Merge branch 'master' into PRWLR-6064-change-user-deletion-api-response

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

.env

@@ -6,11 +6,15 @@
 PROWLER_UI_VERSION="stable"
 AUTH_URL=http://localhost:3000
 API_BASE_URL=http://prowler-api:8080/api/v1
+NEXT_PUBLIC_API_BASE_URL=${API_BASE_URL}
 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 +28,10 @@ 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
@@ -123,7 +131,7 @@ SENTRY_ENVIRONMENT=local
 SENTRY_RELEASE=local
 
 #### Prowler release version ####
-NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.5.0
+NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.7.5
 
 # Social login credentials
 SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
@@ -133,3 +141,12 @@ SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET=""
 SOCIAL_GITHUB_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/github"
 SOCIAL_GITHUB_OAUTH_CLIENT_ID=""
 SOCIAL_GITHUB_OAUTH_CLIENT_SECRET=""
+
+# Single Sign-On (SSO)
+SAML_SSO_CALLBACK_URL="${AUTH_URL}/api/auth/callback/saml"
+
+# Lighthouse tracing
+LANGSMITH_TRACING=false
+LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
+LANGSMITH_API_KEY=""
+LANGCHAIN_PROJECT=""

.github/dependabot.yml

@@ -9,8 +9,8 @@ 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"
@@ -31,8 +31,8 @@ updates:
   - 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"
@@ -53,46 +53,47 @@ updates:
   - 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
@@ -107,13 +108,13 @@ updates:
   #     - "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

@@ -76,12 +76,12 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        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@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           push: true

.github/workflows/api-codeql.yml

@@ -48,12 +48,12 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+      uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/api-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+      uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
       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:
@@ -75,15 +79,18 @@ jobs:
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@823fcebdb31bb35fdf2229d9f769b400309430d0 # v46.0.3
+        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@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        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'
@@ -144,8 +163,9 @@ jobs:
       - name: Safety
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        # 76352, 76353, 77323 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 70612,66963,74429,76352,76353,77323
 
       - name: Vulture
         working-directory: ./api
@@ -167,7 +187,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: codecov/codecov-action@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
@@ -176,10 +196,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - 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@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
       - name: Build Container
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        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/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

@@ -11,7 +11,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: TruffleHog OSS
-        uses: trufflesecurity/trufflehog@34339eaf08bf5c2a27dbd969812127721f3743ed # v3.88.22
+        uses: trufflesecurity/trufflehog@6641d4ba5b684fffe195b9820345de1bf19f3181 # v3.89.2
         with:
           path: ./
           base: ${{ github.event.repository.default_branch }}

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

@@ -0,0 +1,86 @@
+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:
+      id-token: write
+      contents: read
+      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
+        if: github.event.pull_request.head.repo.full_name == github.repository
+        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: github.event.pull_request.head.repo.full_name == github.repository && 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: github.event.pull_request.head.repo.full_name == github.repository && 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

@@ -62,13 +62,13 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Setup Python
-        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        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
@@ -123,11 +123,11 @@ jobs:
           AWS_REGION: ${{ env.AWS_REGION }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
       - name: Build and push container image (latest)
         if: github.event_name == 'push'
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        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@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        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 +1,147 @@
+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 }}"
+            labels: no-changelog
+            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 }}"
+            labels: no-changelog
+            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 * * *'
 
@@ -54,12 +56,12 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+      uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/sdk-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+      uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
       with:
         category: "/language:${{matrix.language}}"

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

@@ -25,7 +25,7 @@ jobs:
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@823fcebdb31bb35fdf2229d9f769b400309430d0 # v46.0.3
+        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@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
@@ -101,20 +102,155 @@ jobs:
         run: |
           poetry run vulture --exclude "contrib,api,ui" --min-confidence 100 .
 
+      - name: Dockerfile - Check if Dockerfile has changed
+        id: dockerfile-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            Dockerfile
+
       - name: Hadolint
-        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        if: steps.dockerfile-changed-files.outputs.any_changed == 'true'
         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@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
+        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:
@@ -71,10 +71,10 @@ jobs:
           pipx install poetry==2.1.1
 
       - name: Setup Python
-        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        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"
@@ -28,7 +28,7 @@ jobs:
           ref: ${{ env.GITHUB_BRANCH }}
 
       - name: setup python
-        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        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@ececac1a45f3b08a01d2dd070d28d111c5fe6722 # v4.1.0
+        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 }}

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

@@ -30,6 +30,7 @@ env:
   # Container Registries
   PROWLERCLOUD_DOCKERHUB_REPOSITORY: prowlercloud
   PROWLERCLOUD_DOCKERHUB_IMAGE: prowler-ui
+  NEXT_PUBLIC_API_BASE_URL: http://prowler-api:8080/api/v1
 
 jobs:
   repository-check:
@@ -76,16 +77,17 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           build-args: |
             NEXT_PUBLIC_PROWLER_RELEASE_VERSION=${{ env.SHORT_SHA }}
+            NEXT_PUBLIC_API_BASE_URL=${{ env.NEXT_PUBLIC_API_BASE_URL }}
           # Set push: false for testing
           push: true
           tags: |
@@ -96,11 +98,12 @@ jobs:
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           build-args: |
             NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${{ env.RELEASE_TAG }}
+            NEXT_PUBLIC_API_BASE_URL=${{ env.NEXT_PUBLIC_API_BASE_URL }}
           push: true
           tags: |
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.RELEASE_TAG }}

.github/workflows/ui-codeql.yml

@@ -48,12 +48,12 @@ jobs:
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+        uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
         with:
           languages: ${{ matrix.language }}
           config-file: ./.github/codeql/ui-codeql-config.yml
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
+        uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
         with:
           category: "/language:${{matrix.language}}"

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

@@ -31,26 +31,75 @@ jobs:
         with:
           persist-credentials: false
       - name: Setup Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@cdca7365b2dadb8aad0a33bc7601856ffabcc48e # v4.3.0
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: ${{ matrix.node-version }}
+          cache: 'npm'
+          cache-dependency-path: './ui/package-lock.json'
       - name: Install dependencies
         working-directory: ./ui
-        run: npm install
+        run: npm ci
       - name: Run Healthcheck
         working-directory: ./ui
         run: npm run healthcheck
       - name: Build the application
         working-directory: ./ui
         run: npm run build
+
+  e2e-tests:
+    runs-on: ubuntu-latest
+    env:
+      AUTH_SECRET: 'fallback-ci-secret-for-testing'
+      AUTH_TRUST_HOST: true
+      NEXTAUTH_URL: http://localhost:3000
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          persist-credentials: false
+      - name: Setup Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
+        with:
+          node-version: '20.x'
+          cache: 'npm'
+          cache-dependency-path: './ui/package-lock.json'
+      - name: Install dependencies
+        working-directory: ./ui
+        run: npm ci
+      - name: Cache Playwright browsers
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        id: playwright-cache
+        with:
+          path: ~/.cache/ms-playwright
+          key: ${{ runner.os }}-playwright-${{ hashFiles('ui/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-playwright-
+      - name: Install Playwright browsers
+        working-directory: ./ui
+        if: steps.playwright-cache.outputs.cache-hit != 'true'
+        run: npm run test:e2e:install
+      - name: Build the application
+        working-directory: ./ui
+        run: npm run build
+      - name: Run Playwright tests
+        working-directory: ./ui
+        run: npm run test:e2e
+      - name: Upload Playwright report
+        uses: actions/upload-artifact@6f51ac03b9356f520e9adb1b1b7802705f340c2b # v4.5.0
+        if: failure()
+        with:
+          name: playwright-report
+          path: ui/playwright-report/
+          retention-days: 30
+
   test-container-build:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
       - name: Build Container
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
         with:
           context: ${{ env.UI_WORKING_DIR }}
           # Always build using `prod` target

.gitignore

@@ -42,6 +42,19 @@ junit-reports/
 # VSCode files
 .vscode/
 
+# Cursor files
+.cursorignore
+.cursor/
+
+# RooCode files
+.roo/
+.rooignore
+.roomodes
+
+# Cline files
+.cline/
+.clineignore
+
 # Terraform
 .terraform*
 *.tfstate

.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 +1,44 @@
-FROM python:3.12.9-alpine3.20
+FROM python:3.12.11-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 libunwind8 libssl3 libcurl4 ca-certificates apt-transport-https gnupg \
+    && 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'
@@ -27,13 +47,12 @@ ENV PATH="${HOME}/.local/bin:${PATH}"
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir poetry
 
-# By default poetry does not compile Python source files to bytecode during installation.
-# This speeds up the installation process, but the first execution may take a little more
-# time because Python then compiles source files to bytecode automatically. If you want to
-# compile source files to bytecode during installation, you can use the --compile option
 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 | 78 | 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 +125,24 @@ 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.
+
+### Common Issues with Docker Pull Installation
+
+> [!Note]
+  If you want to use AWS role assumption (e.g., with the "Connect assuming IAM Role" option), you may need to mount your local `.aws` directory into the container as a volume (e.g., `- "${HOME}/.aws:/home/prowler/.aws:ro"`). There are several ways to configure credentials for Docker containers. See the [Troubleshooting](./docs/troubleshooting.md) section for more details and examples.
+
+You can find more information in the [Troubleshooting](./docs/troubleshooting.md) section.
+
 
 ### From GitHub
 
@@ -128,12 +168,12 @@ 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 +211,31 @@ 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:
@@ -205,7 +247,7 @@ 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
@@ -215,25 +257,46 @@ poetry install
 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 +304,36 @@ 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/.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

@@ -2,42 +2,171 @@
 
 All notable changes to the **Prowler API** are documented in this file.
 
+## [v1.10.0] (Prowler UNRELEASED)
+
+### Added
+- SSO with SAML support [(#8175)](https://github.com/prowler-cloud/prowler/pull/8175)
+- `GET /resources/metadata`, `GET /resources/metadata/latest` and `GET /resources/latest` to expose resource metadata and latest scan results [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
+
+### Changed
+- `/processors` endpoints to post-process findings. Currently, only the Mutelist processor is supported to allow to mute findings.
+- Optimized the underlying queries for resources endpoints [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
+- Optimized include parameters for resources view [(#8229)](https://github.com/prowler-cloud/prowler/pull/8229)
+- Improved user deletion error handling with structured JSON response [(#8272)](https://github.com/prowler-cloud/prowler/pull/8272)
+
+### Fixed
+- Search filter for findings and resources [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
+- RBAC is now applied to `GET /overviews/providers` [(#8277)](https://github.com/prowler-cloud/prowler/pull/8277)
+
+### Changed
+- `POST /schedules/daily` returns a `409 CONFLICT` if already created [(#8258)](https://github.com/prowler-cloud/prowler/pull/8258)
+
+### Security
+- Enhanced password validation to enforce 12+ character passwords with special characters, uppercase, lowercase, and numbers [(#8225)](https://github.com/prowler-cloud/prowler/pull/8225)
+
 ---
 
-## [v1.6.0] (Prowler UNRELEASED)
+## [v1.9.1] (Prowler v5.8.1)
+
+### Added
+- Custom exception for provider connection errors during scans [(#8234)](https://github.com/prowler-cloud/prowler/pull/8234)
+
+### Changed
+- Summary and overview tasks now use a dedicated queue and no longer propagate errors to compliance tasks [(#8214)](https://github.com/prowler-cloud/prowler/pull/8214)
+
+### Fixed
+- Scan with no resources will not trigger legacy code for findings metadata [(#8183)](https://github.com/prowler-cloud/prowler/pull/8183)
+- Invitation email comparison case-insensitive [(#8206)](https://github.com/prowler-cloud/prowler/pull/8206)
+
+### Removed
+- Validation of the provider's secret type during updates [(#8197)](https://github.com/prowler-cloud/prowler/pull/8197)
+
+---
+
+## [v1.9.0] (Prowler v5.8.0)
+
+### Added
+- 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)
+- Optional `user` and `password` for M365 provider [(#7992)](https://github.com/prowler-cloud/prowler/pull/7992)
+
+### Fixed
+- Scheduled scans are no longer deleted when their daily schedule run is disabled [(#8082)](https://github.com/prowler-cloud/prowler/pull/8082)
+
+---
+
+## [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).
-- 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).
-- Added missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318).
+- 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
-- Added duplicated scheduled scans handling ([#7401])(https://github.com/prowler-cloud/prowler/pull/7401).
-- Added environment variable to configure the deletion task batch size ([#7423])(https://github.com/prowler-cloud/prowler/pull/7423).
+- 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).
+- 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
-- Added a handled response in case local files are missing [(#7183)](https://github.com/prowler-cloud/prowler/pull/7183).
-- Fixed a race condition when deleting export files after the S3 upload [(#7172)](https://github.com/prowler-cloud/prowler/pull/7172).
-- Handled exception when a provider has no secret in test connection [(#7283)](https://github.com/prowler-cloud/prowler/pull/7283).
-
+- 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)
 
 ---
 
@@ -45,20 +174,20 @@ 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 +49,22 @@ 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"
+
+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
 
@@ -256,7 +257,7 @@ cd src/backend
 python manage.py loaddata api/fixtures/0_dev_users.json --database admin
 ```
 
-> The default credentials are `dev@prowler.com:thisisapassword123` or `dev2@prowler.com:thisisapassword123`
+> The default credentials are `dev@prowler.com:Thisisapassword123@` or `dev2@prowler.com:Thisisapassword123@`
 
 ## Run tests
 

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,overview -E --max-tasks-per-child 1
 }
 
 start_worker_beat() {

api/pyproject.toml

@@ -7,8 +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-allauth==65.4.1",
+  "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",
@@ -23,11 +23,14 @@ dependencies = [
   "drf-spectacular==0.27.2",
   "drf-spectacular-jsonapi==0.5.1",
   "gunicorn==23.0.0",
+  "lxml==5.3.2",
   "prowler @ git+https://github.com/prowler-cloud/prowler.git@master",
   "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)",
+  "xmlsec==1.3.14"
 ]
 description = "Prowler's API (Django/DRF)"
 license = "Apache-2.0"
@@ -35,7 +38,7 @@ name = "prowler-api"
 package-mode = false
 # Needed for the SDK compatibility
 requires-python = ">=3.11,<3.13"
-version = "1.6.0"
+version = "1.10.0"
 
 [project.scripts]
 celery = "src.backend.config.settings.celery"
@@ -46,6 +49,7 @@ 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

@@ -17,6 +17,8 @@ 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.provider.id == "saml":
+            email = sociallogin.user.email
         if email:
             existing_user = self.get_user_by_email(email)
             if existing_user:
@@ -29,33 +31,41 @@ class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
         """
         with transaction.atomic(using=MainRouter.admin_db):
             user = super().save_user(request, sociallogin, form)
-            user.save(using=MainRouter.admin_db)
-            social_account_name = sociallogin.account.extra_data.get("name")
-            if social_account_name:
-                user.name = social_account_name
-                user.save(using=MainRouter.admin_db)
+            provider = sociallogin.provider.id
+            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
-                )
-                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,
+            if provider != "saml":
+                # 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,
+                    )
+            else:
+                request.session["saml_user_created"] = str(user.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
@@ -152,6 +153,28 @@ def delete_related_daily_task(provider_id: str):
     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
 
 
@@ -227,6 +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
 
 
@@ -345,3 +529,15 @@ class IntegrationTypeEnum(EnumType):
 class IntegrationTypeEnumField(PostgresEnumField):
     def __init__(self, *args, **kwargs):
         super().__init__("integration_type", *args, **kwargs)
+
+
+# Postgres enum definition for Processor type
+
+
+class ProcessorTypeEnum(EnumType):
+    enum_type_name = "processor_type"
+
+
+class ProcessorTypeEnumField(PostgresEnumField):
+    def __init__(self, *args, **kwargs):
+        super().__init__("processor_type", *args, **kwargs)

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 +32,36 @@ 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__()
+
+
+# Provider connection errors
+class ProviderConnectionError(Exception):
+    """Base exception for provider connection errors."""
+
+
 def custom_exception_handler(exc, context):
     if isinstance(exc, django_validation_error):
         if hasattr(exc, "error_dict"):
@@ -39,7 +69,30 @@ 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)
+
+
+class ConflictException(APIException):
+    status_code = status.HTTP_409_CONFLICT
+    default_detail = "A conflict occurred. The resource already exists."
+    default_code = "conflict"
+
+    def __init__(self, detail=None, code=None, pointer=None):
+        error_detail = {
+            "detail": detail or self.default_detail,
+            "status": self.status_code,
+            "code": self.default_code,
+        }
+
+        if pointer:
+            error_detail["source"] = {"pointer": pointer}
+
+        super().__init__(detail=[error_detail])

api/src/backend/api/filters.py

@@ -1,5 +1,6 @@
 from datetime import date, datetime, timedelta, timezone
 
+from dateutil.parser import parse
 from django.conf import settings
 from django.db.models import Q
 from django_filters.rest_framework import (
@@ -22,12 +23,13 @@ from api.db_utils import (
     StatusEnumField,
 )
 from api.models import (
-    ComplianceOverview,
+    ComplianceRequirementOverview,
     Finding,
     Integration,
     Invitation,
     Membership,
     PermissionChoices,
+    Processor,
     Provider,
     ProviderGroup,
     ProviderSecret,
@@ -81,6 +83,114 @@ 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")
@@ -230,6 +340,8 @@ class ResourceFilter(ProviderRelationshipFilterSet):
     tags = CharFilter(method="filter_tag")
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
     updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
+    scan = UUIDFilter(field_name="provider__scan", lookup_expr="exact")
+    scan__in = UUIDInFilter(field_name="provider__scan", lookup_expr="in")
 
     class Meta:
         model = Resource
@@ -244,6 +356,82 @@ class ResourceFilter(ProviderRelationshipFilterSet):
             "updated_at": ["gte", "lte"],
         }
 
+    def filter_queryset(self, queryset):
+        if not (self.data.get("scan") or self.data.get("scan__in")) and not (
+            self.data.get("updated_at")
+            or self.data.get("updated_at__date")
+            or self.data.get("updated_at__gte")
+            or self.data.get("updated_at__lte")
+        ):
+            raise ValidationError(
+                [
+                    {
+                        "detail": "At least one date filter is required: filter[updated_at], filter[updated_at.gte], "
+                        "or filter[updated_at.lte].",
+                        "status": 400,
+                        "source": {"pointer": "/data/attributes/updated_at"},
+                        "code": "required",
+                    }
+                ]
+            )
+
+        gte_date = (
+            parse(self.data.get("updated_at__gte")).date()
+            if self.data.get("updated_at__gte")
+            else datetime.now(timezone.utc).date()
+        )
+        lte_date = (
+            parse(self.data.get("updated_at__lte")).date()
+            if self.data.get("updated_at__lte")
+            else datetime.now(timezone.utc).date()
+        )
+
+        if abs(lte_date - gte_date) > timedelta(
+            days=settings.FINDINGS_MAX_DAYS_IN_RANGE
+        ):
+            raise ValidationError(
+                [
+                    {
+                        "detail": f"The date range cannot exceed {settings.FINDINGS_MAX_DAYS_IN_RANGE} days.",
+                        "status": 400,
+                        "source": {"pointer": "/data/attributes/updated_at"},
+                        "code": "invalid",
+                    }
+                ]
+            )
+
+        return super().filter_queryset(queryset)
+
+    def filter_tag_key(self, queryset, name, value):
+        return queryset.filter(Q(tags__key=value) | Q(tags__key__icontains=value))
+
+    def filter_tag_value(self, queryset, name, value):
+        return queryset.filter(Q(tags__value=value) | Q(tags__value__icontains=value))
+
+    def filter_tag(self, queryset, name, value):
+        # We won't know what the user wants to filter on just based on the value,
+        # and we don't want to build special filtering logic for every possible
+        # provider tag spec, so we'll just do a full text search
+        return queryset.filter(tags__text_search=value)
+
+
+class LatestResourceFilter(ProviderRelationshipFilterSet):
+    tag_key = CharFilter(method="filter_tag_key")
+    tag_value = CharFilter(method="filter_tag_value")
+    tag = CharFilter(method="filter_tag")
+    tags = CharFilter(method="filter_tag")
+
+    class Meta:
+        model = Resource
+        fields = {
+            "provider": ["exact", "in"],
+            "uid": ["exact", "icontains"],
+            "name": ["exact", "icontains"],
+            "region": ["exact", "icontains", "in"],
+            "service": ["exact", "icontains", "in"],
+            "type": ["exact", "icontains", "in"],
+        }
+
     def filter_tag_key(self, queryset, name, value):
         return queryset.filter(Q(tags__key=value) | Q(tags__key__icontains=value))
 
@@ -257,94 +445,7 @@ 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)
-    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(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")
 
@@ -385,6 +486,15 @@ 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")
@@ -503,16 +613,6 @@ 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
@@ -521,6 +621,31 @@ 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")
@@ -592,12 +717,11 @@ 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"],
@@ -660,3 +784,12 @@ class IntegrationFilter(FilterSet):
         fields = {
             "inserted_at": ["date", "gte", "lte"],
         }
+
+
+class ProcessorFilter(FilterSet):
+    processor_type = ChoiceFilter(choices=Processor.ProcessorChoices.choices)
+    processor_type__in = ChoiceInFilter(
+        choices=Processor.ProcessorChoices.choices,
+        field_name="processor_type",
+        lookup_expr="in",
+    )

api/src/backend/api/fixtures/dev/0_dev_users.json

@@ -3,7 +3,7 @@
     "model": "api.user",
     "pk": "8b38e2eb-6689-4f1e-a4ba-95b275130200",
     "fields": {
-      "password": "pbkdf2_sha256$720000$vA62S78kog2c2ytycVQdke$Fp35GVLLMyy5fUq3krSL9I02A+ocQ+RVa4S22LIAO5s=",
+      "password": "pbkdf2_sha256$870000$Z63pGJ7nre48hfcGbk5S0O$rQpKczAmijs96xa+gPVJifpT3Fetb8DOusl5Eq6gxac=",
       "last_login": null,
       "name": "Devie Prowlerson",
       "email": "dev@prowler.com",
@@ -16,7 +16,7 @@
     "model": "api.user",
     "pk": "b6493a3a-c997-489b-8b99-278bf74de9f6",
     "fields": {
-      "password": "pbkdf2_sha256$720000$vA62S78kog2c2ytycVQdke$Fp35GVLLMyy5fUq3krSL9I02A+ocQ+RVa4S22LIAO5s=",
+      "password": "pbkdf2_sha256$870000$Z63pGJ7nre48hfcGbk5S0O$rQpKczAmijs96xa+gPVJifpT3Fetb8DOusl5Eq6gxac=",
       "last_login": null,
       "name": "Devietoo Prowlerson",
       "email": "dev2@prowler.com",

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/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_lighthouseconfiguration.py

@@ -0,0 +1,107 @@
+# 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", "0029_findings_check_index_parent"),
+    ]
+
+    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"),
+                        ],
+                        default="gpt-4o-2024-08-06",
+                        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/migrations/0031_scan_disable_on_cascade_periodic_tasks.py

@@ -0,0 +1,24 @@
+# Generated by Django 5.1.10 on 2025-06-23 10:04
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0030_lighthouseconfiguration"),
+        ("django_celery_beat", "0019_alter_periodictasks_options"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="scan",
+            name="scheduler_task",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                to="django_celery_beat.periodictask",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0032_saml.py

@@ -0,0 +1,150 @@
+# Generated by Django 5.1.10 on 2025-07-02 15:47
+
+import uuid
+
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations, models
+
+import api.db_utils
+import api.rls
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0031_scan_disable_on_cascade_periodic_tasks"),
+    ]
+
+    operations = [
+        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"),
+                ]
+            ),
+        ),
+        migrations.CreateModel(
+            name="SAMLToken",
+            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)),
+                ("expires_at", models.DateTimeField(editable=False)),
+                ("token", models.JSONField(unique=True)),
+                (
+                    "user",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to=settings.AUTH_USER_MODEL,
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "saml_tokens",
+            },
+        ),
+        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.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"],
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0033_processors_enum.py

@@ -0,0 +1,34 @@
+# Generated by Django 5.1.5 on 2025-03-03 15:46
+
+from functools import partial
+
+from django.db import migrations
+
+from api.db_utils import PostgresEnumMigration, ProcessorTypeEnum, register_enum
+from api.models import Processor
+
+ProcessorTypeEnumMigration = PostgresEnumMigration(
+    enum_name="processor_type",
+    enum_values=tuple(
+        processor_type[0] for processor_type in Processor.ProcessorChoices.choices
+    ),
+)
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0032_saml"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            ProcessorTypeEnumMigration.create_enum_type,
+            reverse_code=ProcessorTypeEnumMigration.drop_enum_type,
+        ),
+        migrations.RunPython(
+            partial(register_enum, enum_class=ProcessorTypeEnum),
+            reverse_code=migrations.RunPython.noop,
+        ),
+    ]

api/src/backend/api/migrations/0034_processors.py

@@ -0,0 +1,88 @@
+# Generated by Django 5.1.5 on 2025-03-26 13:04
+
+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", "0033_processors_enum"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Processor",
+            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)),
+                (
+                    "processor_type",
+                    api.db_utils.ProcessorTypeEnumField(
+                        choices=[("mutelist", "Mutelist")]
+                    ),
+                ),
+                ("configuration", models.JSONField(default=dict)),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "processors",
+                "abstract": False,
+                "indexes": [
+                    models.Index(
+                        fields=["tenant_id", "id"], name="processor_tenant_id_idx"
+                    ),
+                    models.Index(
+                        fields=["tenant_id", "processor_type"],
+                        name="processor_tenant_type_idx",
+                    ),
+                ],
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="processor",
+            constraint=models.UniqueConstraint(
+                fields=("tenant_id", "processor_type"),
+                name="unique_processor_types_tenant",
+            ),
+        ),
+        migrations.AddConstraint(
+            model_name="processor",
+            constraint=RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_processor",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+        migrations.AddField(
+            model_name="scan",
+            name="processor",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="scans",
+                related_query_name="scan",
+                to="api.processor",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0035_finding_muted_reason.py

@@ -0,0 +1,22 @@
+import django.core.validators
+import django.db.models.deletion
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0034_processors"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="muted_reason",
+            field=models.TextField(
+                blank=True,
+                max_length=500,
+                null=True,
+                validators=[django.core.validators.MinLengthValidator(3)],
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0036_rfm_tenant_finding_index_partitions.py

@@ -0,0 +1,30 @@
+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", "0035_finding_muted_reason"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="resource_finding_mappings",
+                index_name="rfm_tenant_finding_idx",
+                columns="tenant_id, finding_id",
+                method="BTREE",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="resource_finding_mappings",
+                index_name="rfm_tenant_finding_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0037_rfm_tenant_finding_index_parent.py

@@ -0,0 +1,17 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0036_rfm_tenant_finding_index_partitions"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="resourcefindingmapping",
+            index=models.Index(
+                fields=["tenant_id", "finding_id"],
+                name="rfm_tenant_finding_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0038_resource_failed_findings_count.py

@@ -0,0 +1,15 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0037_rfm_tenant_finding_index_parent"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="resource",
+            name="failed_findings_count",
+            field=models.IntegerField(default=0),
+        )
+    ]

api/src/backend/api/migrations/0039_resource_resources_failed_findings_idx.py

@@ -0,0 +1,20 @@
+from django.contrib.postgres.operations import AddIndexConcurrently
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0038_resource_failed_findings_count"),
+    ]
+
+    operations = [
+        AddIndexConcurrently(
+            model_name="resource",
+            index=models.Index(
+                fields=["tenant_id", "-failed_findings_count", "id"],
+                name="resources_failed_findings_idx",
+            ),
+        ),
+    ]

api/src/backend/api/models.py

@@ -1,12 +1,21 @@
 import json
+import logging
 import re
+import xml.etree.ElementTree as ET
+from datetime import datetime, timedelta, timezone
 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
@@ -18,12 +27,14 @@ 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,
     IntegrationTypeEnumField,
     InvitationStateEnumField,
     MemberRoleEnumField,
+    ProcessorTypeEnumField,
     ProviderEnumField,
     ProviderSecretTypeEnumField,
     ScanTriggerEnumField,
@@ -48,6 +59,8 @@ 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):
     """
@@ -191,6 +204,7 @@ class Provider(RowLevelSecurityProtectedModel):
         AZURE = "azure", _("Azure")
         GCP = "gcp", _("GCP")
         KUBERNETES = "kubernetes", _("Kubernetes")
+        M365 = "m365", _("M365")
 
     @staticmethod
     def validate_aws_uid(value):
@@ -214,6 +228,19 @@ 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):
@@ -227,7 +254,7 @@ 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(
@@ -383,20 +410,6 @@ class Scan(RowLevelSecurityProtectedModel):
     name = models.CharField(
         blank=True, null=True, max_length=100, validators=[MinLengthValidator(3)]
     )
-    provider = models.ForeignKey(
-        Provider,
-        on_delete=models.CASCADE,
-        related_name="scans",
-        related_query_name="scan",
-    )
-    task = models.ForeignKey(
-        Task,
-        on_delete=models.CASCADE,
-        related_name="scans",
-        related_query_name="scan",
-        null=True,
-        blank=True,
-    )
     trigger = ScanTriggerEnumField(
         choices=TriggerChoices.choices,
     )
@@ -412,10 +425,31 @@ class Scan(RowLevelSecurityProtectedModel):
     completed_at = models.DateTimeField(null=True, blank=True)
     next_scan_at = models.DateTimeField(null=True, blank=True)
     scheduler_task = models.ForeignKey(
-        PeriodicTask, on_delete=models.CASCADE, null=True, blank=True
+        PeriodicTask, on_delete=models.SET_NULL, null=True, blank=True
     )
     output_location = models.CharField(blank=True, null=True, max_length=200)
-    # TODO: mutelist foreign key
+    provider = models.ForeignKey(
+        Provider,
+        on_delete=models.CASCADE,
+        related_name="scans",
+        related_query_name="scan",
+    )
+    task = models.ForeignKey(
+        Task,
+        on_delete=models.CASCADE,
+        related_name="scans",
+        related_query_name="scan",
+        null=True,
+        blank=True,
+    )
+    processor = models.ForeignKey(
+        "Processor",
+        on_delete=models.SET_NULL,
+        related_name="scans",
+        related_query_name="scan",
+        null=True,
+        blank=True,
+    )
 
     class Meta(RowLevelSecurityProtectedModel.Meta):
         db_table = "scans"
@@ -437,6 +471,11 @@ 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:
@@ -522,6 +561,8 @@ class Resource(RowLevelSecurityProtectedModel):
     details = models.TextField(blank=True, null=True)
     partition = models.TextField(blank=True, null=True)
 
+    failed_findings_count = models.IntegerField(default=0)
+
     # Relationships
     tags = models.ManyToManyField(
         ResourceTag,
@@ -563,6 +604,15 @@ 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",
+            ),
+            models.Index(
+                fields=["tenant_id", "-failed_findings_count", "id"],
+                name="resources_failed_findings_idx",
+            ),
         ]
 
         constraints = [
@@ -661,8 +711,26 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
     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)
+    muted_reason = models.TextField(
+        blank=True, null=True, validators=[MinLengthValidator(3)], max_length=500
+    )
     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)
 
@@ -703,18 +771,6 @@ 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"),
@@ -726,19 +782,46 @@ 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()
 
 
@@ -772,6 +855,12 @@ class ResourceFindingMapping(PostgresPartitionedModel, RowLevelSecurityProtected
         #   - tenant_id
         #   - id
 
+        indexes = [
+            models.Index(
+                fields=["tenant_id", "finding_id"],
+                name="rfm_tenant_finding_idx",
+            ),
+        ]
         constraints = [
             models.UniqueConstraint(
                 fields=("tenant_id", "resource_id", "finding_id"),
@@ -798,6 +887,7 @@ 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)
@@ -875,6 +965,11 @@ class Invitation(RowLevelSecurityProtectedModel):
         null=True,
     )
 
+    def save(self, *args, **kwargs):
+        if self.email:
+            self.email = self.email.strip().lower()
+        super().save(*args, **kwargs)
+
     class Meta(RowLevelSecurityProtectedModel.Meta):
         db_table = "invitations"
 
@@ -1090,6 +1185,78 @@ 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()
@@ -1140,7 +1307,15 @@ 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:
@@ -1150,7 +1325,6 @@ 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")
@@ -1222,3 +1396,485 @@ class IntegrationProviderRelationship(RowLevelSecurityProtectedModel):
                 statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
             ),
         ]
+
+
+class SAMLToken(models.Model):
+    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)
+    expires_at = models.DateTimeField(editable=False)
+    token = models.JSONField(unique=True)
+    user = models.ForeignKey(User, on_delete=models.CASCADE)
+
+    class Meta:
+        db_table = "saml_tokens"
+
+    def save(self, *args, **kwargs):
+        if not self.expires_at:
+            self.expires_at = datetime.now(timezone.utc) + timedelta(seconds=15)
+        super().save(*args, **kwargs)
+
+    def is_expired(self) -> bool:
+        return datetime.now(timezone.utc) >= self.expires_at
+
+
+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, is_create=False):
+        # 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."}
+            )
+
+        # The entityID must be unique in the system
+        idp_settings = self._parsed_metadata
+        entity_id = idp_settings.get("entity_id")
+
+        if entity_id:
+            # Find any SocialApp with this entityID
+            q = SocialApp.objects.filter(provider="saml", provider_id=entity_id)
+
+            # If updating, exclude our own SocialApp from the check
+            if not is_create:
+                q = q.exclude(client_id=old_email_domain)
+            else:
+                q = q.exclude(client_id=self.email_domain)
+
+            if q.exists():
+                raise ValidationError(
+                    {"metadata_xml": "There is a problem with your metadata."}
+                )
+
+    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._parsed_metadata = self._parse_metadata()
+        self.clean(old_email_domain, is_create)
+        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 delete(self, *args, **kwargs):
+        super().delete(*args, **kwargs)
+
+        SocialApp.objects.filter(provider="saml", client_id=self.email_domain).delete()
+        SAMLDomainIndex.objects.filter(email_domain=self.email_domain).delete()
+
+    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")
+        if not entity_id:
+            raise ValidationError({"metadata_xml": "Missing entityID in metadata."})
+
+        # 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.
+        """
+        settings_dict = SOCIALACCOUNT_PROVIDERS["saml"].copy()
+        settings_dict["idp"] = self._parsed_metadata
+
+        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
+        )
+
+        client_id = self.email_domain[:191]
+        name = f"SAML-{self.email_domain}"[:40]
+
+        if social_app_qs.exists():
+            social_app = social_app_qs.first()
+            social_app.client_id = client_id
+            social_app.name = name
+            social_app.settings = settings_dict
+            social_app.provider_id = self._parsed_metadata["entity_id"]
+            social_app.save()
+            social_app.sites.set([current_site])
+        else:
+            social_app = SocialApp.objects.create(
+                provider="saml",
+                client_id=client_id,
+                name=name,
+                settings=settings_dict,
+                provider_id=self._parsed_metadata["entity_id"],
+            )
+            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"
+
+
+class Processor(RowLevelSecurityProtectedModel):
+    class ProcessorChoices(models.TextChoices):
+        MUTELIST = "mutelist", _("Mutelist")
+
+    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)
+    processor_type = ProcessorTypeEnumField(choices=ProcessorChoices.choices)
+    configuration = models.JSONField(default=dict)
+
+    class Meta(RowLevelSecurityProtectedModel.Meta):
+        db_table = "processors"
+
+        constraints = [
+            models.UniqueConstraint(
+                fields=("tenant_id", "processor_type"),
+                name="unique_processor_types_tenant",
+            ),
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+        indexes = [
+            models.Index(
+                fields=["tenant_id", "id"],
+                name="processor_tenant_id_idx",
+            ),
+            models.Index(
+                fields=["tenant_id", "processor_type"],
+                name="processor_tenant_type_idx",
+            ),
+        ]
+
+    class JSONAPIMeta:
+        resource_name = "processors"

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/tests/integration/test_authentication.py

@@ -11,7 +11,7 @@ def test_basic_authentication():
     client = APIClient()
 
     test_user = "test_email@prowler.com"
-    test_password = "test_password"
+    test_password = "Test_password@1"
 
     # Check that a 401 is returned when no basic authentication is provided
     no_auth_response = client.get(reverse("provider-list"))
@@ -108,7 +108,7 @@ def test_user_me_when_inviting_users(create_test_user, tenants_fixture, roles_fi
     user1_email = "user1@testing.com"
     user2_email = "user2@testing.com"
 
-    password = "thisisapassword123"
+    password = "Thisisapassword123@"
 
     user1_response = client.post(
         reverse("user-list"),
@@ -187,7 +187,7 @@ class TestTokenSwitchTenant:
         client = APIClient()
 
         test_user = "test_email@prowler.com"
-        test_password = "test_password"
+        test_password = "Test_password1@"
 
         # Check that we can create a new user without any kind of authentication
         user_creation_response = client.post(

api/src/backend/api/tests/integration/test_providers.py

@@ -17,7 +17,7 @@ def test_delete_provider_without_executing_task(
     client = APIClient()
 
     test_user = "test_email@prowler.com"
-    test_password = "test_password"
+    test_password = "Test_password1@"
 
     prowler_task = tasks_fixture[0]
     task_mock = Mock()

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

@@ -0,0 +1,77 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from allauth.socialaccount.models import SocialLogin
+from django.contrib.auth import get_user_model
+
+from api.adapters import ProwlerSocialAccountAdapter
+
+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.provider = MagicMock()
+        sociallogin.provider.id = "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.provider = MagicMock()
+        sociallogin.user = MagicMock()
+        sociallogin.provider.id = "saml"
+        sociallogin.account.extra_data = {}
+        sociallogin.connect = MagicMock()
+
+        adapter.pre_social_login(rf.get("/"), sociallogin)
+
+        sociallogin.connect.assert_not_called()
+
+    def test_save_user_saml_sets_session_flag(self, rf):
+        adapter = ProwlerSocialAccountAdapter()
+        request = rf.get("/")
+        request.session = {}
+
+        sociallogin = MagicMock(spec=SocialLogin)
+        sociallogin.provider = MagicMock()
+        sociallogin.provider.id = "saml"
+        sociallogin.account = MagicMock()
+        sociallogin.account.extra_data = {}
+
+        mock_user = MagicMock()
+        mock_user.id = 123
+
+        with patch("api.adapters.super") as mock_super:
+            with patch("api.adapters.transaction"):
+                with patch("api.adapters.MainRouter"):
+                    mock_super.return_value.save_user.return_value = mock_user
+                    adapter.save_user(request, sociallogin)
+                    assert request.session["saml_user_created"] == "123"

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,
@@ -138,3 +142,88 @@ class TestBatchDelete:
         )
         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, SAMLDomainIndex
 
 
 @pytest.mark.django_db
@@ -92,3 +95,232 @@ 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, tenants_fixture):
+        tenant = tenants_fixture[0]
+        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, tenants_fixture):
+        tenant = tenants_fixture[0]
+        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, tenants_fixture):
+        tenant1, tenant2, *_ = tenants_fixture
+
+        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, tenants_fixture):
+        tenant = tenants_fixture[0]
+
+        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, tenants_fixture):
+        tenant = tenants_fixture[0]
+        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, tenants_fixture):
+        tenant = tenants_fixture[0]
+        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, tenants_fixture):
+        tenant = tenants_fixture[0]
+        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]
+
+    def test_deletes_saml_configuration_and_related_objects(self, tenants_fixture):
+        tenant = tenants_fixture[0]
+        email_domain = "deleteme.com"
+
+        # Create the configuration
+        config = SAMLConfiguration.objects.using(MainRouter.admin_db).create(
+            email_domain=email_domain,
+            metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
+            tenant=tenant,
+        )
+
+        # Verify that the SocialApp and SAMLDomainIndex exist
+        assert SocialApp.objects.filter(client_id=email_domain).exists()
+        assert (
+            SAMLDomainIndex.objects.using(MainRouter.admin_db)
+            .filter(email_domain=email_domain)
+            .exists()
+        )
+
+        # Delete the configuration
+        config.delete()
+
+        # Verify that the configuration and its related objects are deleted
+        assert (
+            not SAMLConfiguration.objects.using(MainRouter.admin_db)
+            .filter(pk=config.pk)
+            .exists()
+        )
+        assert not SocialApp.objects.filter(client_id=email_domain).exists()
+        assert (
+            not SAMLDomainIndex.objects.using(MainRouter.admin_db)
+            .filter(email_domain=email_domain)
+            .exists()
+        )
+
+    def test_duplicate_entity_id_fails_on_creation(self, tenants_fixture):
+        tenant1, tenant2, *_ = tenants_fixture
+        SAMLConfiguration.objects.using(MainRouter.admin_db).create(
+            email_domain="first.com",
+            metadata_xml=self.VALID_METADATA,
+            tenant=tenant1,
+        )
+
+        config = SAMLConfiguration(
+            email_domain="second.com",
+            metadata_xml=self.VALID_METADATA,
+            tenant=tenant2,
+        )
+
+        with pytest.raises(ValidationError) as exc_info:
+            config.save()
+
+        errors = exc_info.value.message_dict
+        assert "metadata_xml" in errors
+        assert "There is a problem with your metadata." in errors["metadata_xml"][0]

api/src/backend/api/tests/test_rbac.py

@@ -1,6 +1,7 @@
 from unittest.mock import ANY, Mock, patch
 
 import pytest
+from conftest import TODAY
 from django.urls import reverse
 from rest_framework import status
 
@@ -60,7 +61,7 @@ class TestUserViewSet:
     def test_create_user_with_all_permissions(self, authenticated_client_rbac):
         valid_user_payload = {
             "name": "test",
-            "password": "newpassword123",
+            "password": "Newpassword123@",
             "email": "new_user@test.com",
         }
         response = authenticated_client_rbac.post(
@@ -74,7 +75,7 @@ class TestUserViewSet:
     ):
         valid_user_payload = {
             "name": "test",
-            "password": "newpassword123",
+            "password": "Newpassword123@",
             "email": "new_user@test.com",
         }
         response = authenticated_client_no_permissions_rbac.post(
@@ -321,7 +322,7 @@ class TestProviderViewSet:
 @pytest.mark.django_db
 class TestLimitedVisibility:
     TEST_EMAIL = "rbac@rbac.com"
-    TEST_PASSWORD = "thisisapassword123"
+    TEST_PASSWORD = "Thisisapassword123@"
 
     @pytest.fixture
     def limited_admin_user(
@@ -409,3 +410,87 @@ class TestLimitedVisibility:
         assert (
             response.json()["data"]["relationships"]["providers"]["meta"]["count"] == 1
         )
+
+    def test_overviews_providers(
+        self,
+        authenticated_client_rbac_limited,
+        scan_summaries_fixture,
+        providers_fixture,
+    ):
+        # By default, the associated provider is the one which has the overview data
+        response = authenticated_client_rbac_limited.get(reverse("overview-providers"))
+
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) > 0
+
+        # Changing the provider visibility, no data should be returned
+        # Only the associated provider to that group is changed
+        new_provider = providers_fixture[1]
+        ProviderGroupMembership.objects.all().update(provider=new_provider)
+
+        response = authenticated_client_rbac_limited.get(reverse("overview-providers"))
+
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) == 0
+
+    @pytest.mark.parametrize(
+        "endpoint_name",
+        [
+            "findings",
+            "findings_severity",
+        ],
+    )
+    def test_overviews_findings(
+        self,
+        endpoint_name,
+        authenticated_client_rbac_limited,
+        scan_summaries_fixture,
+        providers_fixture,
+    ):
+        # By default, the associated provider is the one which has the overview data
+        response = authenticated_client_rbac_limited.get(
+            reverse(f"overview-{endpoint_name}")
+        )
+
+        assert response.status_code == status.HTTP_200_OK
+        values = response.json()["data"]["attributes"].values()
+        assert any(value > 0 for value in values)
+
+        # Changing the provider visibility, no data should be returned
+        # Only the associated provider to that group is changed
+        new_provider = providers_fixture[1]
+        ProviderGroupMembership.objects.all().update(provider=new_provider)
+
+        response = authenticated_client_rbac_limited.get(
+            reverse(f"overview-{endpoint_name}")
+        )
+
+        assert response.status_code == status.HTTP_200_OK
+        data = response.json()["data"]["attributes"].values()
+        assert all(value == 0 for value in data)
+
+    def test_overviews_services(
+        self,
+        authenticated_client_rbac_limited,
+        scan_summaries_fixture,
+        providers_fixture,
+    ):
+        # By default, the associated provider is the one which has the overview data
+        response = authenticated_client_rbac_limited.get(
+            reverse("overview-services"), {"filter[inserted_at]": TODAY}
+        )
+
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) > 0
+
+        # Changing the provider visibility, no data should be returned
+        # Only the associated provider to that group is changed
+        new_provider = providers_fixture[1]
+        ProviderGroupMembership.objects.all().update(provider=new_provider)
+
+        response = authenticated_client_rbac_limited.get(
+            reverse("overview-services"), {"filter[inserted_at]": TODAY}
+        )
+
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) == 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

@@ -19,6 +19,7 @@ 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 prowler.providers.m365.m365_provider import M365Provider
 
 
 class TestMergeDicts:
@@ -104,6 +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):
@@ -129,6 +131,21 @@ class TestInitializeProwlerProvider:
         initialize_prowler_provider(provider)
         mock_return_prowler_provider.return_value.assert_called_once_with(key="value")
 
+    @patch("api.utils.return_prowler_provider")
+    def test_initialize_prowler_provider_with_mutelist(
+        self, mock_return_prowler_provider
+    ):
+        provider = MagicMock()
+        provider.secret.secret = {"key": "value"}
+        mutelist_processor = MagicMock()
+        mutelist_processor.configuration = {"Mutelist": {"key": "value"}}
+        mock_return_prowler_provider.return_value = MagicMock()
+
+        initialize_prowler_provider(provider, mutelist_processor)
+        mock_return_prowler_provider.return_value.assert_called_once_with(
+            key="value", mutelist_content={"key": "value"}
+        )
+
 
 class TestProwlerProviderConnectionTest:
     @patch("api.utils.return_prowler_provider")
@@ -176,6 +193,10 @@ 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):
@@ -194,6 +215,25 @@ class TestGetProwlerProviderKwargs:
         expected_result = {**secret_dict, **expected_extra_kwargs}
         assert result == expected_result
 
+    def test_get_prowler_provider_kwargs_with_mutelist(self):
+        provider_uid = "provider_uid"
+        secret_dict = {"key": "value"}
+        secret_mock = MagicMock()
+        secret_mock.secret = secret_dict
+
+        mutelist_processor = MagicMock()
+        mutelist_processor.configuration = {"Mutelist": {"key": "value"}}
+
+        provider = MagicMock()
+        provider.provider = Provider.ProviderChoices.AWS.value
+        provider.secret = secret_mock
+        provider.uid = provider_uid
+
+        result = get_prowler_provider_kwargs(provider, mutelist_processor)
+
+        expected_result = {**secret_dict, "mutelist_content": {"key": "value"}}
+        assert result == expected_result
+
     def test_get_prowler_provider_kwargs_unsupported_provider(self):
         # Setup
         provider_uid = "provider_uid"
@@ -248,7 +288,7 @@ class TestValidateInvitation:
 
             assert result == invitation
             mock_db.get.assert_called_once_with(
-                token="VALID_TOKEN", email="user@example.com"
+                token="VALID_TOKEN", email__iexact="user@example.com"
             )
 
     def test_invitation_not_found_raises_validation_error(self):
@@ -263,7 +303,7 @@ class TestValidateInvitation:
                 "invitation_token": "Invalid invitation code."
             }
             mock_db.get.assert_called_once_with(
-                token="INVALID_TOKEN", email="user@example.com"
+                token="INVALID_TOKEN", email__iexact="user@example.com"
             )
 
     def test_invitation_not_found_raises_not_found(self):
@@ -278,7 +318,7 @@ class TestValidateInvitation:
 
             assert exc_info.value.detail == "Invitation is not valid."
             mock_db.get.assert_called_once_with(
-                token="INVALID_TOKEN", email="user@example.com"
+                token="INVALID_TOKEN", email__iexact="user@example.com"
             )
 
     def test_invitation_expired(self, invitation):
@@ -326,5 +366,27 @@ class TestValidateInvitation:
                 "invitation_token": "Invalid invitation code."
             }
             mock_db.get.assert_called_once_with(
-                token="VALID_TOKEN", email="different@example.com"
+                token="VALID_TOKEN", email__iexact="different@example.com"
+            )
+
+    def test_valid_invitation_uppercase_email(self):
+        """Test that validate_invitation works with case-insensitive email lookup."""
+        uppercase_email = "USER@example.com"
+
+        invitation = MagicMock(spec=Invitation)
+        invitation.token = "VALID_TOKEN"
+        invitation.email = uppercase_email
+        invitation.expires_at = datetime.now(timezone.utc) + timedelta(days=1)
+        invitation.state = Invitation.State.PENDING
+        invitation.tenant = MagicMock()
+
+        with patch("api.utils.Invitation.objects.using") as mock_using:
+            mock_db = mock_using.return_value
+            mock_db.get.return_value = invitation
+
+            result = validate_invitation("VALID_TOKEN", "user@example.com")
+
+            assert result == invitation
+            mock_db.get.assert_called_once_with(
+                token="VALID_TOKEN", email__iexact="user@example.com"
             )

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, Processor, 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.
@@ -72,16 +76,21 @@ 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
 
 
-def get_prowler_provider_kwargs(provider: Provider) -> dict:
+def get_prowler_provider_kwargs(
+    provider: Provider, mutelist_processor: Processor | None = None
+) -> dict:
     """Get the Prowler provider kwargs based on the given provider type.
 
     Args:
         provider (Provider): The provider object containing the provider type and associated secret.
+        mutelist_processor (Processor): The mutelist processor object containing the mutelist configuration.
 
     Returns:
         dict: The provider kwargs for the corresponding provider class.
@@ -99,24 +108,32 @@ def get_prowler_provider_kwargs(provider: Provider) -> dict:
         }
     elif provider.provider == Provider.ProviderChoices.KUBERNETES.value:
         prowler_provider_kwargs = {**prowler_provider_kwargs, "context": provider.uid}
+
+    if mutelist_processor:
+        mutelist_content = mutelist_processor.configuration.get("Mutelist", {})
+        if mutelist_content:
+            prowler_provider_kwargs["mutelist_content"] = mutelist_content
+
     return prowler_provider_kwargs
 
 
 def initialize_prowler_provider(
     provider: Provider,
-) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider:
+    mutelist_processor: Processor | None = None,
+) -> 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.
+        mutelist_processor (Processor): The mutelist processor object containing the mutelist configuration.
 
     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)
-    prowler_provider_kwargs = get_prowler_provider_kwargs(provider)
+    prowler_provider_kwargs = get_prowler_provider_kwargs(provider, mutelist_processor)
     return prowler_provider(**prowler_provider_kwargs)
 
 
@@ -130,10 +147,12 @@ 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)
+
     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
     )
@@ -179,7 +198,7 @@ def validate_invitation(
         # Admin DB connector is used to bypass RLS protection since the invitation belongs to a tenant the user
         # is not a member of yet
         invitation = Invitation.objects.using(MainRouter.admin_db).get(
-            token=invitation_token, email=email
+            token=invitation_token, email__iexact=email
         )
     except Invitation.DoesNotExist:
         if raise_not_found:
@@ -200,3 +219,33 @@ 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 +1,234 @@
+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 | None = None,
+        prefetch_related: list | None = None,
+    ) -> Response:
+        """
+        Paginate a queryset by primary key.
+
+        This method is useful when you want to paginate a queryset that has been
+        filtered or annotated in a way that would be lost if you used the default
+        pagination method.
+        """
+        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)
+
+        # Optimize tags loading, if applicable
+        if hasattr(self, "_optimize_tags_loading"):
+            queryset = self._optimize_tags_loading(queryset)
+
+        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/base.py

@@ -0,0 +1,23 @@
+import yaml
+from rest_framework_json_api import serializers
+from rest_framework_json_api.serializers import ValidationError
+
+
+class BaseValidateSerializer(serializers.Serializer):
+    def validate(self, data):
+        if hasattr(self, "initial_data"):
+            initial_data = set(self.initial_data.keys()) - {"id", "type"}
+            unknown_keys = initial_data - set(self.fields.keys())
+            if unknown_keys:
+                raise ValidationError(f"Invalid fields: {unknown_keys}")
+        return data
+
+
+class YamlOrJsonField(serializers.JSONField):
+    def to_internal_value(self, data):
+        if isinstance(data, str):
+            try:
+                data = yaml.safe_load(data)
+            except yaml.YAMLError as exc:
+                raise serializers.ValidationError("Invalid YAML format") from exc
+        return super().to_internal_value(data)

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

@@ -1,19 +1,7 @@
 from drf_spectacular.utils import extend_schema_field
 from rest_framework_json_api import serializers
-from rest_framework_json_api.serializers import ValidationError
 
-
-class BaseValidateSerializer(serializers.Serializer):
-    def validate(self, data):
-        if hasattr(self, "initial_data"):
-            initial_data = set(self.initial_data.keys()) - {"id", "type"}
-            unknown_keys = initial_data - set(self.fields.keys())
-            if unknown_keys:
-                raise ValidationError(f"Invalid fields: {unknown_keys}")
-        return data
-
-
-# Integrations
+from api.v1.serializer_utils.base import BaseValidateSerializer
 
 
 class S3ConfigSerializer(BaseValidateSerializer):

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

@@ -0,0 +1,21 @@
+from drf_spectacular.utils import extend_schema_field
+
+from api.v1.serializer_utils.base import YamlOrJsonField
+
+from prowler.lib.mutelist.mutelist import mutelist_schema
+
+
+@extend_schema_field(
+    {
+        "oneOf": [
+            {
+                "type": "object",
+                "title": "Mutelist",
+                "properties": {"Mutelist": mutelist_schema},
+                "additionalProperties": False,
+            },
+        ]
+    }
+)
+class ProcessorConfigField(YamlOrJsonField):
+    pass

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

@@ -7,20 +7,23 @@ from django.contrib.auth.models import update_last_login
 from django.contrib.auth.password_validation import validate_password
 from drf_spectacular.utils import extend_schema_field
 from jwt.exceptions import InvalidKeyError
+from rest_framework.validators import UniqueTogetherValidator
 from rest_framework_json_api import serializers
+from rest_framework_json_api.relations import SerializerMethodResourceRelatedField
 from rest_framework_json_api.serializers import ValidationError
 from rest_framework_simplejwt.exceptions import TokenError
 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,
+    Processor,
     Provider,
     ProviderGroup,
     ProviderGroupMembership,
@@ -29,8 +32,10 @@ from api.models import (
     ResourceTag,
     Role,
     RoleProviderGroupRelationship,
+    SAMLConfiguration,
     Scan,
     StateChoices,
+    StatusChoices,
     Task,
     User,
     UserRoleRelationship,
@@ -42,6 +47,9 @@ from api.v1.serializer_utils.integrations import (
     IntegrationCredentialField,
     S3ConfigSerializer,
 )
+from api.v1.serializer_utils.processors import ProcessorConfigField
+from api.v1.serializer_utils.providers import ProviderSecretField
+from prowler.lib.mutelist.mutelist import Mutelist
 
 # Tokens
 
@@ -127,6 +135,12 @@ class TokenSerializer(BaseTokenSerializer):
 
 class TokenSocialLoginSerializer(BaseTokenSerializer):
     email = serializers.EmailField(write_only=True)
+    tenant_id = serializers.UUIDField(
+        write_only=True,
+        required=False,
+        help_text="If not provided, the tenant ID of the first membership that was added"
+        " to the user will be used.",
+    )
 
     # Output tokens
     refresh = serializers.CharField(read_only=True)
@@ -848,6 +862,7 @@ class ScanSerializer(RLSSerializer):
             "completed_at",
             "scheduled_at",
             "next_scan_at",
+            "processor",
             "url",
         ]
 
@@ -959,6 +974,15 @@ 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
@@ -976,8 +1000,12 @@ class ResourceSerializer(RLSSerializer):
 
     tags = serializers.SerializerMethodField()
     type_ = serializers.CharField(read_only=True)
+    failed_findings_count = serializers.IntegerField(read_only=True)
 
-    findings = serializers.ResourceRelatedField(many=True, read_only=True)
+    findings = SerializerMethodResourceRelatedField(
+        many=True,
+        read_only=True,
+    )
 
     class Meta:
         model = Resource
@@ -993,6 +1021,7 @@ class ResourceSerializer(RLSSerializer):
             "tags",
             "provider",
             "findings",
+            "failed_findings_count",
             "url",
         ]
         extra_kwargs = {
@@ -1002,8 +1031,8 @@ class ResourceSerializer(RLSSerializer):
         }
 
     included_serializers = {
-        "findings": "api.v1.serializers.FindingSerializer",
-        "provider": "api.v1.serializers.ProviderSerializer",
+        "findings": "api.v1.serializers.FindingIncludeSerializer",
+        "provider": "api.v1.serializers.ProviderIncludeSerializer",
     }
 
     @extend_schema_field(
@@ -1014,6 +1043,10 @@ class ResourceSerializer(RLSSerializer):
         }
     )
     def get_tags(self, obj):
+        # Use prefetched tags if available to avoid N+1 queries
+        if hasattr(obj, "prefetched_tags"):
+            return {tag.key: tag.value for tag in obj.prefetched_tags}
+        # Fallback to the original method if prefetch is not available
         return obj.get_tags(self.context.get("tenant_id"))
 
     def get_fields(self):
@@ -1023,10 +1056,17 @@ class ResourceSerializer(RLSSerializer):
         fields["type"] = type_
         return fields
 
+    def get_findings(self, obj):
+        return (
+            obj.latest_findings
+            if hasattr(obj, "latest_findings")
+            else obj.findings.all()
+        )
+
 
 class ResourceIncludeSerializer(RLSSerializer):
     """
-    Serializer for the Resource model.
+    Serializer for the included Resource model.
     """
 
     tags = serializers.SerializerMethodField()
@@ -1059,6 +1099,10 @@ class ResourceIncludeSerializer(RLSSerializer):
         }
     )
     def get_tags(self, obj):
+        # Use prefetched tags if available to avoid N+1 queries
+        if hasattr(obj, "prefetched_tags"):
+            return {tag.key: tag.value for tag in obj.prefetched_tags}
+        # Fallback to the original method if prefetch is not available
         return obj.get_tags(self.context.get("tenant_id"))
 
     def get_fields(self):
@@ -1069,6 +1113,17 @@ class ResourceIncludeSerializer(RLSSerializer):
         return fields
 
 
+class ResourceMetadataSerializer(serializers.Serializer):
+    services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
+    regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
+    types = serializers.ListField(child=serializers.CharField(), allow_empty=True)
+    # Temporarily disabled until we implement tag filtering in the UI
+    # tags = serializers.JSONField(help_text="Tags are described as key-value pairs.")
+
+    class Meta:
+        resource_name = "resources-metadata"
+
+
 class FindingSerializer(RLSSerializer):
     """
     Serializer for the Finding model.
@@ -1092,6 +1147,7 @@ class FindingSerializer(RLSSerializer):
             "updated_at",
             "first_seen_at",
             "muted",
+            "muted_reason",
             "url",
             # Relationships
             "scan",
@@ -1104,6 +1160,28 @@ class FindingSerializer(RLSSerializer):
     }
 
 
+class FindingIncludeSerializer(RLSSerializer):
+    """
+    Serializer for the include Finding model.
+    """
+
+    class Meta:
+        model = Finding
+        fields = [
+            "id",
+            "uid",
+            "status",
+            "severity",
+            "check_id",
+            "check_metadata",
+            "inserted_at",
+            "updated_at",
+            "first_seen_at",
+            "muted",
+            "muted_reason",
+        ]
+
+
 # To be removed when the related endpoint is removed as well
 class FindingDynamicFilterSerializer(serializers.Serializer):
     services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
@@ -1141,12 +1219,16 @@ 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}"}
@@ -1180,6 +1262,17 @@ 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(required=False)
+    password = serializers.CharField(required=False)
+
+    class Meta:
+        resource_name = "provider-secrets"
+
+
 class GCPProviderSecret(serializers.Serializer):
     client_id = serializers.CharField()
     client_secret = serializers.CharField()
@@ -1189,6 +1282,13 @@ 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()
 
@@ -1211,141 +1311,6 @@ 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.
@@ -1410,12 +1375,13 @@ class ProviderSecretUpdateSerializer(BaseWriteProviderSecretSerializer):
             "inserted_at": {"read_only": True},
             "updated_at": {"read_only": True},
             "provider": {"read_only": True},
-            "secret_type": {"read_only": True},
+            "secret_type": {"required": False},
         }
 
     def validate(self, attrs):
         provider = self.instance.provider
-        secret_type = self.instance.secret_type
+        # To allow updating a secret with the same type without making the `secret_type` mandatory
+        secret_type = attrs.get("secret_type") or self.instance.secret_type
         secret = attrs.get("secret")
 
         validated_attrs = super().validate(attrs)
@@ -1782,130 +1748,63 @@ 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 Meta:
+    class JSONAPIMeta:
         resource_name = "compliance-overviews-metadata"
 
 
@@ -2231,3 +2130,278 @@ class IntegrationUpdateSerializer(BaseWriteIntegrationSerializer):
             IntegrationProviderRelationship.objects.bulk_create(new_relationships)
 
         return super().update(instance, validated_data)
+
+
+# Processors
+
+
+class ProcessorSerializer(RLSSerializer):
+    """
+    Serializer for the Processor model.
+    """
+
+    configuration = ProcessorConfigField()
+
+    class Meta:
+        model = Processor
+        fields = [
+            "id",
+            "inserted_at",
+            "updated_at",
+            "processor_type",
+            "configuration",
+            "url",
+        ]
+
+
+class ProcessorCreateSerializer(RLSSerializer, BaseWriteSerializer):
+    configuration = ProcessorConfigField(required=True)
+
+    class Meta:
+        model = Processor
+        fields = [
+            "inserted_at",
+            "updated_at",
+            "processor_type",
+            "configuration",
+        ]
+        extra_kwargs = {
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+        }
+        validators = [
+            UniqueTogetherValidator(
+                queryset=Processor.objects.all(),
+                fields=["processor_type"],
+                message="A processor with the same type already exists.",
+            )
+        ]
+
+    def validate(self, attrs):
+        validated_attrs = super().validate(attrs)
+        self.validate_processor_data(attrs)
+        return validated_attrs
+
+    def validate_processor_data(self, attrs):
+        processor_type = attrs.get("processor_type")
+        configuration = attrs.get("configuration")
+        if processor_type == "mutelist":
+            self.validate_mutelist_configuration(configuration)
+
+    def validate_mutelist_configuration(self, configuration):
+        if not isinstance(configuration, dict):
+            raise serializers.ValidationError("Invalid Mutelist configuration.")
+
+        mutelist_configuration = configuration.get("Mutelist", {})
+
+        if not mutelist_configuration:
+            raise serializers.ValidationError(
+                "Invalid Mutelist configuration: 'Mutelist' is a required property."
+            )
+
+        try:
+            Mutelist.validate_mutelist(mutelist_configuration, raise_on_exception=True)
+            return
+        except Exception as error:
+            raise serializers.ValidationError(
+                f"Invalid Mutelist configuration: {error}"
+            )
+
+
+class ProcessorUpdateSerializer(BaseWriteSerializer):
+    configuration = ProcessorConfigField(required=True)
+
+    class Meta:
+        model = Processor
+        fields = [
+            "inserted_at",
+            "updated_at",
+            "configuration",
+        ]
+        extra_kwargs = {
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+        }
+
+    def validate(self, attrs):
+        validated_attrs = super().validate(attrs)
+        self.validate_processor_data(attrs)
+        return validated_attrs
+
+    def validate_processor_data(self, attrs):
+        processor_type = self.instance.processor_type
+        configuration = attrs.get("configuration")
+        if processor_type == "mutelist":
+            self.validate_mutelist_configuration(configuration)
+
+    def validate_mutelist_configuration(self, configuration):
+        if not isinstance(configuration, dict):
+            raise serializers.ValidationError("Invalid Mutelist configuration.")
+
+        mutelist_configuration = configuration.get("Mutelist", {})
+
+        if not mutelist_configuration:
+            raise serializers.ValidationError(
+                "Invalid Mutelist configuration: 'Mutelist' is a required property."
+            )
+
+        try:
+            Mutelist.validate_mutelist(mutelist_configuration, raise_on_exception=True)
+            return
+        except Exception as error:
+            raise serializers.ValidationError(
+                f"Invalid Mutelist configuration: {error}"
+            )
+
+
+# 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

@@ -1,9 +1,11 @@
+from allauth.socialaccount.providers.saml.views import ACSView, MetadataView, SLSView
 from django.urls import include, path
 from drf_spectacular.views import SpectacularRedocView
 from rest_framework_nested import routers
 
 from api.v1.views import (
     ComplianceOverviewViewSet,
+    CustomSAMLLoginView,
     CustomTokenObtainView,
     CustomTokenRefreshView,
     CustomTokenSwitchTenantView,
@@ -13,8 +15,10 @@ from api.v1.views import (
     IntegrationViewSet,
     InvitationAcceptViewSet,
     InvitationViewSet,
+    LighthouseConfigViewSet,
     MembershipViewSet,
     OverviewViewSet,
+    ProcessorViewSet,
     ProviderGroupProvidersRelationshipView,
     ProviderGroupViewSet,
     ProviderSecretViewSet,
@@ -22,10 +26,14 @@ from api.v1.views import (
     ResourceViewSet,
     RoleProviderGroupRelationshipView,
     RoleViewSet,
+    SAMLConfigurationViewSet,
+    SAMLInitiateAPIView,
+    SAMLTokenValidateView,
     ScanViewSet,
     ScheduleViewSet,
     SchemaView,
     TaskViewSet,
+    TenantFinishACSView,
     TenantMembersViewSet,
     TenantViewSet,
     UserRoleRelationshipView,
@@ -49,6 +57,13 @@ 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"processors", ProcessorViewSet, basename="processor")
+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 +127,36 @@ urlpatterns = [
         ),
         name="provider_group-providers-relationship",
     ),
+    # API endpoint to start SAML SSO flow
+    path(
+        "auth/saml/initiate/", SAMLInitiateAPIView.as_view(), name="api_saml_initiate"
+    ),
+    path(
+        "accounts/saml/<organization_slug>/login/",
+        CustomSAMLLoginView.as_view(),
+        name="saml_login",
+    ),
+    path(
+        "accounts/saml/<organization_slug>/acs/",
+        ACSView.as_view(),
+        name="saml_acs",
+    ),
+    path(
+        "accounts/saml/<organization_slug>/acs/finish/",
+        TenantFinishACSView.as_view(),
+        name="saml_finish_acs",
+    ),
+    path(
+        "accounts/saml/<organization_slug>/sls/",
+        SLSView.as_view(),
+        name="saml_sls",
+    ),
+    path(
+        "accounts/saml/<organization_slug>/metadata/",
+        MetadataView.as_view(),
+        name="saml_metadata",
+    ),
+    path("tokens/saml", SAMLTokenValidateView.as_view(), name="token-saml"),
     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/api/validators.py

@@ -1,3 +1,5 @@
+import string
+
 from django.core.exceptions import ValidationError
 from django.utils.translation import gettext as _
 
@@ -20,3 +22,89 @@ class MaximumLengthValidator:
         return _(
             f"Your password must contain no more than {self.max_length} characters."
         )
+
+
+class SpecialCharactersValidator:
+    def __init__(self, special_characters=None, min_special_characters=1):
+        # Use string.punctuation if no custom characters provided
+        self.special_characters = special_characters or string.punctuation
+        self.min_special_characters = min_special_characters
+
+    def validate(self, password, user=None):
+        if (
+            sum(1 for char in password if char in self.special_characters)
+            < self.min_special_characters
+        ):
+            raise ValidationError(
+                _("This password must contain at least one special character."),
+                code="password_no_special_characters",
+                params={
+                    "special_characters": self.special_characters,
+                    "min_special_characters": self.min_special_characters,
+                },
+            )
+
+    def get_help_text(self):
+        return _(
+            f"Your password must contain at least one special character from: {self.special_characters}"
+        )
+
+
+class UppercaseValidator:
+    def __init__(self, min_uppercase=1):
+        self.min_uppercase = min_uppercase
+
+    def validate(self, password, user=None):
+        if sum(1 for char in password if char.isupper()) < self.min_uppercase:
+            raise ValidationError(
+                _(
+                    "This password must contain at least %(min_uppercase)d uppercase letter."
+                ),
+                code="password_no_uppercase_letters",
+                params={"min_uppercase": self.min_uppercase},
+            )
+
+    def get_help_text(self):
+        return _(
+            f"Your password must contain at least {self.min_uppercase} uppercase letter."
+        )
+
+
+class LowercaseValidator:
+    def __init__(self, min_lowercase=1):
+        self.min_lowercase = min_lowercase
+
+    def validate(self, password, user=None):
+        if sum(1 for char in password if char.islower()) < self.min_lowercase:
+            raise ValidationError(
+                _(
+                    "This password must contain at least %(min_lowercase)d lowercase letter."
+                ),
+                code="password_no_lowercase_letters",
+                params={"min_lowercase": self.min_lowercase},
+            )
+
+    def get_help_text(self):
+        return _(
+            f"Your password must contain at least {self.min_lowercase} lowercase letter."
+        )
+
+
+class NumericValidator:
+    def __init__(self, min_numeric=1):
+        self.min_numeric = min_numeric
+
+    def validate(self, password, user=None):
+        if sum(1 for char in password if char.isdigit()) < self.min_numeric:
+            raise ValidationError(
+                _(
+                    "This password must contain at least %(min_numeric)d numeric character."
+                ),
+                code="password_no_numeric_characters",
+                params={"min_numeric": self.min_numeric},
+            )
+
+    def get_help_text(self):
+        return _(
+            f"Your password must contain at least {self.min_numeric} numeric character."
+        )

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")

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

@@ -10,6 +10,8 @@ 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")
+USE_X_FORWARDED_HOST = True
 
 # Application definition
 
@@ -26,16 +28,19 @@ 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 +116,7 @@ SPECTACULAR_SETTINGS = {
     "PREPROCESSING_HOOKS": [
         "drf_spectacular_jsonapi.hooks.fix_nested_path_parameters",
     ],
+    "TITLE": "API Reference - Prowler",
 }
 
 WSGI_APPLICATION = "config.wsgi.application"
@@ -153,6 +159,30 @@ AUTH_PASSWORD_VALIDATORS = [
     {
         "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
     },
+    {
+        "NAME": "api.validators.SpecialCharactersValidator",
+        "OPTIONS": {
+            "min_special_characters": 1,
+        },
+    },
+    {
+        "NAME": "api.validators.UppercaseValidator",
+        "OPTIONS": {
+            "min_uppercase": 1,
+        },
+    },
+    {
+        "NAME": "api.validators.LowercaseValidator",
+        "OPTIONS": {
+            "min_lowercase": 1,
+        },
+    },
+    {
+        "NAME": "api.validators.NumericValidator",
+        "OPTIONS": {
+            "min_numeric": 1,
+        },
+    },
 ]
 
 SIMPLE_JWT = {
@@ -243,3 +273,7 @@ X_FRAME_OPTIONS = "DENY"
 SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
 
 DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)
+
+# SAML requirement
+CSRF_COOKIE_SECURE = True
+SESSION_COOKIE_SECURE = True

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

@@ -4,6 +4,7 @@ from config.env import env
 IGNORED_EXCEPTIONS = [
     # Provider is not connected due to credentials errors
     "is not connected",
+    "ProviderConnectionError",
     # Authentication Errors from AWS
     "InvalidToken",
     "AccessDeniedException",
@@ -12,9 +13,11 @@ 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
+    "RequestLimitExceeded",  # For now, we don't want to log the RequestLimitExceeded errors
     "ThrottlingException",
     "Rate exceeded",
     "SubscriptionRequiredException",
@@ -33,7 +36,16 @@ IGNORED_EXCEPTIONS = [
     "ValidationException",
     "AWSSecretAccessKeyInvalidError",
     "InvalidAction",
-    "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.
+    "InvalidRequestException",
+    "RequestExpired",
+    "ConnectionClosedError",
+    "MaxRetryError",
+    "AWSAccessKeyIDInvalidError",
+    "AWSSessionTokenExpiredError",
+    "EndpointConnectionError",  # AWS Service is not available in a region
+    # 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.
+    "Pool is closed",
     # Authentication Errors from GCP
     "ClientAuthenticationError",
     "AuthorizationFailed",
@@ -41,6 +53,8 @@ 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",
@@ -49,19 +63,18 @@ IGNORED_EXCEPTIONS = [
     "AzureNotValidClientIdError",
     "AzureNotValidClientSecretError",
     "AzureNotValidTenantIdError",
+    "AzureInvalidProviderIdError",
     "AzureTenantIdAndClientSecretNotBelongingToClientIdError",
     "AzureTenantIdAndClientIdNotBelongingToClientSecretError",
     "AzureClientIdAndClientSecretNotBelongingToTenantIdError",
     "AzureHTTPResponseError",
     "Error with credentials provided",
-    # AWS Service is not available in a region
-    "EndpointConnectionError",
 ]
 
 
 def before_send(event, hint):
     """
-    before_send handles the Sentry events in order to sent them or not
+    before_send handles the Sentry events in order to send them or not
     """
     # Ignore logs with the ignored_exceptions
     # https://docs.python.org/3/library/logging.html#logrecord-objects
@@ -69,9 +82,16 @@ 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
 
 
@@ -87,4 +107,6 @@ sentry_sdk.init(
         # possible.
         "continuous_profiling_auto_start": True,
     },
+    attach_stacktrace=True,
+    ignore_errors=IGNORED_EXCEPTIONS,
 )

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

@@ -11,8 +11,7 @@ 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 +24,20 @@ 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"
+
+
+# def inline(pem: str) -> str:
+#     return "".join(
+#         line.strip()
+#         for line in pem.splitlines()
+#         if "CERTIFICATE" not in line and "KEY" not in line
+#     )
+
+
+# # SAML keys (TODO: Validate certificates)
+# SAML_PUBLIC_CERT = inline(env("SAML_PUBLIC_CERT", default=""))
+# SAML_PRIVATE_KEY = inline(env("SAML_PRIVATE_KEY", default=""))
+
 SOCIALACCOUNT_PROVIDERS = {
     "google": {
         "APP": {
@@ -50,4 +63,20 @@ SOCIALACCOUNT_PROVIDERS = {
             "read:org",
         ],
     },
+    "saml": {
+        "use_nameid_for_email": True,
+        "sp": {
+            "entity_id": "urn:prowler.com:sp",
+        },
+        "advanced": {
+            # TODO: Validate certificates
+            # "x509cert": SAML_PUBLIC_CERT,
+            # "private_key": SAML_PRIVATE_KEY,
+            # "authn_request_signed": True,
+            # "want_message_signed": True,
+            # "want_assertion_signed": True,
+            "reject_idp_initiated_sso": False,
+            "name_id_format": "urn:oasis:names:tc:SAML:1.1:nameid-format:emailAddress",
+        },
+    },
 }

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
@@ -10,24 +11,32 @@ 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,
+    Processor,
     Provider,
     ProviderGroup,
     ProviderSecret,
     Resource,
     ResourceTag,
+    ResourceTagMapping,
     Role,
+    SAMLConfiguration,
+    SAMLDomainIndex,
     Scan,
     ScanSummary,
     StateChoices,
+    StatusChoices,
     Task,
     User,
     UserRoleRelationship,
@@ -37,12 +46,19 @@ from api.v1.serializers import TokenSerializer
 from prowler.lib.check.models import Severity
 from prowler.lib.outputs.finding import Status
 
+TODAY = str(datetime.today().date())
 API_JSON_CONTENT_TYPE = "application/vnd.api+json"
 NO_TENANT_HTTP_STATUS = status.HTTP_401_UNAUTHORIZED
 TEST_USER = "dev@prowler.com"
 TEST_PASSWORD = "testing_psswd"
 
 
+def today_after_n_days(n_days: int) -> str:
+    return datetime.strftime(
+        datetime.today().date() + timedelta(days=n_days), "%Y-%m-%d"
+    )
+
+
 @pytest.fixture(scope="module")
 def enforce_test_user_db_connection(django_db_setup, django_db_blocker):
     """Ensure tests use the test user for database connections."""
@@ -374,8 +390,27 @@ def providers_fixture(tenants_fixture):
         tenant_id=tenant.id,
         scanner_args={"key1": "value1", "key2": {"key21": "value21"}},
     )
+    provider6 = Provider.objects.create(
+        provider="m365",
+        uid="m365.test.com",
+        alias="m365_testing",
+        tenant_id=tenant.id,
+    )
 
-    return provider1, provider2, provider3, provider4, provider5
+    return provider1, provider2, provider3, provider4, provider5, provider6
+
+
+@pytest.fixture
+def processor_fixture(tenants_fixture):
+    tenant, *_ = tenants_fixture
+    processor = Processor.objects.create(
+        tenant_id=tenant.id,
+        processor_type="mutelist",
+        configuration="Mutelist:\n  Accounts:\n    *:\n      Checks:\n        iam_user_hardware_mfa_enabled:\n         "
+        " Regions:\n            - *\n          Resources:\n            - *",
+    )
+
+    return processor
 
 
 @pytest.fixture
@@ -627,6 +662,7 @@ def findings_fixture(scans_fixture, resources_fixture):
         check_metadata={
             "CheckId": "test_check_id",
             "Description": "test description apple sauce",
+            "servicename": "ec2",
         },
         first_seen_at="2024-01-02T00:00:00Z",
     )
@@ -653,6 +689,7 @@ def findings_fixture(scans_fixture, resources_fixture):
         check_metadata={
             "CheckId": "test_check_id",
             "Description": "test description orange juice",
+            "servicename": "s3",
         },
         first_seen_at="2024-01-02T00:00:00Z",
         muted=True,
@@ -776,6 +813,131 @@ 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]:
@@ -920,6 +1082,190 @@ 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(scope="function")
+def latest_scan_resource(authenticated_client, providers_fixture):
+    provider = providers_fixture[0]
+    tenant_id = str(providers_fixture[0].tenant_id)
+    scan = Scan.objects.create(
+        name="latest completed scan for resource",
+        provider=provider,
+        trigger=Scan.TriggerChoices.MANUAL,
+        state=StateChoices.COMPLETED,
+        tenant_id=tenant_id,
+    )
+    resource = Resource.objects.create(
+        tenant_id=tenant_id,
+        provider=provider,
+        uid="latest_resource_uid",
+        name="Latest Resource",
+        region="us-east-1",
+        service="ec2",
+        type="instance",
+        metadata='{"test": "metadata"}',
+        details='{"test": "details"}',
+    )
+
+    resource_tag = ResourceTag.objects.create(
+        tenant_id=tenant_id,
+        key="environment",
+        value="test",
+    )
+    ResourceTagMapping.objects.create(
+        tenant_id=tenant_id,
+        resource=resource,
+        tag=resource_tag,
+    )
+
+    finding = Finding.objects.create(
+        tenant_id=tenant_id,
+        uid="test_finding_uid_latest",
+        scan=scan,
+        delta="new",
+        status=Status.FAIL,
+        status_extended="test status extended ",
+        impact=Severity.critical,
+        impact_extended="test impact extended",
+        severity=Severity.critical,
+        raw_result={
+            "status": Status.FAIL,
+            "impact": Severity.critical,
+            "severity": Severity.critical,
+        },
+        tags={"test": "latest"},
+        check_id="test_check_id_latest",
+        check_metadata={
+            "CheckId": "test_check_id_latest",
+            "Description": "test description latest",
+        },
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding.add_resources([resource])
+
+    backfill_resource_scan_summaries(tenant_id, str(scan.id))
+    return resource
+
+
+@pytest.fixture
+def saml_setup(tenants_fixture):
+    tenant_id = tenants_fixture[0].id
+    domain = "prowler.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/beat.py

@@ -2,10 +2,10 @@ import json
 from datetime import datetime, timedelta, timezone
 
 from django_celery_beat.models import IntervalSchedule, PeriodicTask
-from rest_framework_json_api.serializers import ValidationError
 from tasks.tasks import perform_scheduled_scan_task
 
 from api.db_utils import rls_transaction
+from api.exceptions import ConflictException
 from api.models import Provider, Scan, StateChoices
 
 
@@ -24,15 +24,9 @@ def schedule_provider_scan(provider_instance: Provider):
     if PeriodicTask.objects.filter(
         interval=schedule, name=task_name, task="scan-perform-scheduled"
     ).exists():
-        raise ValidationError(
-            [
-                {
-                    "detail": "There is already a scheduled scan for this provider.",
-                    "status": 400,
-                    "source": {"pointer": "/data/attributes/provider_id"},
-                    "code": "invalid",
-                }
-            ]
+        raise ConflictException(
+            detail="There is already a scheduled scan for this provider.",
+            pointer="/data/attributes/provider_id",
         )
 
     with rls_transaction(tenant_id):

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/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("cis_"), M365CIS),
+        (lambda name: name == "prowler_threatscore_m365", ProwlerThreatScoreM365),
+        (lambda name: name.startswith("iso27001_"), M365ISO27001),
+    ],
+}
+
+
 # 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

@@ -6,26 +6,29 @@ from datetime import datetime, timezone
 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 django.db.models import Case, Count, IntegerField, OuterRef, Subquery, 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.exceptions import ProviderConnectionError
 from api.models import (
-    ComplianceOverview,
+    ComplianceRequirementOverview,
     Finding,
+    Processor,
     Provider,
     Resource,
+    ResourceScanSummary,
     ResourceTag,
     Scan,
     ScanSummary,
     StateChoices,
 )
 from api.models import StatusChoices as FindingStatus
-from api.utils import initialize_prowler_provider
+from api.utils import initialize_prowler_provider, return_prowler_provider
 from api.v1.serializers import ScanTaskSerializer
 from prowler.lib.outputs.finding import Finding as ProwlerFinding
 from prowler.lib.scan.scan import Scan as ProwlerScan
@@ -118,10 +121,11 @@ 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)
@@ -130,14 +134,28 @@ def perform_prowler_scan(
         scan_instance.started_at = datetime.now(tz=timezone.utc)
         scan_instance.save()
 
+    # Find the mutelist processor if it exists
+    with rls_transaction(tenant_id):
+        try:
+            mutelist_processor = Processor.objects.get(
+                tenant_id=tenant_id, processor_type=Processor.ProcessorChoices.MUTELIST
+            )
+        except Processor.DoesNotExist:
+            mutelist_processor = None
+        except Exception as e:
+            logger.error(f"Error processing mutelist rules: {e}")
+            mutelist_processor = None
+
     try:
         with rls_transaction(tenant_id):
             try:
-                prowler_provider = initialize_prowler_provider(provider_instance)
+                prowler_provider = initialize_prowler_provider(
+                    provider_instance, mutelist_processor
+                )
                 provider_instance.connected = True
             except Exception as e:
                 provider_instance.connected = False
-                raise ValueError(
+                exc = ProviderConnectionError(
                     f"Provider {provider_instance.provider} is not connected: {e}"
                 )
             finally:
@@ -146,6 +164,12 @@ 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 = {}
@@ -266,6 +290,9 @@ def perform_prowler_scan(
                     if not last_first_seen_at:
                         last_first_seen_at = datetime.now(tz=timezone.utc)
 
+                    # If the finding is muted at this time the reason must be the configured Mutelist
+                    muted_reason = "Muted by mutelist" if finding.muted else None
+
                     # Create the finding
                     finding_instance = Finding.objects.create(
                         tenant_id=tenant_id,
@@ -281,19 +308,20 @@ def perform_prowler_scan(
                         scan=scan_instance,
                         first_seen_at=last_first_seen_at,
                         muted=finding.muted,
+                        muted_reason=muted_reason,
                         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):
@@ -314,66 +342,33 @@ 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
 
@@ -381,12 +376,16 @@ def perform_prowler_scan(
 def aggregate_findings(tenant_id: str, scan_id: str):
     """
     Aggregates findings for a given scan and stores the results in the ScanSummary table.
+    Also updates the failed_findings_count for each resource based on the latest findings.
 
     This function retrieves all findings associated with a given `scan_id` and calculates various
     metrics such as counts of failed, passed, and muted findings, as well as their deltas (new,
     changed, unchanged). The results are grouped by `check_id`, `service`, `severity`, and `region`.
     These aggregated metrics are then stored in the `ScanSummary` table.
 
+    Additionally, it updates the failed_findings_count field for each resource based on the most
+    recent findings for each finding.uid.
+
     Args:
         tenant_id (str): The ID of the tenant to which the scan belongs.
         scan_id (str): The ID of the scan for which findings need to be aggregated.
@@ -406,6 +405,8 @@ def aggregate_findings(tenant_id: str, scan_id: str):
         - muted_new: Muted findings with a delta of 'new'.
         - muted_changed: Muted findings with a delta of 'changed'.
     """
+    _update_resource_failed_findings_count(tenant_id, scan_id)
+
     with rls_transaction(tenant_id):
         findings = Finding.objects.filter(tenant_id=tenant_id, scan_id=scan_id)
 
@@ -528,3 +529,161 @@ def aggregate_findings(tenant_id: str, scan_id: str):
             for agg in aggregation
         }
         ScanSummary.objects.bulk_create(scan_aggregations, batch_size=3000)
+
+
+def _update_resource_failed_findings_count(tenant_id: str, scan_id: str):
+    """
+    Update the failed_findings_count field for resources based on the latest findings.
+
+    This function calculates the number of failed findings for each resource by:
+    1. Getting the latest finding for each finding.uid
+    2. Counting failed findings per resource
+    3. Updating the failed_findings_count field for each resource
+
+    Args:
+        tenant_id (str): The ID of the tenant to which the scan belongs.
+        scan_id (str): The ID of the scan for which to update resource counts.
+    """
+
+    with rls_transaction(tenant_id):
+        scan = Scan.objects.get(pk=scan_id)
+        provider_id = scan.provider_id
+
+        resources = list(
+            Resource.all_objects.filter(tenant_id=tenant_id, provider_id=provider_id)
+        )
+
+    # For each resource, calculate failed findings count based on latest findings
+    for resource in resources:
+        with rls_transaction(tenant_id):
+            # Get the latest finding for each finding.uid that affects this resource
+            latest_findings_subquery = (
+                Finding.all_objects.filter(
+                    tenant_id=tenant_id, uid=OuterRef("uid"), resources=resource
+                )
+                .order_by("-inserted_at")
+                .values("id")[:1]
+            )
+
+            # Count failed findings from the latest findings
+            failed_count = Finding.all_objects.filter(
+                tenant_id=tenant_id,
+                resources=resource,
+                id__in=Subquery(latest_findings_subquery),
+                status=FindingStatus.FAIL,
+                muted=False,
+            ).count()
+
+            resource.failed_findings_count = failed_count
+            resource.save(update_fields=["failed_findings_count"])
+
+
+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 = return_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