlns:ds='http://www.w3.org/2000/09/xmldsig#'>
+            <ds:X509Data>
+            <ds:X509Certificate>TEST</ds:X509Certificate>
+            </ds:X509Data>
+        </ds:KeyInfo>
+        </md:KeyDescriptor>
+        <md:NameIDFormat>urn:oasis:names:tc:SAML:1.1:nameid-format:emailAddress</md:NameIDFormat>
+        <md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-POST' Location='https://TEST/sso/saml'/>
+        <md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-Redirect' Location='https://TEST/sso/saml'/>
+    </md:IDPSSODescriptor>
+    </md:EntityDescriptor>
+    """
+    SAMLConfiguration.objects.create(
+        tenant_id=str(tenant_id),
+        email_domain=domain,
+        metadata_xml=metadata_xml,
+    )
+
+    return {
+        "email": f"user@{domain}",
+        "domain": domain,
+        "tenant_id": tenant_id,
+    }
+
+
+@pytest.fixture
+def saml_sociallogin(users_fixture):
+    user = users_fixture[0]
+    user.email = "samlsso@acme.com"
+    extra_data = {
+        "firstName": ["Test"],
+        "lastName": ["User"],
+        "organization": ["Prowler"],
+        "userType": ["member"],
+    }
+
+    account = MagicMock()
+    account.provider = "saml"
+    account.extra_data = extra_data
+
+    sociallogin = MagicMock(spec=SocialLogin)
+    sociallogin.account = account
+    sociallogin.user = user
+
+    return sociallogin
+
+
 def get_authorization_header(access_token: str) -> dict:
     return {"Authorization": f"Bearer {access_token}"}
 

api/src/backend/manage.py

@@ -3,6 +3,12 @@
 
 import os
 import sys
+import warnings
+
+# Suppress specific warnings from django-rest-auth: https://github.com/iMerica/dj-rest-auth/issues/684
+warnings.filterwarnings(
+    "ignore", category=UserWarning, module="dj_rest_auth.registration.serializers"
+)
 
 
 def main():

api/src/backend/tasks/jobs/backfill.py

@@ -0,0 +1,61 @@
+from api.db_utils import rls_transaction
+from api.models import (
+    Resource,
+    ResourceFindingMapping,
+    ResourceScanSummary,
+    Scan,
+    StateChoices,
+)
+
+
+def backfill_resource_scan_summaries(tenant_id: str, scan_id: str):
+    with rls_transaction(tenant_id):
+        if ResourceScanSummary.objects.filter(
+            tenant_id=tenant_id, scan_id=scan_id
+        ).exists():
+            return {"status": "already backfilled"}
+
+    with rls_transaction(tenant_id):
+        if not Scan.objects.filter(
+            tenant_id=tenant_id,
+            id=scan_id,
+            state__in=(StateChoices.COMPLETED, StateChoices.FAILED),
+        ).exists():
+            return {"status": "scan is not completed"}
+
+        resource_ids_qs = (
+            ResourceFindingMapping.objects.filter(
+                tenant_id=tenant_id, finding__scan_id=scan_id
+            )
+            .values_list("resource_id", flat=True)
+            .distinct()
+        )
+
+        resource_ids = list(resource_ids_qs)
+
+        if not resource_ids:
+            return {"status": "no resources to backfill"}
+
+        resources_qs = Resource.objects.filter(
+            tenant_id=tenant_id, id__in=resource_ids
+        ).only("id", "service", "region", "type")
+
+        summaries = []
+        for resource in resources_qs.iterator():
+            summaries.append(
+                ResourceScanSummary(
+                    tenant_id=tenant_id,
+                    scan_id=scan_id,
+                    resource_id=str(resource.id),
+                    service=resource.service,
+                    region=resource.region,
+                    resource_type=resource.type,
+                )
+            )
+
+        for i in range(0, len(summaries), 500):
+            ResourceScanSummary.objects.bulk_create(
+                summaries[i : i + 500], ignore_conflicts=True
+            )
+
+    return {"status": "backfilled", "inserted": len(summaries)}

api/src/backend/tasks/jobs/connection.py

@@ -1,8 +1,9 @@
 from datetime import datetime, timezone
 
+import openai
 from celery.utils.log import get_task_logger
 
-from api.models import Provider
+from api.models import LighthouseConfiguration, Provider
 from api.utils import prowler_provider_connection_test
 
 logger = get_task_logger(__name__)
@@ -39,3 +40,46 @@ def check_provider_connection(provider_id: str):
 
     connection_error = f"{connection_result.error}" if connection_result.error else None
     return {"connected": connection_result.is_connected, "error": connection_error}
+
+
+def check_lighthouse_connection(lighthouse_config_id: str):
+    """
+    Business logic to check the connection status of a Lighthouse configuration.
+
+    Args:
+        lighthouse_config_id (str): The primary key of the LighthouseConfiguration instance to check.
+
+    Returns:
+        dict: A dictionary containing:
+            - 'connected' (bool): Indicates whether the connection is successful.
+            - 'error' (str or None): The error message if the connection failed, otherwise `None`.
+            - 'available_models' (list): List of available models if connection is successful.
+
+    Raises:
+        Model.DoesNotExist: If the lighthouse configuration does not exist.
+    """
+    lighthouse_config = LighthouseConfiguration.objects.get(pk=lighthouse_config_id)
+
+    if not lighthouse_config.api_key_decoded:
+        lighthouse_config.is_active = False
+        lighthouse_config.save()
+        return {
+            "connected": False,
+            "error": "API key is invalid or missing.",
+            "available_models": [],
+        }
+
+    try:
+        client = openai.OpenAI(api_key=lighthouse_config.api_key_decoded)
+        models = client.models.list()
+        lighthouse_config.is_active = True
+        lighthouse_config.save()
+        return {
+            "connected": True,
+            "error": None,
+            "available_models": [model.id for model in models.data],
+        }
+    except Exception as e:
+        lighthouse_config.is_active = False
+        lighthouse_config.save()
+        return {"connected": False, "error": str(e), "available_models": []}

api/src/backend/tasks/jobs/deletion.py

@@ -1,5 +1,5 @@
 from celery.utils.log import get_task_logger
-from django.db import transaction
+from django.db import DatabaseError
 
 from api.db_router import MainRouter
 from api.db_utils import batch_delete, rls_transaction
@@ -8,11 +8,12 @@ from api.models import Finding, Provider, Resource, Scan, ScanSummary, Tenant
 logger = get_task_logger(__name__)
 
 
-def delete_provider(pk: str):
+def delete_provider(tenant_id: str, pk: str):
     """
     Gracefully deletes an instance of a provider along with its related data.
 
     Args:
+        tenant_id (str): Tenant ID the resources belong to.
         pk (str): The primary key of the Provider instance to delete.
 
     Returns:
@@ -22,33 +23,31 @@ def delete_provider(pk: str):
     Raises:
         Provider.DoesNotExist: If no instance with the provided primary key exists.
     """
-    instance = Provider.all_objects.get(pk=pk)
-    deletion_summary = {}
+    with rls_transaction(tenant_id):
+        instance = Provider.all_objects.get(pk=pk)
+        deletion_summary = {}
+        deletion_steps = [
+            ("Scan Summaries", ScanSummary.all_objects.filter(scan__provider=instance)),
+            ("Findings", Finding.all_objects.filter(scan__provider=instance)),
+            ("Resources", Resource.all_objects.filter(provider=instance)),
+            ("Scans", Scan.all_objects.filter(provider=instance)),
+        ]
 
-    with transaction.atomic():
-        # Delete Scan Summaries
-        scan_summaries_qs = ScanSummary.all_objects.filter(scan__provider=instance)
-        _, scans_summ_summary = batch_delete(scan_summaries_qs)
-        deletion_summary.update(scans_summ_summary)
+    for step_name, queryset in deletion_steps:
+        try:
+            _, step_summary = batch_delete(tenant_id, queryset)
+            deletion_summary.update(step_summary)
+        except DatabaseError as db_error:
+            logger.error(f"Error deleting {step_name}: {db_error}")
+            raise
 
-        # Delete Findings
-        findings_qs = Finding.all_objects.filter(scan__provider=instance)
-        _, findings_summary = batch_delete(findings_qs)
-        deletion_summary.update(findings_summary)
-
-        # Delete Resources
-        resources_qs = Resource.all_objects.filter(provider=instance)
-        _, resources_summary = batch_delete(resources_qs)
-        deletion_summary.update(resources_summary)
-
-        # Delete Scans
-        scans_qs = Scan.all_objects.filter(provider=instance)
-        _, scans_summary = batch_delete(scans_qs)
-        deletion_summary.update(scans_summary)
-
-        provider_deleted_count, provider_summary = instance.delete()
+    try:
+        with rls_transaction(tenant_id):
+            _, provider_summary = instance.delete()
         deletion_summary.update(provider_summary)
-
+    except DatabaseError as db_error:
+        logger.error(f"Error deleting Provider: {db_error}")
+        raise
     return deletion_summary
 
 
@@ -66,9 +65,8 @@ def delete_tenant(pk: str):
     deletion_summary = {}
 
     for provider in Provider.objects.using(MainRouter.admin_db).filter(tenant_id=pk):
-        with rls_transaction(pk):
-            summary = delete_provider(provider.id)
-            deletion_summary.update(summary)
+        summary = delete_provider(pk, provider.id)
+        deletion_summary.update(summary)
 
     Tenant.objects.using(MainRouter.admin_db).filter(id=pk).delete()
 

api/src/backend/tasks/jobs/export.py

@@ -1,4 +1,5 @@
 import os
+import re
 import zipfile
 
 import boto3
@@ -13,6 +14,42 @@ from prowler.config.config import (
     json_ocsf_file_suffix,
     output_file_timestamp,
 )
+from prowler.lib.outputs.compliance.aws_well_architected.aws_well_architected import (
+    AWSWellArchitected,
+)
+from prowler.lib.outputs.compliance.cis.cis_aws import AWSCIS
+from prowler.lib.outputs.compliance.cis.cis_azure import AzureCIS
+from prowler.lib.outputs.compliance.cis.cis_gcp import GCPCIS
+from prowler.lib.outputs.compliance.cis.cis_kubernetes import KubernetesCIS
+from prowler.lib.outputs.compliance.cis.cis_m365 import M365CIS
+from prowler.lib.outputs.compliance.ens.ens_aws import AWSENS
+from prowler.lib.outputs.compliance.ens.ens_azure import AzureENS
+from prowler.lib.outputs.compliance.ens.ens_gcp import GCPENS
+from prowler.lib.outputs.compliance.iso27001.iso27001_aws import AWSISO27001
+from prowler.lib.outputs.compliance.iso27001.iso27001_azure import AzureISO27001
+from prowler.lib.outputs.compliance.iso27001.iso27001_gcp import GCPISO27001
+from prowler.lib.outputs.compliance.iso27001.iso27001_kubernetes import (
+    KubernetesISO27001,
+)
+from prowler.lib.outputs.compliance.iso27001.iso27001_m365 import M365ISO27001
+from prowler.lib.outputs.compliance.kisa_ismsp.kisa_ismsp_aws import AWSKISAISMSP
+from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_aws import AWSMitreAttack
+from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_azure import (
+    AzureMitreAttack,
+)
+from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_gcp import GCPMitreAttack
+from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_aws import (
+    ProwlerThreatScoreAWS,
+)
+from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_azure import (
+    ProwlerThreatScoreAzure,
+)
+from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_gcp import (
+    ProwlerThreatScoreGCP,
+)
+from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_m365 import (
+    ProwlerThreatScoreM365,
+)
 from prowler.lib.outputs.csv.csv import CSV
 from prowler.lib.outputs.html.html import HTML
 from prowler.lib.outputs.ocsf.ocsf import OCSF
@@ -20,6 +57,45 @@ from prowler.lib.outputs.ocsf.ocsf import OCSF
 logger = get_task_logger(__name__)
 
 
+COMPLIANCE_CLASS_MAP = {
+    "aws": [
+        (lambda name: name.startswith("cis_"), AWSCIS),
+        (lambda name: name == "mitre_attack_aws", AWSMitreAttack),
+        (lambda name: name.startswith("ens_"), AWSENS),
+        (
+            lambda name: name.startswith("aws_well_architected_framework"),
+            AWSWellArchitected,
+        ),
+        (lambda name: name.startswith("iso27001_"), AWSISO27001),
+        (lambda name: name.startswith("kisa"), AWSKISAISMSP),
+        (lambda name: name == "prowler_threatscore_aws", ProwlerThreatScoreAWS),
+    ],
+    "azure": [
+        (lambda name: name.startswith("cis_"), AzureCIS),
+        (lambda name: name == "mitre_attack_azure", AzureMitreAttack),
+        (lambda name: name.startswith("ens_"), AzureENS),
+        (lambda name: name.startswith("iso27001_"), AzureISO27001),
+        (lambda name: name == "prowler_threatscore_azure", ProwlerThreatScoreAzure),
+    ],
+    "gcp": [
+        (lambda name: name.startswith("cis_"), GCPCIS),
+        (lambda name: name == "mitre_attack_gcp", GCPMitreAttack),
+        (lambda name: name.startswith("ens_"), GCPENS),
+        (lambda name: name.startswith("iso27001_"), GCPISO27001),
+        (lambda name: name == "prowler_threatscore_gcp", ProwlerThreatScoreGCP),
+    ],
+    "kubernetes": [
+        (lambda name: name.startswith("cis_"), KubernetesCIS),
+        (lambda name: name.startswith("iso27001_"), KubernetesISO27001),
+    ],
+    "m365": [
+        (lambda name: name.startswith("iso27001_"), M365ISO27001),
+        (lambda name: name.startswith("cis_"), M365CIS),
+        (lambda name: name == "prowler_threatscore_m365", ProwlerThreatScoreM365),
+    ],
+}
+
+
 # Predefined mapping for output formats and their configurations
 OUTPUT_FORMATS_MAPPING = {
     "csv": {
@@ -43,13 +119,17 @@ def _compress_output_files(output_directory: str) -> str:
         str: The full path to the newly created ZIP archive.
     """
     zip_path = f"{output_directory}.zip"
+    parent_dir = os.path.dirname(output_directory)
+    zip_path_abs = os.path.abspath(zip_path)
 
     with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zipf:
-        for suffix in [config["suffix"] for config in OUTPUT_FORMATS_MAPPING.values()]:
-            zipf.write(
-                f"{output_directory}{suffix}",
-                f"output/{output_directory.split('/')[-1]}{suffix}",
-            )
+        for foldername, _, filenames in os.walk(parent_dir):
+            for filename in filenames:
+                file_path = os.path.join(foldername, filename)
+                if os.path.abspath(file_path) == zip_path_abs:
+                    continue
+                arcname = os.path.relpath(file_path, start=parent_dir)
+                zipf.write(file_path, arcname)
 
     return zip_path
 
@@ -102,25 +182,38 @@ def _upload_to_s3(tenant_id: str, zip_path: str, scan_id: str) -> str:
     Raises:
         botocore.exceptions.ClientError: If the upload attempt to S3 fails for any reason.
     """
-    if not base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET:
-        return
+    bucket = base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET
+    if not bucket:
+        return None
 
     try:
         s3 = get_s3_client()
-        s3_key = f"{tenant_id}/{scan_id}/{os.path.basename(zip_path)}"
+
+        # Upload the ZIP file (outputs) to the S3 bucket
+        zip_key = f"{tenant_id}/{scan_id}/{os.path.basename(zip_path)}"
         s3.upload_file(
             Filename=zip_path,
-            Bucket=base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET,
-            Key=s3_key,
+            Bucket=bucket,
+            Key=zip_key,
         )
-        return f"s3://{base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET}/{s3_key}"
+
+        # Upload the compliance directory to the S3 bucket
+        compliance_dir = os.path.join(os.path.dirname(zip_path), "compliance")
+        for filename in os.listdir(compliance_dir):
+            local_path = os.path.join(compliance_dir, filename)
+            if not os.path.isfile(local_path):
+                continue
+            file_key = f"{tenant_id}/{scan_id}/compliance/{filename}"
+            s3.upload_file(Filename=local_path, Bucket=bucket, Key=file_key)
+
+        return f"s3://{base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET}/{zip_key}"
     except (ClientError, NoCredentialsError, ParamValidationError, ValueError) as e:
         logger.error(f"S3 upload failed: {str(e)}")
 
 
 def _generate_output_directory(
     output_directory, prowler_provider: object, tenant_id: str, scan_id: str
-) -> str:
+) -> tuple[str, str]:
     """
     Generate a file system path for the output directory of a prowler scan.
 
@@ -145,12 +238,22 @@ def _generate_output_directory(
 
     Example:
         >>> _generate_output_directory("/tmp", "aws", "tenant-1234", "scan-5678")
-        '/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56'
+        '/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56',
+        '/tmp/tenant-1234/aws/scan-5678/compliance/prowler-output-2023-02-15T12:34:56'
     """
+    # Sanitize the prowler provider name to ensure it is a valid directory name
+    prowler_provider_sanitized = re.sub(r"[^\w\-]", "-", prowler_provider)
+
     path = (
         f"{output_directory}/{tenant_id}/{scan_id}/prowler-output-"
-        f"{prowler_provider}-{output_file_timestamp}"
+        f"{prowler_provider_sanitized}-{output_file_timestamp}"
     )
     os.makedirs("/".join(path.split("/")[:-1]), exist_ok=True)
 
-    return path
+    compliance_path = (
+        f"{output_directory}/{tenant_id}/{scan_id}/compliance/prowler-output-"
+        f"{prowler_provider_sanitized}-{output_file_timestamp}"
+    )
+    os.makedirs("/".join(compliance_path.split("/")[:-1]), exist_ok=True)
+
+    return path, compliance_path

api/src/backend/tasks/jobs/scan.py

@@ -1,3 +1,4 @@
+import json
 import time
 from copy import deepcopy
 from datetime import datetime, timezone
@@ -6,17 +7,19 @@ from celery.utils.log import get_task_logger
 from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
 from django.db import IntegrityError, OperationalError
 from django.db.models import Case, Count, IntegerField, Sum, When
+from tasks.utils import CustomEncoder
 
 from api.compliance import (
     PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
     generate_scan_compliance,
 )
-from api.db_utils import rls_transaction
+from api.db_utils import create_objects_in_batches, rls_transaction
 from api.models import (
-    ComplianceOverview,
+    ComplianceRequirementOverview,
     Finding,
     Provider,
     Resource,
+    ResourceScanSummary,
     ResourceTag,
     Scan,
     ScanSummary,
@@ -116,10 +119,11 @@ def perform_prowler_scan(
         ValueError: If the provider cannot be connected.
 
     """
-    check_status_by_region = {}
     exception = None
     unique_resources = set()
+    scan_resource_cache: set[tuple[str, str, str, str]] = set()
     start_time = time.time()
+    exc = None
 
     with rls_transaction(tenant_id):
         provider_instance = Provider.objects.get(pk=provider_id)
@@ -135,7 +139,7 @@ def perform_prowler_scan(
                 provider_instance.connected = True
             except Exception as e:
                 provider_instance.connected = False
-                raise ValueError(
+                exc = ValueError(
                     f"Provider {provider_instance.provider} is not connected: {e}"
                 )
             finally:
@@ -144,6 +148,11 @@ def perform_prowler_scan(
                 )
                 provider_instance.save()
 
+        # If the provider is not connected, raise an exception outside the transaction.
+        # If raised within the transaction, the transaction will be rolled back and the provider will not be marked as not connected.
+        if exc:
+            raise exc
+
         prowler_scan = ProwlerScan(provider=prowler_provider, checks=checks_to_execute)
 
         resource_cache = {}
@@ -191,6 +200,17 @@ def perform_prowler_scan(
                         if resource_instance.type != finding.resource_type:
                             resource_instance.type = finding.resource_type
                             updated_fields.append("type")
+                        if resource_instance.metadata != finding.resource_metadata:
+                            resource_instance.metadata = json.dumps(
+                                finding.resource_metadata, cls=CustomEncoder
+                            )
+                            updated_fields.append("metadata")
+                        if resource_instance.details != finding.resource_details:
+                            resource_instance.details = finding.resource_details
+                            updated_fields.append("details")
+                        if resource_instance.partition != finding.partition:
+                            resource_instance.partition = finding.partition
+                            updated_fields.append("partition")
                         if updated_fields:
                             with rls_transaction(tenant_id):
                                 resource_instance.save(update_fields=updated_fields)
@@ -267,18 +287,20 @@ def perform_prowler_scan(
                         check_id=finding.check_id,
                         scan=scan_instance,
                         first_seen_at=last_first_seen_at,
+                        muted=finding.muted,
+                        compliance=finding.compliance,
                     )
                     finding_instance.add_resources([resource_instance])
 
-                # Update compliance data if applicable
-                if finding.status.value == "MUTED":
-                    continue
-
-                region_dict = check_status_by_region.setdefault(finding.region, {})
-                current_status = region_dict.get(finding.check_id)
-                if current_status == "FAIL":
-                    continue
-                region_dict[finding.check_id] = finding.status.value
+                # Update scan resource summaries
+                scan_resource_cache.add(
+                    (
+                        str(resource_instance.id),
+                        resource_instance.service,
+                        resource_instance.region,
+                        resource_instance.type,
+                    )
+                )
 
             # Update scan progress
             with rls_transaction(tenant_id):
@@ -299,66 +321,33 @@ def perform_prowler_scan(
             scan_instance.unique_resource_count = len(unique_resources)
             scan_instance.save()
 
-    if exception is None:
-        try:
-            regions = prowler_provider.get_regions()
-        except AttributeError:
-            regions = set()
-
-        compliance_template = PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE[
-            provider_instance.provider
-        ]
-        compliance_overview_by_region = {
-            region: deepcopy(compliance_template) for region in regions
-        }
-
-        for region, check_status in check_status_by_region.items():
-            compliance_data = compliance_overview_by_region.setdefault(
-                region, deepcopy(compliance_template)
-            )
-            for check_name, status in check_status.items():
-                generate_scan_compliance(
-                    compliance_data,
-                    provider_instance.provider,
-                    check_name,
-                    status,
-                )
-
-        # Prepare compliance overview objects
-        compliance_overview_objects = []
-        for region, compliance_data in compliance_overview_by_region.items():
-            for compliance_id, compliance in compliance_data.items():
-                compliance_overview_objects.append(
-                    ComplianceOverview(
-                        tenant_id=tenant_id,
-                        scan=scan_instance,
-                        region=region,
-                        compliance_id=compliance_id,
-                        framework=compliance["framework"],
-                        version=compliance["version"],
-                        description=compliance["description"],
-                        requirements=compliance["requirements"],
-                        requirements_passed=compliance["requirements_status"]["passed"],
-                        requirements_failed=compliance["requirements_status"]["failed"],
-                        requirements_manual=compliance["requirements_status"]["manual"],
-                        total_requirements=compliance["total_requirements"],
-                    )
-                )
-        try:
-            with rls_transaction(tenant_id):
-                ComplianceOverview.objects.bulk_create(
-                    compliance_overview_objects, batch_size=100
-                )
-        except Exception as overview_exception:
-            import sentry_sdk
-
-            sentry_sdk.capture_exception(overview_exception)
-            logger.error(
-                f"Error storing compliance overview for scan {scan_id}: {overview_exception}"
-            )
     if exception is not None:
         raise exception
 
+    try:
+        resource_scan_summaries = [
+            ResourceScanSummary(
+                tenant_id=tenant_id,
+                scan_id=scan_id,
+                resource_id=resource_id,
+                service=service,
+                region=region,
+                resource_type=resource_type,
+            )
+            for resource_id, service, region, resource_type in scan_resource_cache
+        ]
+        with rls_transaction(tenant_id):
+            ResourceScanSummary.objects.bulk_create(
+                resource_scan_summaries, batch_size=500, ignore_conflicts=True
+            )
+    except Exception as filter_exception:
+        import sentry_sdk
+
+        sentry_sdk.capture_exception(filter_exception)
+        logger.error(
+            f"Error storing filter values for scan {scan_id}: {filter_exception}"
+        )
+
     serializer = ScanTaskSerializer(instance=scan_instance)
     return serializer.data
 
@@ -402,21 +391,21 @@ def aggregate_findings(tenant_id: str, scan_id: str):
         ).annotate(
             fail=Sum(
                 Case(
-                    When(status="FAIL", then=1),
+                    When(status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             _pass=Sum(
                 Case(
-                    When(status="PASS", then=1),
+                    When(status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
-            muted=Sum(
+            muted_count=Sum(
                 Case(
-                    When(status="MUTED", then=1),
+                    When(muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
@@ -424,63 +413,63 @@ def aggregate_findings(tenant_id: str, scan_id: str):
             total=Count("id"),
             new=Sum(
                 Case(
-                    When(delta="new", then=1),
+                    When(delta="new", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             changed=Sum(
                 Case(
-                    When(delta="changed", then=1),
+                    When(delta="changed", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             unchanged=Sum(
                 Case(
-                    When(delta__isnull=True, then=1),
+                    When(delta__isnull=True, muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             fail_new=Sum(
                 Case(
-                    When(delta="new", status="FAIL", then=1),
+                    When(delta="new", status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             fail_changed=Sum(
                 Case(
-                    When(delta="changed", status="FAIL", then=1),
+                    When(delta="changed", status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             pass_new=Sum(
                 Case(
-                    When(delta="new", status="PASS", then=1),
+                    When(delta="new", status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             pass_changed=Sum(
                 Case(
-                    When(delta="changed", status="PASS", then=1),
+                    When(delta="changed", status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             muted_new=Sum(
                 Case(
-                    When(delta="new", status="MUTED", then=1),
+                    When(delta="new", muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             muted_changed=Sum(
                 Case(
-                    When(delta="changed", status="MUTED", then=1),
+                    When(delta="changed", muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
@@ -498,7 +487,7 @@ def aggregate_findings(tenant_id: str, scan_id: str):
                 region=agg["resources__region"],
                 fail=agg["fail"],
                 _pass=agg["_pass"],
-                muted=agg["muted"],
+                muted=agg["muted_count"],
                 total=agg["total"],
                 new=agg["new"],
                 changed=agg["changed"],
@@ -513,3 +502,114 @@ def aggregate_findings(tenant_id: str, scan_id: str):
             for agg in aggregation
         }
         ScanSummary.objects.bulk_create(scan_aggregations, batch_size=3000)
+
+
+def create_compliance_requirements(tenant_id: str, scan_id: str):
+    """
+    Create detailed compliance requirement overview records for a scan.
+
+    This function processes the compliance data collected during a scan and creates
+    individual records for each compliance requirement in each region. These detailed
+    records provide a granular view of compliance status.
+
+    Args:
+        tenant_id (str): The ID of the tenant for which to create records.
+        scan_id (str): The ID of the scan for which to create records.
+
+    Returns:
+        dict: A dictionary containing the number of requirements created and the regions processed.
+
+    Raises:
+        ValidationError: If tenant_id is not a valid UUID.
+    """
+    try:
+        with rls_transaction(tenant_id):
+            scan_instance = Scan.objects.get(pk=scan_id)
+            provider_instance = scan_instance.provider
+            prowler_provider = initialize_prowler_provider(provider_instance)
+
+        # Get check status data by region from findings
+        check_status_by_region = {}
+        with rls_transaction(tenant_id):
+            findings = Finding.objects.filter(scan_id=scan_id, muted=False)
+            for finding in findings:
+                # Get region from resources
+                for resource in finding.resources.all():
+                    region = resource.region
+                    region_dict = check_status_by_region.setdefault(region, {})
+                    current_status = region_dict.get(finding.check_id)
+                    if current_status == "FAIL":
+                        continue
+                    region_dict[finding.check_id] = finding.status
+
+        try:
+            # Try to get regions from provider
+            regions = prowler_provider.get_regions()
+        except (AttributeError, Exception):
+            # If not available, use regions from findings
+            regions = set(check_status_by_region.keys())
+
+        # Get compliance template for the provider
+        compliance_template = PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE[
+            provider_instance.provider
+        ]
+
+        # Create compliance data by region
+        compliance_overview_by_region = {
+            region: deepcopy(compliance_template) for region in regions
+        }
+
+        # Apply check statuses to compliance data
+        for region, check_status in check_status_by_region.items():
+            compliance_data = compliance_overview_by_region.setdefault(
+                region, deepcopy(compliance_template)
+            )
+            for check_name, status in check_status.items():
+                generate_scan_compliance(
+                    compliance_data,
+                    provider_instance.provider,
+                    check_name,
+                    status,
+                )
+
+        # Prepare compliance requirement objects
+        compliance_requirement_objects = []
+        for region, compliance_data in compliance_overview_by_region.items():
+            for compliance_id, compliance in compliance_data.items():
+                # Create an overview record for each requirement within each compliance framework
+                for requirement_id, requirement in compliance["requirements"].items():
+                    compliance_requirement_objects.append(
+                        ComplianceRequirementOverview(
+                            tenant_id=tenant_id,
+                            scan=scan_instance,
+                            region=region,
+                            compliance_id=compliance_id,
+                            framework=compliance["framework"],
+                            version=compliance["version"],
+                            requirement_id=requirement_id,
+                            description=requirement["description"],
+                            passed_checks=requirement["checks_status"]["pass"],
+                            failed_checks=requirement["checks_status"]["fail"],
+                            total_checks=requirement["checks_status"]["total"],
+                            requirement_status=requirement["status"],
+                        )
+                    )
+
+        # Bulk create requirement records
+        create_objects_in_batches(
+            tenant_id, ComplianceRequirementOverview, compliance_requirement_objects
+        )
+
+        return {
+            "requirements_created": len(compliance_requirement_objects),
+            "regions_processed": list(regions),
+            "compliance_frameworks": (
+                list(compliance_overview_by_region.get(list(regions)[0], {}).keys())
+                if regions
+                else []
+            ),
+        }
+
+    except Exception as e:
+        logger.error(f"Error creating compliance requirements for scan {scan_id}: {e}")
+        raise e

api/src/backend/tasks/tasks.py

@@ -1,3 +1,5 @@
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
 from shutil import rmtree
 
 from celery import chain, shared_task
@@ -5,21 +7,31 @@ from celery.utils.log import get_task_logger
 from config.celery import RLSTask
 from config.django.base import DJANGO_FINDINGS_BATCH_SIZE, DJANGO_TMP_OUTPUT_DIRECTORY
 from django_celery_beat.models import PeriodicTask
-from tasks.jobs.connection import check_provider_connection
+from tasks.jobs.backfill import backfill_resource_scan_summaries
+from tasks.jobs.connection import check_lighthouse_connection, check_provider_connection
 from tasks.jobs.deletion import delete_provider, delete_tenant
 from tasks.jobs.export import (
+    COMPLIANCE_CLASS_MAP,
     OUTPUT_FORMATS_MAPPING,
     _compress_output_files,
     _generate_output_directory,
     _upload_to_s3,
 )
-from tasks.jobs.scan import aggregate_findings, perform_prowler_scan
+from tasks.jobs.scan import (
+    aggregate_findings,
+    create_compliance_requirements,
+    perform_prowler_scan,
+)
 from tasks.utils import batched, get_next_execution_datetime
 
+from api.compliance import get_compliance_frameworks
 from api.db_utils import rls_transaction
 from api.decorators import set_tenant
 from api.models import Finding, Provider, Scan, ScanSummary, StateChoices
 from api.utils import initialize_prowler_provider
+from api.v1.serializers import ScanTaskSerializer
+from prowler.lib.check.compliance_models import Compliance
+from prowler.lib.outputs.compliance.generic.generic import GenericCompliance
 from prowler.lib.outputs.finding import Finding as FindingOutput
 
 logger = get_task_logger(__name__)
@@ -42,9 +54,10 @@ def check_provider_connection_task(provider_id: str):
     return check_provider_connection(provider_id=provider_id)
 
 
-@shared_task(base=RLSTask, name="provider-deletion", queue="deletion")
-@set_tenant
-def delete_provider_task(provider_id: str):
+@shared_task(
+    base=RLSTask, name="provider-deletion", queue="deletion", autoretry_for=(Exception,)
+)
+def delete_provider_task(provider_id: str, tenant_id: str):
     """
     Task to delete a specific Provider instance.
 
@@ -52,6 +65,7 @@ def delete_provider_task(provider_id: str):
 
     Args:
         provider_id (str): The primary key of the `Provider` instance to be deleted.
+        tenant_id (str): Tenant ID the provider belongs to.
 
     Returns:
         tuple: A tuple containing:
@@ -59,7 +73,7 @@ def delete_provider_task(provider_id: str):
             - A dictionary with the count of deleted instances per model,
               including related models if cascading deletes were triggered.
     """
-    return delete_provider(pk=provider_id)
+    return delete_provider(tenant_id=tenant_id, pk=provider_id)
 
 
 @shared_task(base=RLSTask, name="scan-perform", queue="scans")
@@ -91,6 +105,7 @@ def perform_scan_task(
 
     chain(
         perform_scan_summary_task.si(tenant_id, scan_id),
+        create_compliance_requirements_task.si(tenant_id=tenant_id, scan_id=scan_id),
         generate_outputs.si(
             scan_id=scan_id, provider_id=provider_id, tenant_id=tenant_id
         ),
@@ -125,6 +140,43 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
         periodic_task_instance = PeriodicTask.objects.get(
             name=f"scan-perform-scheduled-{provider_id}"
         )
+
+        executed_scan = Scan.objects.filter(
+            tenant_id=tenant_id,
+            provider_id=provider_id,
+            task__task_runner_task__task_id=task_id,
+        ).order_by("completed_at")
+
+        if (
+            Scan.objects.filter(
+                tenant_id=tenant_id,
+                provider_id=provider_id,
+                trigger=Scan.TriggerChoices.SCHEDULED,
+                state=StateChoices.EXECUTING,
+                scheduler_task_id=periodic_task_instance.id,
+                scheduled_at__date=datetime.now(timezone.utc).date(),
+            ).exists()
+            or executed_scan.exists()
+        ):
+            # Duplicated task execution due to visibility timeout or scan is already running
+            logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
+            try:
+                affected_scan = executed_scan.first()
+                if not affected_scan:
+                    raise ValueError(
+                        "Error retrieving affected scan details after detecting duplicated scheduled "
+                        "scan."
+                    )
+                # Return the affected scan details to avoid losing data
+                serializer = ScanTaskSerializer(instance=affected_scan)
+            except Exception as duplicated_scan_exception:
+                logger.error(
+                    f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
+                    f"{str(duplicated_scan_exception)}"
+                )
+                raise duplicated_scan_exception
+            return serializer.data
+
         next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
         scan_instance, _ = Scan.objects.get_or_create(
             tenant_id=tenant_id,
@@ -132,7 +184,11 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
             trigger=Scan.TriggerChoices.SCHEDULED,
             state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
             scheduler_task_id=periodic_task_instance.id,
-            defaults={"state": StateChoices.SCHEDULED},
+            defaults={
+                "state": StateChoices.SCHEDULED,
+                "name": "Daily scheduled scan",
+                "scheduled_at": next_scan_datetime - timedelta(days=1),
+            },
         )
 
         scan_instance.task_id = task_id
@@ -160,6 +216,9 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
 
     chain(
         perform_scan_summary_task.si(tenant_id, scan_instance.id),
+        create_compliance_requirements_task.si(
+            tenant_id=tenant_id, scan_id=str(scan_instance.id)
+        ),
         generate_outputs.si(
             scan_id=str(scan_instance.id), provider_id=provider_id, tenant_id=tenant_id
         ),
@@ -173,7 +232,7 @@ def perform_scan_summary_task(tenant_id: str, scan_id: str):
     return aggregate_findings(tenant_id=tenant_id, scan_id=scan_id)
 
 
-@shared_task(name="tenant-deletion", queue="deletion")
+@shared_task(name="tenant-deletion", queue="deletion", autoretry_for=(Exception,))
 def delete_tenant_task(tenant_id: str):
     return delete_tenant(pk=tenant_id)
 
@@ -200,80 +259,158 @@ def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
         scan_id (str): The scan identifier.
         provider_id (str): The provider_id id to be used in generating outputs.
     """
-    # Initialize the prowler provider
-    prowler_provider = initialize_prowler_provider(Provider.objects.get(id=provider_id))
+    # Check if the scan has findings
+    if not ScanSummary.objects.filter(scan_id=scan_id).exists():
+        logger.info(f"No findings found for scan {scan_id}")
+        return {"upload": False}
 
-    # Get the provider UID
-    provider_uid = Provider.objects.get(id=provider_id).uid
+    provider_obj = Provider.objects.get(id=provider_id)
+    prowler_provider = initialize_prowler_provider(provider_obj)
+    provider_uid = provider_obj.uid
+    provider_type = provider_obj.provider
 
-    # Generate and ensure the output directory exists
-    output_directory = _generate_output_directory(
+    frameworks_bulk = Compliance.get_bulk(provider_type)
+    frameworks_avail = get_compliance_frameworks(provider_type)
+    out_dir, comp_dir = _generate_output_directory(
         DJANGO_TMP_OUTPUT_DIRECTORY, provider_uid, tenant_id, scan_id
     )
 
-    # Define auxiliary variables
+    def get_writer(writer_map, name, factory, is_last):
+        """
+        Return existing writer_map[name] or create via factory().
+        In both cases set `.close_file = is_last`.
+        """
+        initialization = False
+        if name not in writer_map:
+            writer_map[name] = factory()
+            initialization = True
+        w = writer_map[name]
+        w.close_file = is_last
+
+        return w, initialization
+
     output_writers = {}
+    compliance_writers = {}
+
     scan_summary = FindingOutput._transform_findings_stats(
         ScanSummary.objects.filter(scan_id=scan_id)
     )
 
-    # Retrieve findings queryset
-    findings_qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid")
+    qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid").iterator()
+    for batch, is_last in batched(qs, DJANGO_FINDINGS_BATCH_SIZE):
+        fos = [FindingOutput.transform_api_finding(f, prowler_provider) for f in batch]
 
-    # Process findings in batches
-    for batch, is_last_batch in batched(
-        findings_qs.iterator(), DJANGO_FINDINGS_BATCH_SIZE
-    ):
-        finding_outputs = [
-            FindingOutput.transform_api_finding(finding, prowler_provider)
-            for finding in batch
-        ]
-
-        # Generate output files
-        for mode, config in OUTPUT_FORMATS_MAPPING.items():
-            kwargs = dict(config.get("kwargs", {}))
+        # Outputs
+        for mode, cfg in OUTPUT_FORMATS_MAPPING.items():
+            cls = cfg["class"]
+            suffix = cfg["suffix"]
+            extra = cfg.get("kwargs", {}).copy()
             if mode == "html":
-                kwargs["provider"] = prowler_provider
-                kwargs["stats"] = scan_summary
+                extra.update(provider=prowler_provider, stats=scan_summary)
 
-            writer_class = config["class"]
-            if writer_class in output_writers:
-                writer = output_writers[writer_class]
-                writer.transform(finding_outputs)
-                writer.close_file = is_last_batch
-            else:
-                writer = writer_class(
-                    findings=finding_outputs,
-                    file_path=output_directory,
-                    file_extension=config["suffix"],
+            writer, initialization = get_writer(
+                output_writers,
+                cls,
+                lambda cls=cls, fos=fos, suffix=suffix: cls(
+                    findings=fos,
+                    file_path=out_dir,
+                    file_extension=suffix,
                     from_cli=False,
-                )
-                writer.close_file = is_last_batch
-                output_writers[writer_class] = writer
+                ),
+                is_last,
+            )
+            if not initialization:
+                writer.transform(fos)
+            writer.batch_write_data_to_file(**extra)
+            writer._data.clear()
 
-            # Write the current batch using the writer
-            writer.batch_write_data_to_file(**kwargs)
+        # Compliance CSVs
+        for name in frameworks_avail:
+            compliance_obj = frameworks_bulk[name]
 
-            # TODO: Refactor the output classes to avoid this manual reset
-            writer._data = []
+            klass = GenericCompliance
+            for condition, cls in COMPLIANCE_CLASS_MAP.get(provider_type, []):
+                if condition(name):
+                    klass = cls
+                    break
 
-    # Compress output files
-    output_directory = _compress_output_files(output_directory)
+            filename = f"{comp_dir}_{name}.csv"
 
-    # Save to configured storage
-    uploaded = _upload_to_s3(tenant_id, output_directory, scan_id)
+            writer, initialization = get_writer(
+                compliance_writers,
+                name,
+                lambda klass=klass, fos=fos: klass(
+                    findings=fos,
+                    compliance=compliance_obj,
+                    file_path=filename,
+                    from_cli=False,
+                ),
+                is_last,
+            )
+            if not initialization:
+                writer.transform(fos, compliance_obj, name)
+            writer.batch_write_data_to_file()
+            writer._data.clear()
 
-    if uploaded:
-        output_directory = uploaded
-        uploaded = True
-        # Remove the local files after upload
-        rmtree(DJANGO_TMP_OUTPUT_DIRECTORY, ignore_errors=True)
+    compressed = _compress_output_files(out_dir)
+    upload_uri = _upload_to_s3(tenant_id, compressed, scan_id)
+
+    if upload_uri:
+        try:
+            rmtree(Path(compressed).parent, ignore_errors=True)
+        except Exception as e:
+            logger.error(f"Error deleting output files: {e}")
+        final_location, did_upload = upload_uri, True
     else:
-        uploaded = False
+        final_location, did_upload = compressed, False
 
-    # Update the scan instance with the output path
-    Scan.all_objects.filter(id=scan_id).update(output_location=output_directory)
+    Scan.all_objects.filter(id=scan_id).update(output_location=final_location)
+    logger.info(f"Scan outputs at {final_location}")
+    return {"upload": did_upload}
 
-    logger.info(f"Scan output files generated, output location: {output_directory}")
 
-    return {"upload": uploaded}
+@shared_task(name="backfill-scan-resource-summaries", queue="backfill")
+def backfill_scan_resource_summaries_task(tenant_id: str, scan_id: str):
+    """
+    Tries to backfill the resource scan summaries table for a given scan.
+
+    Args:
+        tenant_id (str): The tenant identifier.
+        scan_id (str): The scan identifier.
+    """
+    return backfill_resource_scan_summaries(tenant_id=tenant_id, scan_id=scan_id)
+
+
+@shared_task(base=RLSTask, name="scan-compliance-overviews")
+def create_compliance_requirements_task(tenant_id: str, scan_id: str):
+    """
+    Creates detailed compliance requirement records for a scan.
+
+    This task processes the compliance data collected during a scan and creates
+    individual records for each compliance requirement in each region. These detailed
+    records provide a granular view of compliance status.
+
+    Args:
+        tenant_id (str): The tenant ID for which to create records.
+        scan_id (str): The ID of the scan for which to create records.
+    """
+    return create_compliance_requirements(tenant_id=tenant_id, scan_id=scan_id)
+
+
+@shared_task(base=RLSTask, name="lighthouse-connection-check")
+@set_tenant
+def check_lighthouse_connection_task(lighthouse_config_id: str, tenant_id: str = None):
+    """
+    Task to check the connection status of a Lighthouse configuration.
+
+    Args:
+        lighthouse_config_id (str): The primary key of the LighthouseConfiguration instance to check.
+        tenant_id (str): The tenant ID for the task.
+
+    Returns:
+        dict: A dictionary containing:
+            - 'connected' (bool): Indicates whether the connection is successful.
+            - 'error' (str or None): The error message if the connection failed, otherwise `None`.
+            - 'available_models' (list): List of available models if connection is successful.
+    """
+    return check_lighthouse_connection(lighthouse_config_id=lighthouse_config_id)

api/src/backend/tasks/tests/test_backfill.py

@@ -0,0 +1,79 @@
+from uuid import uuid4
+
+import pytest
+from tasks.jobs.backfill import backfill_resource_scan_summaries
+
+from api.models import ResourceScanSummary, Scan, StateChoices
+
+
+@pytest.mark.django_db
+class TestBackfillResourceScanSummaries:
+    @pytest.fixture(scope="function")
+    def resource_scan_summary_data(self, scans_fixture):
+        scan = scans_fixture[0]
+        return ResourceScanSummary.objects.create(
+            tenant_id=scan.tenant_id,
+            scan_id=scan.id,
+            resource_id=str(uuid4()),
+            service="aws",
+            region="us-east-1",
+            resource_type="instance",
+        )
+
+    @pytest.fixture(scope="function")
+    def get_not_completed_scans(self, providers_fixture):
+        provider_id = providers_fixture[0].id
+        tenant_id = providers_fixture[0].tenant_id
+        scan_1 = Scan.objects.create(
+            tenant_id=tenant_id,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.EXECUTING,
+            provider_id=provider_id,
+        )
+        scan_2 = Scan.objects.create(
+            tenant_id=tenant_id,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.AVAILABLE,
+            provider_id=provider_id,
+        )
+        return scan_1, scan_2
+
+    def test_already_backfilled(self, resource_scan_summary_data):
+        tenant_id = resource_scan_summary_data.tenant_id
+        scan_id = resource_scan_summary_data.scan_id
+
+        result = backfill_resource_scan_summaries(tenant_id, scan_id)
+
+        assert result == {"status": "already backfilled"}
+
+    def test_not_completed_scan(self, get_not_completed_scans):
+        for scan_instance in get_not_completed_scans:
+            tenant_id = scan_instance.tenant_id
+            scan_id = scan_instance.id
+            result = backfill_resource_scan_summaries(tenant_id, scan_id)
+
+            assert result == {"status": "scan is not completed"}
+
+    def test_successful_backfill_inserts_one_summary(
+        self, resources_fixture, findings_fixture
+    ):
+        tenant_id = findings_fixture[0].tenant_id
+        scan_id = findings_fixture[0].scan_id
+
+        # This scan affects the first two resources
+        resources = resources_fixture[:2]
+
+        result = backfill_resource_scan_summaries(tenant_id, scan_id)
+        assert result == {"status": "backfilled", "inserted": len(resources)}
+
+        # Verify correct values
+        summaries = ResourceScanSummary.objects.filter(
+            tenant_id=tenant_id, scan_id=scan_id
+        )
+        assert summaries.count() == len(resources)
+        for resource in resources:
+            summary = summaries.get(resource_id=resource.id)
+            assert summary.resource_id == resource.id
+            assert summary.service == resource.service
+            assert summary.region == resource.region
+            assert summary.resource_type == resource.type

api/src/backend/tasks/tests/test_connection.py

@@ -1,10 +1,10 @@
 from datetime import datetime, timezone
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
+from tasks.jobs.connection import check_lighthouse_connection, check_provider_connection
 
-from api.models import Provider
-from tasks.jobs.connection import check_provider_connection
+from api.models import LighthouseConfiguration, Provider
 
 
 @pytest.mark.parametrize(
@@ -70,3 +70,60 @@ def test_check_provider_connection_exception(
 
     mock_provider_instance.save.assert_called_once()
     assert mock_provider_instance.connected is False
+
+
+@pytest.mark.parametrize(
+    "lighthouse_data",
+    [
+        {
+            "name": "OpenAI",
+            "api_key_decoded": "sk-test1234567890T3BlbkFJtest1234567890",
+            "model": "gpt-4o",
+            "temperature": 0,
+            "max_tokens": 4000,
+            "business_context": "Test business context",
+            "is_active": True,
+        },
+    ],
+)
+@patch("tasks.jobs.connection.openai.OpenAI")
+@pytest.mark.django_db
+def test_check_lighthouse_connection(
+    mock_openai_client, tenants_fixture, lighthouse_data
+):
+    lighthouse_config = LighthouseConfiguration.objects.create(
+        **lighthouse_data, tenant_id=tenants_fixture[0].id
+    )
+
+    mock_models = MagicMock()
+    mock_models.data = [MagicMock(id="gpt-4o"), MagicMock(id="gpt-4o-mini")]
+    mock_openai_client.return_value.models.list.return_value = mock_models
+
+    result = check_lighthouse_connection(
+        lighthouse_config_id=str(lighthouse_config.id),
+    )
+    lighthouse_config.refresh_from_db()
+
+    mock_openai_client.assert_called_once_with(
+        api_key=lighthouse_data["api_key_decoded"]
+    )
+    assert lighthouse_config.is_active is True
+    assert result["connected"] is True
+    assert result["error"] is None
+    assert result["available_models"] == ["gpt-4o", "gpt-4o-mini"]
+
+
+@patch("tasks.jobs.connection.LighthouseConfiguration.objects.get")
+@pytest.mark.django_db
+def test_check_lighthouse_connection_missing_api_key(mock_lighthouse_get):
+    mock_lighthouse_instance = MagicMock()
+    mock_lighthouse_instance.api_key_decoded = None
+    mock_lighthouse_get.return_value = mock_lighthouse_instance
+
+    result = check_lighthouse_connection("lighthouse_config_id")
+
+    assert result["connected"] is False
+    assert result["error"] == "API key is invalid or missing."
+    assert result["available_models"] == []
+    assert mock_lighthouse_instance.is_active is False
+    mock_lighthouse_instance.save.assert_called_once()

api/src/backend/tasks/tests/test_deletion.py

@@ -9,17 +9,19 @@ from api.models import Provider, Tenant
 class TestDeleteProvider:
     def test_delete_provider_success(self, providers_fixture):
         instance = providers_fixture[0]
-        result = delete_provider(instance.id)
+        tenant_id = str(instance.tenant_id)
+        result = delete_provider(tenant_id, instance.id)
 
         assert result
         with pytest.raises(ObjectDoesNotExist):
             Provider.objects.get(pk=instance.id)
 
-    def test_delete_provider_does_not_exist(self):
+    def test_delete_provider_does_not_exist(self, tenants_fixture):
+        tenant_id = str(tenants_fixture[0].id)
         non_existent_pk = "babf6796-cfcc-4fd3-9dcf-88d012247645"
 
         with pytest.raises(ObjectDoesNotExist):
-            delete_provider(non_existent_pk)
+            delete_provider(tenant_id, non_existent_pk)
 
 
 @pytest.mark.django_db

api/src/backend/tasks/tests/test_export.py

@@ -0,0 +1,166 @@
+import os
+import zipfile
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+from botocore.exceptions import ClientError
+from tasks.jobs.export import (
+    _compress_output_files,
+    _generate_output_directory,
+    _upload_to_s3,
+    get_s3_client,
+)
+
+
+@pytest.mark.django_db
+class TestOutputs:
+    def test_compress_output_files_creates_zip(self, tmpdir):
+        base_tmp = Path(str(tmpdir.mkdir("compress_output")))
+        output_dir = base_tmp / "output"
+        output_dir.mkdir()
+        file_path = output_dir / "result.csv"
+        file_path.write_text("data")
+
+        zip_path = _compress_output_files(str(output_dir))
+
+        assert zip_path.endswith(".zip")
+        assert os.path.exists(zip_path)
+        with zipfile.ZipFile(zip_path, "r") as zipf:
+            assert "output/result.csv" in zipf.namelist()
+
+    @patch("tasks.jobs.export.boto3.client")
+    @patch("tasks.jobs.export.settings")
+    def test_get_s3_client_success(self, mock_settings, mock_boto_client):
+        mock_settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = "test"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = "test"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = "token"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = "eu-west-1"
+
+        client_mock = MagicMock()
+        mock_boto_client.return_value = client_mock
+
+        client = get_s3_client()
+        assert client is not None
+        client_mock.list_buckets.assert_called()
+
+    @patch("tasks.jobs.export.boto3.client")
+    @patch("tasks.jobs.export.settings")
+    def test_get_s3_client_fallback(self, mock_settings, mock_boto_client):
+        mock_boto_client.side_effect = [
+            ClientError({"Error": {"Code": "403"}}, "ListBuckets"),
+            MagicMock(),
+        ]
+        client = get_s3_client()
+        assert client is not None
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_success(self, mock_base, mock_get_client, tmpdir):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
+
+        base_tmp = Path(str(tmpdir.mkdir("upload_success")))
+        zip_path = base_tmp / "outputs.zip"
+        zip_path.write_bytes(b"dummy")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "report.csv").write_text("ok")
+
+        client_mock = MagicMock()
+        mock_get_client.return_value = client_mock
+
+        result = _upload_to_s3("tenant-id", str(zip_path), "scan-id")
+
+        expected_uri = "s3://test-bucket/tenant-id/scan-id/outputs.zip"
+        assert result == expected_uri
+        assert client_mock.upload_file.call_count == 2
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_missing_bucket(self, mock_base, mock_get_client):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = ""
+        result = _upload_to_s3("tenant", "/tmp/fake.zip", "scan")
+        assert result is None
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_skips_non_files(self, mock_base, mock_get_client, tmpdir):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
+        base_tmp = Path(str(tmpdir.mkdir("upload_skips_non_files")))
+
+        zip_path = base_tmp / "results.zip"
+        zip_path.write_bytes(b"zip")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "subdir").mkdir()
+
+        client_mock = MagicMock()
+        mock_get_client.return_value = client_mock
+
+        result = _upload_to_s3("tenant", str(zip_path), "scan")
+
+        expected_uri = "s3://test-bucket/tenant/scan/results.zip"
+        assert result == expected_uri
+        client_mock.upload_file.assert_called_once()
+
+    @patch(
+        "tasks.jobs.export.get_s3_client",
+        side_effect=ClientError({"Error": {}}, "Upload"),
+    )
+    @patch("tasks.jobs.export.base")
+    @patch("tasks.jobs.export.logger.error")
+    def test_upload_to_s3_failure_logs_error(
+        self, mock_logger, mock_base, mock_get_client, tmpdir
+    ):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "bucket"
+
+        base_tmp = Path(str(tmpdir.mkdir("upload_failure_logs")))
+        zip_path = base_tmp / "zipfile.zip"
+        zip_path.write_bytes(b"zip")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "report.csv").write_text("csv")
+
+        _upload_to_s3("tenant", str(zip_path), "scan")
+        mock_logger.assert_called()
+
+    def test_generate_output_directory_creates_paths(self, tmpdir):
+        from prowler.config.config import output_file_timestamp
+
+        base_tmp = Path(str(tmpdir.mkdir("generate_output")))
+        base_dir = str(base_tmp)
+        tenant_id = "t1"
+        scan_id = "s1"
+        provider = "aws"
+
+        path, compliance = _generate_output_directory(
+            base_dir, provider, tenant_id, scan_id
+        )
+
+        assert os.path.isdir(os.path.dirname(path))
+        assert os.path.isdir(os.path.dirname(compliance))
+
+        assert path.endswith(f"{provider}-{output_file_timestamp}")
+        assert compliance.endswith(f"{provider}-{output_file_timestamp}")
+
+    def test_generate_output_directory_invalid_character(self, tmpdir):
+        from prowler.config.config import output_file_timestamp
+
+        base_tmp = Path(str(tmpdir.mkdir("generate_output")))
+        base_dir = str(base_tmp)
+        tenant_id = "t1"
+        scan_id = "s1"
+        provider = "aws/test@check"
+
+        path, compliance = _generate_output_directory(
+            base_dir, provider, tenant_id, scan_id
+        )
+
+        assert os.path.isdir(os.path.dirname(path))
+        assert os.path.isdir(os.path.dirname(compliance))
+
+        assert path.endswith(f"aws-test-check-{output_file_timestamp}")
+        assert compliance.endswith(f"aws-test-check-{output_file_timestamp}")

api/src/backend/tasks/tests/test_scan.py

@@ -1,14 +1,19 @@
+import json
 import uuid
+from datetime import datetime
 from unittest.mock import MagicMock, patch
 
 import pytest
 from tasks.jobs.scan import (
     _create_finding_delta,
     _store_resources,
+    create_compliance_requirements,
     perform_prowler_scan,
 )
+from tasks.utils import CustomEncoder
 
 from api.models import (
+    ComplianceRequirementOverview,
     Finding,
     Provider,
     Resource,
@@ -107,7 +112,13 @@ class TestPerformScan:
             finding.service_name = "service_name"
             finding.resource_type = "resource_type"
             finding.resource_tags = {"tag1": "value1", "tag2": "value2"}
+            finding.muted = False
             finding.raw = {}
+            finding.resource_metadata = {"test": "metadata"}
+            finding.resource_details = {"details": "test"}
+            finding.partition = "partition"
+            finding.muted = True
+            finding.compliance = {"compliance1": "PASS"}
 
             # Mock the ProwlerScan instance
             mock_prowler_scan_instance = MagicMock()
@@ -145,6 +156,8 @@ class TestPerformScan:
         assert scan_finding.severity == finding.severity
         assert scan_finding.check_id == finding.check_id
         assert scan_finding.raw_result == finding.raw
+        assert scan_finding.muted
+        assert scan_finding.compliance == finding.compliance
 
         assert scan_resource.tenant == tenant
         assert scan_resource.uid == finding.resource_uid
@@ -152,6 +165,11 @@ class TestPerformScan:
         assert scan_resource.service == finding.service_name
         assert scan_resource.type == finding.resource_type
         assert scan_resource.name == finding.resource_name
+        assert scan_resource.metadata == json.dumps(
+            finding.resource_metadata, cls=CustomEncoder
+        )
+        assert scan_resource.details == f"{finding.resource_details}"
+        assert scan_resource.partition == finding.partition
 
         # Assert that the resource tags have been created and associated
         tags = scan_resource.tags.all()
@@ -191,6 +209,10 @@ class TestPerformScan:
         scan.refresh_from_db()
         assert scan.state == StateChoices.FAILED
 
+        provider.refresh_from_db()
+        assert provider.connected is False
+        assert isinstance(provider.connection_last_checked_at, datetime)
+
     @pytest.mark.parametrize(
         "last_status, new_status, expected_delta",
         [
@@ -215,7 +237,7 @@ class TestPerformScan:
     ):
         tenant_id = uuid.uuid4()
         provider_instance = MagicMock()
-        provider_instance.id = "provider456"
+        provider_instance.id = "provider123"
 
         finding = MagicMock()
         finding.resource_uid = "resource_uid_123"
@@ -230,15 +252,16 @@ class TestPerformScan:
         resource_instance.region = finding.region
 
         mock_get_or_create_resource.return_value = (resource_instance, True)
+
         tag_instance = MagicMock()
         mock_get_or_create_tag.return_value = (tag_instance, True)
 
         resource, resource_uid_tuple = _store_resources(
-            finding, tenant_id, provider_instance
+            finding, str(tenant_id), provider_instance
         )
 
         mock_get_or_create_resource.assert_called_once_with(
-            tenant_id=tenant_id,
+            tenant_id=str(tenant_id),
             provider=provider_instance,
             uid=finding.resource_uid,
             defaults={
@@ -285,11 +308,11 @@ class TestPerformScan:
         mock_get_or_create_tag.return_value = (tag_instance, True)
 
         resource, resource_uid_tuple = _store_resources(
-            finding, tenant_id, provider_instance
+            finding, str(tenant_id), provider_instance
         )
 
         mock_get_or_create_resource.assert_called_once_with(
-            tenant_id=tenant_id,
+            tenant_id=str(tenant_id),
             provider=provider_instance,
             uid=finding.resource_uid,
             defaults={
@@ -343,14 +366,14 @@ class TestPerformScan:
         ]
 
         resource, resource_uid_tuple = _store_resources(
-            finding, tenant_id, provider_instance
+            finding, str(tenant_id), provider_instance
         )
 
         mock_get_or_create_tag.assert_any_call(
-            tenant_id=tenant_id, key="tag1", value="value1"
+            tenant_id=str(tenant_id), key="tag1", value="value1"
         )
         mock_get_or_create_tag.assert_any_call(
-            tenant_id=tenant_id, key="tag2", value="value2"
+            tenant_id=str(tenant_id), key="tag2", value="value2"
         )
         resource_instance.upsert_or_delete_tags.assert_called_once()
         tags_passed = resource_instance.upsert_or_delete_tags.call_args[1]["tags"]
@@ -362,3 +385,808 @@ class TestPerformScan:
 
 
 # TODO Add tests for aggregations
+
+
+@pytest.mark.django_db
+class TestCreateComplianceRequirements:
+    def test_create_compliance_requirements_success(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+        findings_fixture,
+        resources_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch("tasks.jobs.scan.generate_scan_compliance"),
+            patch("tasks.jobs.scan.create_objects_in_batches") as mock_create_objects,
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.return_value = [
+                "us-east-1",
+                "us-west-2",
+            ]
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {
+                "cis_1.4_aws": {
+                    "framework": "CIS AWS Foundations Benchmark",
+                    "version": "1.4.0",
+                    "requirements": {
+                        "1.1": {
+                            "description": "Ensure root access key does not exist",
+                            "checks_status": {
+                                "pass": 0,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "PASS",
+                        },
+                        "1.2": {
+                            "description": "Ensure MFA is enabled for root account",
+                            "checks_status": {
+                                "pass": 0,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "FAIL",
+                        },
+                    },
+                },
+                "aws_account_security_onboarding_aws": {
+                    "framework": "AWS Account Security Onboarding",
+                    "version": "1.0",
+                    "requirements": {
+                        "requirement1": {
+                            "description": "Basic security requirement",
+                            "checks_status": {
+                                "pass": 1,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "PASS",
+                        },
+                    },
+                },
+            }
+
+            mock_findings_filter.return_value = []
+
+            result = create_compliance_requirements(tenant_id, scan_id)
+
+            assert "requirements_created" in result
+            assert "regions_processed" in result
+            assert "compliance_frameworks" in result
+            assert result["regions_processed"] == ["us-east-1", "us-west-2"]
+            assert result["requirements_created"] == 6
+            assert len(result["compliance_frameworks"]) == 2
+
+            mock_create_objects.assert_called_once()
+            call_args = mock_create_objects.call_args[0]
+            assert call_args[0] == tenant_id
+            assert call_args[1] == ComplianceRequirementOverview
+            assert len(call_args[2]) == 6
+
+            compliance_objects = call_args[2]
+            for obj in compliance_objects:
+                assert isinstance(obj, ComplianceRequirementOverview)
+                assert obj.tenant.id == tenant.id
+                assert obj.scan == scan
+                assert obj.region in ["us-east-1", "us-west-2"]
+                assert obj.compliance_id in [
+                    "cis_1.4_aws",
+                    "aws_account_security_onboarding_aws",
+                ]
+
+    def test_create_compliance_requirements_with_findings(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches"),
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_finding1 = MagicMock()
+            mock_finding1.check_id = "check1"
+            mock_finding1.status = "PASS"
+            mock_resource1 = MagicMock()
+            mock_resource1.region = "us-east-1"
+            mock_finding1.resources.all.return_value = [mock_resource1]
+
+            mock_finding2 = MagicMock()
+            mock_finding2.check_id = "check2"
+            mock_finding2.status = "FAIL"
+            mock_resource2 = MagicMock()
+            mock_resource2.region = "us-west-2"
+            mock_finding2.resources.all.return_value = [mock_resource2]
+
+            mock_findings_filter.return_value = [mock_finding1, mock_finding2]
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.return_value = [
+                "us-east-1",
+                "us-west-2",
+            ]
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {"check_1": None},
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 3,
+                            },
+                            "status": "FAIL",
+                        },
+                        "req_2": {
+                            "description": "Test Requirement 2",
+                            "checks": {"check_2": None},
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "PASS",
+                        },
+                    },
+                }
+            }
+
+            result = create_compliance_requirements(tenant_id, scan_id)
+
+            mock_findings_filter.assert_called_once_with(scan_id=scan_id, muted=False)
+            assert mock_generate_compliance.call_count == 2
+            assert result["requirements_created"] == 4
+            assert set(result["regions_processed"]) == {"us-east-1", "us-west-2"}
+
+    def test_create_compliance_requirements_no_provider_regions(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch("tasks.jobs.scan.generate_scan_compliance"),
+            patch("tasks.jobs.scan.create_objects_in_batches"),
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.KUBERNETES
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_finding = MagicMock()
+            mock_finding.check_id = "check1"
+            mock_finding.status = "PASS"
+            mock_resource = MagicMock()
+            mock_resource.region = "default"
+            mock_finding.resources.all.return_value = [mock_resource]
+            mock_findings_filter.return_value = [mock_finding]
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.side_effect = AttributeError(
+                "No get_regions method"
+            )
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {
+                "kubernetes_cis": {
+                    "framework": "CIS Kubernetes Benchmark",
+                    "version": "1.6.0",
+                    "requirements": {
+                        "1.1": {
+                            "description": "Test requirement",
+                            "checks_status": {
+                                "pass": 0,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "PASS",
+                        },
+                    },
+                },
+            }
+
+            result = create_compliance_requirements(tenant_id, scan_id)
+
+            assert result["regions_processed"] == ["default"]
+
+    def test_create_compliance_requirements_empty_findings(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches"),
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_findings_filter.return_value = []
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {
+                "cis_1.4_aws": {
+                    "framework": "CIS AWS Foundations Benchmark",
+                    "version": "1.4.0",
+                    "requirements": {
+                        "1.1": {
+                            "description": "Test requirement",
+                            "checks_status": {
+                                "pass": 0,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "PASS",
+                        },
+                    },
+                },
+            }
+
+            mock_findings_filter.return_value = []
+
+            result = create_compliance_requirements(tenant_id, scan_id)
+
+            assert result["regions_processed"] == ["us-east-1"]
+            assert result["requirements_created"] == 1
+            mock_generate_compliance.assert_not_called()
+
+    def test_create_compliance_requirements_error_handling(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_initialize_prowler_provider.side_effect = Exception(
+                "Provider initialization failed"
+            )
+
+            with pytest.raises(Exception, match="Provider initialization failed"):
+                create_compliance_requirements(tenant_id, scan_id)
+
+    def test_create_compliance_requirements_muted_findings_excluded(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch("tasks.jobs.scan.generate_scan_compliance"),
+            patch("tasks.jobs.scan.create_objects_in_batches"),
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_findings_filter.return_value = []
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {}
+
+            mock_findings_filter.return_value = []
+
+            create_compliance_requirements(tenant_id, scan_id)
+
+            mock_findings_filter.assert_called_once_with(scan_id=scan_id, muted=False)
+
+    def test_create_compliance_requirements_check_status_priority(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches"),
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            provider = providers_fixture[0]
+
+            provider.provider = Provider.ProviderChoices.AWS
+            provider.save()
+            scan.provider = provider
+            scan.save()
+
+            tenant_id = str(tenant.id)
+            scan_id = str(scan.id)
+
+            mock_finding1 = MagicMock()
+            mock_finding1.check_id = "check1"
+            mock_finding1.status = "PASS"
+            mock_resource1 = MagicMock()
+            mock_resource1.region = "us-east-1"
+            mock_finding1.resources.all.return_value = [mock_resource1]
+
+            mock_finding2 = MagicMock()
+            mock_finding2.check_id = "check1"
+            mock_finding2.status = "FAIL"
+            mock_resource2 = MagicMock()
+            mock_resource2.region = "us-east-1"
+            mock_finding2.resources.all.return_value = [mock_resource2]
+
+            mock_findings_filter.return_value = [mock_finding1, mock_finding2]
+
+            mock_prowler_provider_instance = MagicMock()
+            mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
+            mock_initialize_prowler_provider.return_value = (
+                mock_prowler_provider_instance
+            )
+
+            mock_compliance_template.__getitem__.return_value = {
+                "cis_1.4_aws": {
+                    "framework": "CIS AWS Foundations Benchmark",
+                    "version": "1.4.0",
+                    "requirements": {
+                        "1.1": {
+                            "description": "Test requirement",
+                            "checks_status": {
+                                "pass": 0,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 1,
+                            },
+                            "status": "PASS",
+                        },
+                    },
+                },
+            }
+
+            create_compliance_requirements(tenant_id, scan_id)
+
+            assert mock_generate_compliance.call_count == 1
+
+    def test_compliance_overview_aggregation_requirement_fail_priority(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches") as mock_create_objects,
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            providers_fixture[0]
+
+            mock_findings_filter.return_value = []
+
+            mock_prowler_provider = MagicMock()
+            mock_prowler_provider.get_regions.return_value = [
+                "us-east-1",
+                "us-west-2",
+                "eu-west-1",
+            ]
+            mock_initialize_prowler_provider.return_value = mock_prowler_provider
+
+            mock_compliance_template.__getitem__.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {"check_1": None},
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 3,
+                            },
+                            "status": "FAIL",
+                        }
+                    },
+                }
+            }
+
+            mock_generate_compliance.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {
+                                "check_1": {
+                                    "us-east-1": {"status": "PASS"},
+                                    "us-west-2": {"status": "FAIL"},
+                                    "eu-west-1": {"status": "PASS"},
+                                }
+                            },
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 3,
+                            },
+                            "status": "FAIL",
+                        }
+                    },
+                }
+            }
+
+            created_objects = []
+            mock_create_objects.side_effect = (
+                lambda tenant_id, model, objs, batch_size=500: created_objects.extend(
+                    objs
+                )
+            )
+
+            create_compliance_requirements(str(tenant.id), str(scan.id))
+
+            assert len(created_objects) == 3
+            assert all(obj.requirement_status == "FAIL" for obj in created_objects)
+
+    def test_compliance_overview_aggregation_requirement_pass_all_regions(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches") as mock_create_objects,
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            providers_fixture[0]
+
+            mock_findings_filter.return_value = []
+
+            mock_prowler_provider = MagicMock()
+            mock_prowler_provider.get_regions.return_value = ["us-east-1", "us-west-2"]
+            mock_initialize_prowler_provider.return_value = mock_prowler_provider
+
+            mock_compliance_template.__getitem__.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {"check_1": None},
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "PASS",
+                        }
+                    },
+                }
+            }
+
+            mock_generate_compliance.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {
+                                "check_1": {
+                                    "us-east-1": {"status": "PASS"},
+                                    "us-west-2": {"status": "PASS"},
+                                }
+                            },
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "PASS",
+                        }
+                    },
+                }
+            }
+
+            created_objects = []
+            mock_create_objects.side_effect = (
+                lambda tenant_id, model, objs, batch_size=500: created_objects.extend(
+                    objs
+                )
+            )
+
+            create_compliance_requirements(str(tenant.id), str(scan.id))
+
+            assert len(created_objects) == 2
+            assert all(obj.requirement_status == "PASS" for obj in created_objects)
+
+    def test_compliance_overview_aggregation_multiple_requirements_mixed_status(
+        self,
+        tenants_fixture,
+        scans_fixture,
+        providers_fixture,
+    ):
+        with (
+            patch("api.db_utils.rls_transaction"),
+            patch(
+                "tasks.jobs.scan.initialize_prowler_provider"
+            ) as mock_initialize_prowler_provider,
+            patch(
+                "tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
+            ) as mock_compliance_template,
+            patch(
+                "tasks.jobs.scan.generate_scan_compliance"
+            ) as mock_generate_compliance,
+            patch("tasks.jobs.scan.create_objects_in_batches") as mock_create_objects,
+            patch("api.models.Finding.objects.filter") as mock_findings_filter,
+        ):
+            tenant = tenants_fixture[0]
+            scan = scans_fixture[0]
+            providers_fixture[0]
+
+            mock_findings_filter.return_value = []
+
+            mock_prowler_provider = MagicMock()
+            mock_prowler_provider.get_regions.return_value = ["us-east-1", "us-west-2"]
+            mock_initialize_prowler_provider.return_value = mock_prowler_provider
+
+            mock_compliance_template.__getitem__.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {"check_1": None},
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "PASS",
+                        },
+                        "req_2": {
+                            "description": "Test Requirement 2",
+                            "checks": {"check_2": None},
+                            "checks_status": {
+                                "pass": 1,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "FAIL",
+                        },
+                    },
+                }
+            }
+
+            mock_generate_compliance.return_value = {
+                "test_compliance": {
+                    "framework": "Test Framework",
+                    "version": "1.0",
+                    "requirements": {
+                        "req_1": {
+                            "description": "Test Requirement 1",
+                            "checks": {
+                                "check_1": {
+                                    "us-east-1": {"status": "PASS"},
+                                    "us-west-2": {"status": "PASS"},
+                                }
+                            },
+                            "checks_status": {
+                                "pass": 2,
+                                "fail": 0,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "PASS",
+                        },
+                        "req_2": {
+                            "description": "Test Requirement 2",
+                            "checks": {
+                                "check_2": {
+                                    "us-east-1": {"status": "PASS"},
+                                    "us-west-2": {"status": "FAIL"},
+                                }
+                            },
+                            "checks_status": {
+                                "pass": 1,
+                                "fail": 1,
+                                "manual": 0,
+                                "total": 2,
+                            },
+                            "status": "FAIL",
+                        },
+                    },
+                }
+            }
+
+            created_objects = []
+            mock_create_objects.side_effect = (
+                lambda tenant_id, model, objs, batch_size=500: created_objects.extend(
+                    objs
+                )
+            )
+
+            create_compliance_requirements(str(tenant.id), str(scan.id))
+
+            assert len(created_objects) == 4
+            req_1_objects = [
+                obj for obj in created_objects if obj.requirement_id == "req_1"
+            ]
+            req_2_objects = [
+                obj for obj in created_objects if obj.requirement_id == "req_2"
+            ]
+            assert len(req_1_objects) == 2
+            assert len(req_2_objects) == 2
+            assert all(obj.requirement_status == "PASS" for obj in req_1_objects)
+            assert all(obj.requirement_status == "FAIL" for obj in req_2_objects)

api/src/backend/tasks/tests/test_tasks.py

@@ -0,0 +1,415 @@
+import uuid
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+from tasks.tasks import generate_outputs
+
+
+@pytest.mark.django_db
+class TestGenerateOutputs:
+    def setup_method(self):
+        self.scan_id = str(uuid.uuid4())
+        self.provider_id = str(uuid.uuid4())
+        self.tenant_id = str(uuid.uuid4())
+
+    def test_no_findings_returns_early(self):
+        with patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter:
+            mock_filter.return_value.exists.return_value = False
+
+            result = generate_outputs(
+                scan_id=self.scan_id,
+                provider_id=self.provider_id,
+                tenant_id=self.tenant_id,
+            )
+
+            assert result == {"upload": False}
+            mock_filter.assert_called_once_with(scan_id=self.scan_id)
+
+    @patch("tasks.tasks.rmtree")
+    @patch("tasks.tasks._upload_to_s3")
+    @patch("tasks.tasks._compress_output_files")
+    @patch("tasks.tasks.get_compliance_frameworks")
+    @patch("tasks.tasks.Compliance.get_bulk")
+    @patch("tasks.tasks.initialize_prowler_provider")
+    @patch("tasks.tasks.Provider.objects.get")
+    @patch("tasks.tasks.ScanSummary.objects.filter")
+    @patch("tasks.tasks.Finding.all_objects.filter")
+    def test_generate_outputs_happy_path(
+        self,
+        mock_finding_filter,
+        mock_scan_summary_filter,
+        mock_provider_get,
+        mock_initialize_provider,
+        mock_compliance_get_bulk,
+        mock_get_available_frameworks,
+        mock_compress,
+        mock_upload,
+        mock_rmtree,
+    ):
+        mock_scan_summary_filter.return_value.exists.return_value = True
+
+        mock_provider = MagicMock()
+        mock_provider.uid = "provider-uid"
+        mock_provider.provider = "aws"
+        mock_provider_get.return_value = mock_provider
+
+        prowler_provider = MagicMock()
+        mock_initialize_provider.return_value = prowler_provider
+
+        mock_compliance_get_bulk.return_value = {"cis": MagicMock()}
+        mock_get_available_frameworks.return_value = ["cis"]
+
+        dummy_finding = MagicMock(uid="f1")
+        mock_finding_filter.return_value.order_by.return_value.iterator.return_value = [
+            [dummy_finding],
+            True,
+        ]
+
+        mock_transformed_stats = {"some": "stats"}
+        with (
+            patch(
+                "tasks.tasks.FindingOutput._transform_findings_stats",
+                return_value=mock_transformed_stats,
+            ),
+            patch(
+                "tasks.tasks.FindingOutput.transform_api_finding",
+                return_value={"transformed": "f1"},
+            ),
+            patch(
+                "tasks.tasks.OUTPUT_FORMATS_MAPPING",
+                {
+                    "json": {
+                        "class": MagicMock(name="JSONWriter"),
+                        "suffix": ".json",
+                        "kwargs": {},
+                    }
+                },
+            ),
+            patch(
+                "tasks.tasks.COMPLIANCE_CLASS_MAP",
+                {"aws": [(lambda x: True, MagicMock(name="CSVCompliance"))]},
+            ),
+            patch(
+                "tasks.tasks._generate_output_directory",
+                return_value=("out-dir", "comp-dir"),
+            ),
+            patch("tasks.tasks.Scan.all_objects.filter") as mock_scan_update,
+        ):
+            mock_compress.return_value = "/tmp/zipped.zip"
+            mock_upload.return_value = "s3://bucket/zipped.zip"
+
+            result = generate_outputs(
+                scan_id=self.scan_id,
+                provider_id=self.provider_id,
+                tenant_id=self.tenant_id,
+            )
+
+            assert result == {"upload": True}
+            mock_scan_update.return_value.update.assert_called_once_with(
+                output_location="s3://bucket/zipped.zip"
+            )
+            mock_rmtree.assert_called_once_with(
+                Path("/tmp/zipped.zip").parent, ignore_errors=True
+            )
+
+    def test_generate_outputs_fails_upload(self):
+        with (
+            patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
+            patch("tasks.tasks.Provider.objects.get"),
+            patch("tasks.tasks.initialize_prowler_provider"),
+            patch("tasks.tasks.Compliance.get_bulk"),
+            patch("tasks.tasks.get_compliance_frameworks"),
+            patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
+            patch(
+                "tasks.tasks._generate_output_directory", return_value=("out", "comp")
+            ),
+            patch("tasks.tasks.FindingOutput._transform_findings_stats"),
+            patch("tasks.tasks.FindingOutput.transform_api_finding"),
+            patch(
+                "tasks.tasks.OUTPUT_FORMATS_MAPPING",
+                {
+                    "json": {
+                        "class": MagicMock(name="Writer"),
+                        "suffix": ".json",
+                        "kwargs": {},
+                    }
+                },
+            ),
+            patch(
+                "tasks.tasks.COMPLIANCE_CLASS_MAP",
+                {"aws": [(lambda x: True, MagicMock())]},
+            ),
+            patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
+            patch("tasks.tasks._upload_to_s3", return_value=None),
+            patch("tasks.tasks.Scan.all_objects.filter") as mock_scan_update,
+        ):
+            mock_filter.return_value.exists.return_value = True
+            mock_findings.return_value.order_by.return_value.iterator.return_value = [
+                [MagicMock()],
+                True,
+            ]
+
+            result = generate_outputs(
+                scan_id="scan",
+                provider_id="provider",
+                tenant_id=self.tenant_id,
+            )
+
+            assert result == {"upload": False}
+            mock_scan_update.return_value.update.assert_called_once()
+
+    def test_generate_outputs_triggers_html_extra_update(self):
+        mock_finding_output = MagicMock()
+        mock_finding_output.compliance = {"cis": ["requirement-1", "requirement-2"]}
+
+        with (
+            patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
+            patch("tasks.tasks.Provider.objects.get"),
+            patch("tasks.tasks.initialize_prowler_provider"),
+            patch("tasks.tasks.Compliance.get_bulk", return_value={"cis": MagicMock()}),
+            patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
+            patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
+            patch(
+                "tasks.tasks._generate_output_directory", return_value=("out", "comp")
+            ),
+            patch(
+                "tasks.tasks.FindingOutput._transform_findings_stats",
+                return_value={"some": "stats"},
+            ),
+            patch(
+                "tasks.tasks.FindingOutput.transform_api_finding",
+                return_value=mock_finding_output,
+            ),
+            patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
+            patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/f.zip"),
+            patch("tasks.tasks.Scan.all_objects.filter"),
+        ):
+            mock_filter.return_value.exists.return_value = True
+            mock_findings.return_value.order_by.return_value.iterator.return_value = [
+                [MagicMock()],
+                True,
+            ]
+
+            html_writer_mock = MagicMock()
+            with (
+                patch(
+                    "tasks.tasks.OUTPUT_FORMATS_MAPPING",
+                    {
+                        "html": {
+                            "class": lambda *args, **kwargs: html_writer_mock,
+                            "suffix": ".html",
+                            "kwargs": {},
+                        }
+                    },
+                ),
+                patch(
+                    "tasks.tasks.COMPLIANCE_CLASS_MAP",
+                    {"aws": [(lambda x: True, MagicMock())]},
+                ),
+            ):
+                generate_outputs(
+                    scan_id=self.scan_id,
+                    provider_id=self.provider_id,
+                    tenant_id=self.tenant_id,
+                )
+                html_writer_mock.batch_write_data_to_file.assert_called_once()
+
+    def test_transform_called_only_on_second_batch(self):
+        raw1 = MagicMock()
+        raw2 = MagicMock()
+
+        tf1 = MagicMock()
+        tf1.compliance = {}
+        tf2 = MagicMock()
+        tf2.compliance = {}
+
+        writer_instances = []
+
+        class TrackingWriter:
+            def __init__(self, findings, file_path, file_extension, from_cli):
+                self.transform_called = 0
+                self.batch_write_data_to_file = MagicMock()
+                self._data = []
+                self.close_file = False
+                writer_instances.append(self)
+
+            def transform(self, fos):
+                self.transform_called += 1
+
+        with (
+            patch("tasks.tasks.ScanSummary.objects.filter") as mock_summary,
+            patch("tasks.tasks.Provider.objects.get"),
+            patch("tasks.tasks.initialize_prowler_provider"),
+            patch("tasks.tasks.Compliance.get_bulk"),
+            patch("tasks.tasks.get_compliance_frameworks", return_value=[]),
+            patch("tasks.tasks.FindingOutput._transform_findings_stats"),
+            patch(
+                "tasks.tasks.FindingOutput.transform_api_finding",
+                side_effect=[tf1, tf2],
+            ),
+            patch(
+                "tasks.tasks._generate_output_directory",
+                return_value=("outdir", "compdir"),
+            ),
+            patch("tasks.tasks._compress_output_files", return_value="outdir.zip"),
+            patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/outdir.zip"),
+            patch("tasks.tasks.rmtree"),
+            patch("tasks.tasks.Scan.all_objects.filter"),
+            patch(
+                "tasks.tasks.batched",
+                return_value=[
+                    ([raw1], False),
+                    ([raw2], True),
+                ],
+            ),
+        ):
+            mock_summary.return_value.exists.return_value = True
+
+            with patch(
+                "tasks.tasks.OUTPUT_FORMATS_MAPPING",
+                {
+                    "json": {
+                        "class": TrackingWriter,
+                        "suffix": ".json",
+                        "kwargs": {},
+                    }
+                },
+            ):
+                result = generate_outputs(
+                    scan_id=self.scan_id,
+                    provider_id=self.provider_id,
+                    tenant_id=self.tenant_id,
+                )
+
+        assert result == {"upload": True}
+        assert len(writer_instances) == 1
+        writer = writer_instances[0]
+        assert writer.transform_called == 1
+
+    def test_compliance_transform_called_on_second_batch(self):
+        raw1 = MagicMock()
+        raw2 = MagicMock()
+        compliance_obj = MagicMock()
+        writer_instances = []
+
+        class TrackingComplianceWriter:
+            def __init__(self, *args, **kwargs):
+                self.transform_calls = []
+                self._data = []
+                writer_instances.append(self)
+
+            def transform(self, fos, comp_obj, name):
+                self.transform_calls.append((fos, comp_obj, name))
+
+            def batch_write_data_to_file(self):
+                pass
+
+        two_batches = [
+            ([raw1], False),
+            ([raw2], True),
+        ]
+
+        with (
+            patch("tasks.tasks.ScanSummary.objects.filter") as mock_summary,
+            patch(
+                "tasks.tasks.Provider.objects.get",
+                return_value=MagicMock(uid="UID", provider="aws"),
+            ),
+            patch("tasks.tasks.initialize_prowler_provider"),
+            patch(
+                "tasks.tasks.Compliance.get_bulk", return_value={"cis": compliance_obj}
+            ),
+            patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
+            patch(
+                "tasks.tasks._generate_output_directory",
+                return_value=("outdir", "compdir"),
+            ),
+            patch("tasks.tasks.FindingOutput._transform_findings_stats"),
+            patch(
+                "tasks.tasks.FindingOutput.transform_api_finding",
+                side_effect=lambda f, prov: f,
+            ),
+            patch("tasks.tasks._compress_output_files", return_value="outdir.zip"),
+            patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/outdir.zip"),
+            patch("tasks.tasks.rmtree"),
+            patch(
+                "tasks.tasks.Scan.all_objects.filter",
+                return_value=MagicMock(update=lambda **kw: None),
+            ),
+            patch("tasks.tasks.batched", return_value=two_batches),
+            patch("tasks.tasks.OUTPUT_FORMATS_MAPPING", {}),
+            patch(
+                "tasks.tasks.COMPLIANCE_CLASS_MAP",
+                {"aws": [(lambda name: True, TrackingComplianceWriter)]},
+            ),
+        ):
+            mock_summary.return_value.exists.return_value = True
+
+            result = generate_outputs(
+                scan_id=self.scan_id,
+                provider_id=self.provider_id,
+                tenant_id=self.tenant_id,
+            )
+
+        assert len(writer_instances) == 1
+        writer = writer_instances[0]
+        assert writer.transform_calls == [([raw2], compliance_obj, "cis")]
+        assert result == {"upload": True}
+
+    def test_generate_outputs_logs_rmtree_exception(self, caplog):
+        mock_finding_output = MagicMock()
+        mock_finding_output.compliance = {"cis": ["requirement-1", "requirement-2"]}
+
+        with (
+            patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
+            patch("tasks.tasks.Provider.objects.get"),
+            patch("tasks.tasks.initialize_prowler_provider"),
+            patch("tasks.tasks.Compliance.get_bulk", return_value={"cis": MagicMock()}),
+            patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
+            patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
+            patch(
+                "tasks.tasks._generate_output_directory", return_value=("out", "comp")
+            ),
+            patch(
+                "tasks.tasks.FindingOutput._transform_findings_stats",
+                return_value={"some": "stats"},
+            ),
+            patch(
+                "tasks.tasks.FindingOutput.transform_api_finding",
+                return_value=mock_finding_output,
+            ),
+            patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
+            patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/file.zip"),
+            patch("tasks.tasks.Scan.all_objects.filter"),
+            patch("tasks.tasks.rmtree", side_effect=Exception("Test deletion error")),
+        ):
+            mock_filter.return_value.exists.return_value = True
+            mock_findings.return_value.order_by.return_value.iterator.return_value = [
+                [MagicMock()],
+                True,
+            ]
+
+            with (
+                patch(
+                    "tasks.tasks.OUTPUT_FORMATS_MAPPING",
+                    {
+                        "json": {
+                            "class": lambda *args, **kwargs: MagicMock(),
+                            "suffix": ".json",
+                            "kwargs": {},
+                        }
+                    },
+                ),
+                patch(
+                    "tasks.tasks.COMPLIANCE_CLASS_MAP",
+                    {"aws": [(lambda x: True, MagicMock())]},
+                ),
+            ):
+                with caplog.at_level("ERROR"):
+                    generate_outputs(
+                        scan_id=self.scan_id,
+                        provider_id=self.provider_id,
+                        tenant_id=self.tenant_id,
+                    )
+                    assert "Error deleting output files" in caplog.text