Update lighthouse serializer

Co-authored-by: Pablo Lara <larabjj@gmail.com>

.env

@@ -3,8 +3,8 @@
 # For production, it is recommended to use a secure method to store these variables and change the default secret keys.
 
 #### Prowler UI Configuration ####
-PROWLER_UI_VERSION="latest"
-SITE_URL=http://localhost:3000
+PROWLER_UI_VERSION="stable"
+AUTH_URL=http://localhost:3000
 API_BASE_URL=http://prowler-api:8080/api/v1
 NEXT_PUBLIC_API_DOCS_URL=http://prowler-api:8080/api/v1/docs
 AUTH_TRUST_HOST=true
@@ -30,6 +30,30 @@ VALKEY_HOST=valkey
 VALKEY_PORT=6379
 VALKEY_DB=0
 
+# API scan settings
+
+# The path to the directory where scan output should be stored
+DJANGO_TMP_OUTPUT_DIRECTORY="/tmp/prowler_api_output"
+
+# The maximum number of findings to process in a single batch
+DJANGO_FINDINGS_BATCH_SIZE=1000
+
+# The AWS access key to be used when uploading scan output to an S3 bucket
+# If left empty, default AWS credentials resolution behavior will be used
+DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID=""
+
+# The AWS secret key to be used when uploading scan output to an S3 bucket
+DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY=""
+
+# An optional AWS session token
+DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN=""
+
+# The AWS region where your S3 bucket is located (e.g., "us-east-1")
+DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION=""
+
+# The name of the S3 bucket where scan output should be stored
+DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET=""
+
 # Django settings
 DJANGO_ALLOWED_HOSTS=localhost,127.0.0.1,prowler-api
 DJANGO_BIND_ADDRESS=0.0.0.0
@@ -92,3 +116,20 @@ jQIDAQAB
 # openssl rand -base64 32
 DJANGO_SECRETS_ENCRYPTION_KEY="oE/ltOhp/n1TdbHjVmzcjDPLcLA41CVI/4Rk+UB5ESc="
 DJANGO_BROKER_VISIBILITY_TIMEOUT=86400
+DJANGO_SENTRY_DSN=
+
+# Sentry settings
+SENTRY_ENVIRONMENT=local
+SENTRY_RELEASE=local
+
+#### Prowler release version ####
+NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.6.0
+
+# Social login credentials
+SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
+SOCIAL_GOOGLE_OAUTH_CLIENT_ID=""
+SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET=""
+
+SOCIAL_GITHUB_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/github"
+SOCIAL_GITHUB_OAUTH_CLIENT_ID=""
+SOCIAL_GITHUB_OAUTH_CLIENT_SECRET=""

.github/dependabot.yml

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

.github/labeler.yml

@@ -92,3 +92,13 @@ component/api:
 component/ui:
   - changed-files:
       - any-glob-to-any-file: "ui/**"
+
+compliance:
+  - changed-files:
+      - any-glob-to-any-file: "prowler/compliance/**"
+      - any-glob-to-any-file: "prowler/lib/outputs/compliance/**"
+      - any-glob-to-any-file: "tests/lib/outputs/compliance/**"
+
+review-django-migrations:
+  - changed-files:
+      - any-glob-to-any-file: "api/src/backend/api/migrations/**"

.github/pull_request_template.md

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

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

@@ -61,33 +61,40 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set short git commit SHA
+        id: vars
+        run: |
+          shortSha=$(git rev-parse --short ${{ github.sha }})
+          echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           # Set push: false for testing
           push: true
           tags: |
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.LATEST_TAG }}
+            ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.SHORT_SHA }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
           push: true
@@ -96,3 +103,12 @@ jobs:
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.STABLE_TAG }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
+
+      - name: Trigger deployment
+        if: github.event_name == 'push'
+        uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
+        with:
+          token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+          repository: ${{ secrets.CLOUD_DISPATCH }}
+          event-type: prowler-api-deploy
+          client-payload: '{"sha": "${{ github.sha }}", "short_sha": "${{ env.SHORT_SHA }}"}'

.github/workflows/api-codeql.yml

@@ -44,16 +44,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/api-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
       with:
         category: "/language:${{matrix.language}}"

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

@@ -6,6 +6,7 @@ on:
       - "master"
       - "v5.*"
     paths:
+      - ".github/workflows/api-pull-request.yml"
       - "api/**"
   pull_request:
     branches:
@@ -14,7 +15,6 @@ on:
     paths:
       - "api/**"
 
-
 env:
   POSTGRES_HOST: localhost
   POSTGRES_PORT: 5432
@@ -26,7 +26,8 @@ env:
   VALKEY_HOST: localhost
   VALKEY_PORT: 6379
   VALKEY_DB: 0
-
+  API_WORKING_DIR: ./api
+  IMAGE_NAME: prowler-api
 
 jobs:
   test:
@@ -70,11 +71,11 @@ jobs:
           --health-retries 5
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@v45
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files: api/**
           files_ignore: |
@@ -84,16 +85,30 @@ jobs:
             api/README.md
             api/mkdocs.yml
 
+      - 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
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
           python -m pip install --upgrade pip
-          pipx install poetry==1.8.5
+          pipx install poetry==2.1.1
+
+      - name: Update poetry.lock after the branch name change
+        working-directory: ./api
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          poetry lock
 
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
@@ -102,7 +117,7 @@ jobs:
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
-          poetry install
+          poetry install --no-root
           poetry run pip list
           VERSION=$(curl --silent "https://api.github.com/repos/hadolint/hadolint/releases/latest" | \
             grep '"tag_name":' | \
@@ -144,7 +159,7 @@ jobs:
         working-directory: ./api
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
-          poetry run safety check --ignore 70612,66963
+          poetry run safety check --ignore 70612,66963,74429
 
       - name: Vulture
         working-directory: ./api
@@ -166,8 +181,23 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           flags: api
+  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
+      - name: Build Container
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
+        with:
+          context: ${{ env.API_WORKING_DIR }}
+          push: false
+          tags: ${{ env.IMAGE_NAME }}:latest
+          outputs: type=docker
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/backport.yml

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

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

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

.github/workflows/conventional-commit.yml

@@ -0,0 +1,23 @@
+name: Prowler - Conventional Commit
+
+on:
+  pull_request:
+    types:
+      - "opened"
+      - "edited"
+      - "synchronize"
+    branches:
+      - "master"
+      - "v3"
+      - "v4.*"
+      - "v5.*"
+
+jobs:
+  conventional-commit-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: conventional-commit-check
+        id: conventional-commit-check
+        uses: agenthunt/conventional-commit-checker-action@9e552d650d0e205553ec7792d447929fc78e012b # v2.0.0
+        with:
+            pr-title-regex: '^([^\s(]+)(?:\(([^)]+)\))?: (.+)'

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

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

.github/workflows/find-secrets.yml

@@ -7,11 +7,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
       - name: TruffleHog OSS
-        uses: trufflesecurity/trufflehog@v3.88.5
+        uses: trufflesecurity/trufflehog@b06f6d72a3791308bb7ba59c2b8cb7a083bd17e4 # v3.88.26
         with:
           path: ./
           base: ${{ github.event.repository.default_branch }}

.github/workflows/labeler.yml

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

.github/workflows/pull-request-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 ${{ github.sha }})
+          echo "SHORT_SHA=${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.sha }}",
+            "PROWLER_COMMIT_SHORT_SHA": "${{ env.SHORT_SHA }}",
+            "PROWLER_PR_TITLE": "${{ github.event.pull_request.title }}",
+            "PROWLER_PR_LABELS": ${{ toJson(github.event.pull_request.labels.*.name) }},
+            "PROWLER_PR_BODY": ${{ toJson(github.event.pull_request.body) }},
+            "PROWLER_PR_URL":${{ toJson(github.event.pull_request.html_url) }}
+          }'

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

@@ -59,16 +59,16 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Install Poetry
         run: |
-          pipx install poetry==1.8.5
+          pipx install poetry==2.*
           pipx inject poetry poetry-bumpversion
 
       - name: Get Prowler version
@@ -108,13 +108,13 @@ jobs:
           esac
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Login to Public ECR
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           registry: public.ecr.aws
           username: ${{ secrets.PUBLIC_ECR_AWS_ACCESS_KEY_ID }}
@@ -123,11 +123,11 @@ jobs:
           AWS_REGION: ${{ env.AWS_REGION }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           push: true
           tags: |
@@ -140,7 +140,7 @@ jobs:
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           # Use local context to get changes
           # https://github.com/docker/build-push-action#path-context

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

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

.github/workflows/sdk-codeql.yml

@@ -21,6 +21,7 @@ on:
     paths-ignore:
       - 'ui/**'
       - 'api/**'
+      - '.github/**'
   pull_request:
     branches:
       - "master"
@@ -30,6 +31,7 @@ on:
     paths-ignore:
       - 'ui/**'
       - 'api/**'
+      - '.github/**'
   schedule:
     - cron: '00 12 * * *'
 
@@ -50,16 +52,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
       with:
         languages: ${{ matrix.language }}
         config-file: ./.github/codeql/sdk-codeql-config.yml
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
       with:
         category: "/language:${{matrix.language}}"

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

@@ -21,11 +21,11 @@ jobs:
         python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Test if changes are in not ignored paths
         id: are-non-ignored-files-changed
-        uses: tj-actions/changed-files@v45
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files: ./**
           files_ignore: |
@@ -34,21 +34,24 @@ jobs:
             permissions/**
             api/**
             ui/**
+            prowler/CHANGELOG.md
             README.md
             mkdocs.yml
             .backportrc.json
             .env
             docker-compose*
+            examples/**
+            .gitignore
 
       - name: Install poetry
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
           python -m pip install --upgrade pip
-          pipx install poetry==1.8.5
+          pipx install poetry==2.1.1
 
       - name: Set up Python ${{ matrix.python-version }}
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
@@ -56,7 +59,7 @@ jobs:
       - name: Install dependencies
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
-          poetry install
+          poetry install --no-root
           poetry run pip list
           VERSION=$(curl --silent "https://api.github.com/repos/hadolint/hadolint/releases/latest" | \
             grep '"tag_name":' | \
@@ -104,15 +107,128 @@ jobs:
         run: |
           /tmp/hadolint Dockerfile --ignore=DL3013
 
-      - name: Test with pytest
+      # Test AWS
+      - name: AWS - Check if any file has changed
+        id: aws-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/aws/**
+            ./tests/providers/aws/**
+            .poetry.lock
+
+      - name: AWS - Test
+        if: steps.aws-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/aws --cov-report=xml:aws_coverage.xml tests/providers/aws
+
+      # Test Azure
+      - name: Azure - Check if any file has changed
+        id: azure-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/azure/**
+            ./tests/providers/azure/**
+            .poetry.lock
+
+      - name: Azure - Test
+        if: steps.azure-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/azure --cov-report=xml:azure_coverage.xml tests/providers/azure
+
+      # Test GCP
+      - name: GCP - Check if any file has changed
+        id: gcp-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/gcp/**
+            ./tests/providers/gcp/**
+            .poetry.lock
+
+      - name: GCP - Test
+        if: steps.gcp-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/gcp --cov-report=xml:gcp_coverage.xml tests/providers/gcp
+
+      # Test Kubernetes
+      - name: Kubernetes - Check if any file has changed
+        id: kubernetes-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/kubernetes/**
+            ./tests/providers/kubernetes/**
+            .poetry.lock
+
+      - name: Kubernetes - Test
+        if: steps.kubernetes-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/kubernetes --cov-report=xml:kubernetes_coverage.xml tests/providers/kubernetes
+
+      # Test GitHub
+      - name: GitHub - Check if any file has changed
+        id: github-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/github/**
+            ./tests/providers/github/**
+            .poetry.lock
+
+      - name: GitHub - Test
+        if: steps.github-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/github --cov-report=xml:github_coverage.xml tests/providers/github
+
+      # Test NHN
+      - name: NHN - Check if any file has changed
+        id: nhn-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/nhn/**
+            ./tests/providers/nhn/**
+            .poetry.lock
+
+      - name: NHN - Test
+        if: steps.nhn-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/nhn --cov-report=xml:nhn_coverage.xml tests/providers/nhn
+
+      # Test M365
+      - name: M365 - Check if any file has changed
+        id: m365-changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files: |
+            ./prowler/providers/m365/**
+            ./tests/providers/m365/**
+            .poetry.lock
+
+      - name: M365 - Test
+        if: steps.m365-changed-files.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/providers/m365 --cov-report=xml:m365_coverage.xml tests/providers/m365
+
+      # Common Tests
+      - name: Lib - Test
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
         run: |
-          poetry run pytest -n auto --cov=./prowler --cov-report=xml tests
+          poetry run pytest -n auto --cov=./prowler/lib --cov-report=xml:lib_coverage.xml tests/lib
 
+      - name: Config - Test
+        if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
+        run: |
+          poetry run pytest -n auto --cov=./prowler/config --cov-report=xml:config_coverage.xml tests/config
+
+      # Codecov
       - name: Upload coverage reports to Codecov
         if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           flags: prowler
+          files: ./aws_coverage.xml,./azure_coverage.xml,./gcp_coverage.xml,./kubernetes_coverage.xml,./github_coverage.xml,./nhn_coverage.xml,./m365_coverage.xml,./lib_coverage.xml,./config_coverage.xml

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

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

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

@@ -4,7 +4,7 @@ name: SDK - Refresh AWS services' regions
 
 on:
   schedule:
-    - cron: "0 9 * * *" #runs at 09:00 UTC everyday
+    - cron: "0 9 * * 1" # runs at 09:00 UTC every Monday
 
 env:
   GITHUB_BRANCH: "master"
@@ -23,12 +23,12 @@ jobs:
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
       # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           ref: ${{ env.GITHUB_BRANCH }}
 
       - name: setup python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: 3.9 #install the python needed
 
@@ -38,7 +38,7 @@ jobs:
           pip install boto3
 
       - name: Configure AWS Credentials -- DEV
-        uses: aws-actions/configure-aws-credentials@v4
+        uses: aws-actions/configure-aws-credentials@ececac1a45f3b08a01d2dd070d28d111c5fe6722 # v4.1.0
         with:
           aws-region: ${{ env.AWS_REGION_DEV }}
           role-to-assume: ${{ secrets.DEV_IAM_ROLE_ARN }}
@@ -50,12 +50,13 @@ jobs:
 
       # Create pull request
       - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v7
+        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
         with:
+          author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
           token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
           commit-message: "feat(regions_update): Update regions for AWS services"
           branch: "aws-services-regions-updated-${{ github.sha }}"
-          labels: "status/waiting-for-revision, severity/low, provider/aws, backport-to-v3"
+          labels: "status/waiting-for-revision, severity/low, provider/aws"
           title: "chore(regions_update): Changes in regions for AWS services"
           body: |
             ### Description

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

@@ -61,38 +61,58 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set short git commit SHA
+        id: vars
+        run: |
+          shortSha=$(git rev-parse --short ${{ github.sha }})
+          echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
 
       - name: Login to DockerHub
-        uses: docker/login-action@v3
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
 
       - name: Build and push container image (latest)
         # Comment the following line for testing
         if: github.event_name == 'push'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
+          build-args: |
+            NEXT_PUBLIC_PROWLER_RELEASE_VERSION=${{ env.SHORT_SHA }}
           # Set push: false for testing
           push: true
           tags: |
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.LATEST_TAG }}
+            ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.SHORT_SHA }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
       - name: Build and push container image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ${{ env.WORKING_DIRECTORY }}
+          build-args: |
+            NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${{ env.RELEASE_TAG }}
           push: true
           tags: |
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.RELEASE_TAG }}
             ${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.STABLE_TAG }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
+
+      - name: Trigger deployment
+        if: github.event_name == 'push'
+        uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
+        with:
+          token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+          repository: ${{ secrets.CLOUD_DISPATCH }}
+          event-type: prowler-ui-deploy
+          client-payload: '{"sha": "${{ github.sha }}", "short_sha": "${{ env.SHORT_SHA }}"}'

.github/workflows/ui-codeql.yml

@@ -44,16 +44,16 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v3
+        uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
         with:
           languages: ${{ matrix.language }}
           config-file: ./.github/codeql/ui-codeql-config.yml
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v3
+        uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
         with:
           category: "/language:${{matrix.language}}"

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

@@ -6,6 +6,7 @@ on:
       - "master"
       - "v5.*"
     paths:
+      - ".github/workflows/ui-pull-request.yml"
       - "ui/**"
   pull_request:
     branches:
@@ -13,6 +14,9 @@ on:
       - "v5.*"
     paths:
       - 'ui/**'
+env:
+  UI_WORKING_DIR: ./ui
+  IMAGE_NAME: prowler-ui
 
 jobs:
   test-and-coverage:
@@ -23,11 +27,11 @@ jobs:
         node-version: [20.x]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           persist-credentials: false
       - name: Setup Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
         with:
           node-version: ${{ matrix.node-version }}
       - name: Install dependencies
@@ -39,3 +43,20 @@ jobs:
       - name: Build the application
         working-directory: ./ui
         run: npm run build
+  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
+      - name: Build Container
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
+        with:
+          context: ${{ env.UI_WORKING_DIR }}
+          # Always build using `prod` target
+          target: prod
+          push: false
+          tags: ${{ env.IMAGE_NAME }}:latest
+          outputs: type=docker
+          build-args: |
+            NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=pk_test_51LwpXXXX

.gitignore

@@ -31,7 +31,7 @@ tags
 *.DS_Store
 
 # Prowler output
-output/
+/output
 
 # Prowler found secrets
 secrets-*/
@@ -42,6 +42,9 @@ junit-reports/
 # VSCode files
 .vscode/
 
+# Cursor files
+.cursorignore
+
 # Terraform
 .terraform*
 *.tfstate
@@ -50,6 +53,7 @@ junit-reports/
 # .env
 ui/.env*
 api/.env*
+.env.local
 
 # Coverage
 .coverage*

.pre-commit-config.yaml

@@ -59,7 +59,7 @@ repos:
         args: ["--ignore=E266,W503,E203,E501,W605"]
 
   - repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
+    rev: 2.1.1
     hooks:
       - id: poetry-check
         name: API - poetry-check
@@ -68,7 +68,7 @@ repos:
 
       - id: poetry-lock
         name: API - poetry-lock
-        args: ["--no-update", "--directory=./api"]
+        args: ["--directory=./api"]
         pass_filenames: false
 
       - id: poetry-check
@@ -78,7 +78,7 @@ repos:
 
       - id: poetry-lock
         name: SDK - poetry-lock
-        args: ["--no-update", "--directory=./"]
+        args: ["--directory=./"]
         pass_filenames: false
 
 
@@ -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'
         language: system
 
       - id: vulture

Dockerfile

@@ -1,38 +1,64 @@
-FROM python:3.12.8-alpine3.20
+FROM python:3.12.10-slim-bookworm AS build
 
 LABEL maintainer="https://github.com/prowler-cloud/prowler"
+LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
 
-# Update system dependencies and install essential tools
-#hadolint ignore=DL3018
-RUN apk --no-cache upgrade && apk --no-cache add curl git
+ARG POWERSHELL_VERSION=7.5.0
+
+# hadolint ignore=DL3008
+RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install PowerShell
+RUN ARCH=$(uname -m) && \
+    if [ "$ARCH" = "x86_64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-x64.tar.gz -O /tmp/powershell.tar.gz ; \
+    elif [ "$ARCH" = "aarch64" ]; then \
+        wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-arm64.tar.gz -O /tmp/powershell.tar.gz ; \
+    else \
+        echo "Unsupported architecture: $ARCH" && exit 1 ; \
+    fi && \
+    mkdir -p /opt/microsoft/powershell/7 && \
+    tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7 && \
+    chmod +x /opt/microsoft/powershell/7/pwsh && \
+    ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh && \
+    rm /tmp/powershell.tar.gz
+
+# Add prowler user
+RUN addgroup --gid 1000 prowler && \
+    adduser --uid 1000 --gid 1000 --disabled-password --gecos "" prowler
 
-# Create non-root user
-RUN mkdir -p /home/prowler && \
-    echo 'prowler:x:1000:1000:prowler:/home/prowler:' > /etc/passwd && \
-    echo 'prowler:x:1000:' > /etc/group && \
-    chown -R prowler:prowler /home/prowler
 USER prowler
 
-# Copy necessary files
 WORKDIR /home/prowler
+
+# Copy necessary files
 COPY prowler/  /home/prowler/prowler/
 COPY dashboard/ /home/prowler/dashboard/
 COPY pyproject.toml /home/prowler
-COPY README.md /home/prowler
+COPY 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'
-ENV PATH="$HOME/.local/bin:$PATH"
-RUN pip install --no-cache-dir --upgrade pip setuptools wheel && \
-    pip install --no-cache-dir .
+ENV PATH="${HOME}/.local/bin:${PATH}"
+#hadolint ignore=DL3013
+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
 
-# Remove Prowler directory and build files
-USER 0
-RUN rm -rf /home/prowler/prowler /home/prowler/pyproject.toml /home/prowler/README.md /home/prowler/build /home/prowler/prowler.egg-info
-
 USER prowler
-ENTRYPOINT ["prowler"]
+ENTRYPOINT ["poetry", "run", "prowler"]

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 | 30 | 10 |
-| GCP | 77 | 13 | 4 | 3 |
-| Azure | 140 | 18 | 5 | 3 |
-| Kubernetes | 83 | 7 | 2 | 7 |
-| Microsoft365 | 5 | 2 | 1 | 0 |
+| AWS | 564 | 82 | 35 | 10 |
+| GCP | 79 | 13 | 9 | 3 |
+| Azure | 140 | 18 | 8 | 3 |
+| Kubernetes | 83 | 7 | 5 | 7 |
+| GitHub | 3 | 2 | 1 | 0 |
+| M365 | 44 | 2 | 2 | 0 |
+| 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
 
@@ -101,15 +125,23 @@ curl -LO https://raw.githubusercontent.com/prowler-cloud/prowler/refs/heads/mast
 docker compose up -d
 ```
 
-> Containers are built for `linux/amd64`. If your workstation's architecture is different, please set `DOCKER_DEFAULT_PLATFORM=linux/amd64` in your environment or use the `--platform linux/amd64` flag in the docker command.
-> Enjoy Prowler App at http://localhost:3000 by signing up with your email and password.
+> Containers are built for `linux/amd64`.
+
+### Configuring Your Workstation for Prowler App
+
+If your workstation's architecture is incompatible, you can resolve this by:
+
+- **Setting the environment variable**: `DOCKER_DEFAULT_PLATFORM=linux/amd64`
+- **Using the following flag in your Docker command**: `--platform linux/amd64`
+
+> Once configured, access the Prowler App at http://localhost:3000. Sign up using your email and password to get started.
 
 ### From GitHub
 
 **Requirements**
 
 * `git` installed.
-* `poetry` installed: [poetry installation](https://python-poetry.org/docs/#installation).
+* `poetry` v2 installed: [poetry installation](https://python-poetry.org/docs/#installation).
 * `npm` installed: [npm installation](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm).
 * `Docker Compose` installed: https://docs.docker.com/compose/install/.
 
@@ -119,7 +151,7 @@ docker compose up -d
 git clone https://github.com/prowler-cloud/prowler
 cd prowler/api
 poetry install
-poetry shell
+eval $(poetry env activate)
 set -a
 source .env
 docker compose up postgres valkey -d
@@ -127,8 +159,13 @@ cd src/backend
 python manage.py migrate --database admin
 gunicorn -c config/guniconf.py config.wsgi:application
 ```
+> [!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.
 
-> 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**
 
@@ -136,7 +173,7 @@ gunicorn -c config/guniconf.py config.wsgi:application
 git clone https://github.com/prowler-cloud/prowler
 cd prowler/api
 poetry install
-poetry shell
+eval $(poetry env activate)
 set -a
 source .env
 cd src/backend
@@ -149,7 +186,7 @@ python -m celery -A config.celery worker -l info -E
 git clone https://github.com/prowler-cloud/prowler
 cd prowler/api
 poetry install
-poetry shell
+eval $(poetry env activate)
 set -a
 source .env
 cd src/backend
@@ -166,29 +203,31 @@ npm run build
 npm start
 ```
 
-> Enjoy Prowler App at http://localhost:3000 by signing up with your email and password.
+> Once configured, access the Prowler App at http://localhost:3000. Sign up using your email and password to get started.
 
 ## Prowler CLI
 ### Pip package
-Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/), thus can be installed using pip with Python > 3.9.1, < 3.13:
+Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/). Consequently, it can be installed using pip with Python >3.9.1, <3.13:
 
 ```console
 pip install prowler
 prowler -v
 ```
->More details at [https://docs.prowler.com](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-cli-installation)
+>For further guidance, refer to [https://docs.prowler.com](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-cli-installation)
 
 ### Containers
 
-The available versions of Prowler CLI are the following:
+**Available Versions of Prowler CLI**
 
-- `latest`: in sync with `master` branch (bear in mind that it is not a stable version)
-- `v4-latest`: in sync with `v4` branch (bear in mind that it is not a stable version)
-- `v3-latest`: in sync with `v3` branch (bear in mind that it is not a stable version)
-- `<x.y.z>` (release): you can find the releases [here](https://github.com/prowler-cloud/prowler/releases), those are stable releases.
-- `stable`: this tag always point to the latest release.
-- `v4-stable`: this tag always point to the latest release for v4.
-- `v3-stable`: this tag always point to the latest release for v3.
+The following versions of Prowler CLI are available, depending on your requirements:
+
+- `latest`: Synchronizes with the `master` branch. Note that this version is not stable.
+- `v4-latest`: Synchronizes with the `v4` branch. Note that this version is not stable.
+- `v3-latest`: Synchronizes with the `v3` branch. Note that this version is not stable.
+- `<x.y.z>` (release): Stable releases corresponding to specific versions. You can find the complete list of releases [here](https://github.com/prowler-cloud/prowler/releases).
+- `stable`: Always points to the latest release.
+- `v4-stable`: Always points to the latest release for v4.
+- `v3-stable`: Always points to the latest release for v3.
 
 The container images are available here:
 - Prowler CLI:
@@ -200,29 +239,56 @@ The container images are available here:
 
 ### From GitHub
 
-Python > 3.9.1, < 3.13 is required with pip and poetry:
+Python >3.9.1, <3.13 is required with pip and Poetry:
 
 ``` console
 git clone https://github.com/prowler-cloud/prowler
 cd prowler
-poetry shell
+eval $(poetry env activate)
 poetry install
-python prowler.py -v
+python prowler-cli.py -v
 ```
-> If you want to clone Prowler from Windows, use `git config core.longpaths true` to allow long file paths.
-# 📐✏️ High level architecture
+> [!IMPORTANT]
+> To clone Prowler on Windows, configure Git to support long file paths by running the following command: `git config core.longpaths true`.
+
+> [!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)
 
@@ -230,23 +296,36 @@ You can run Prowler from your workstation, a Kubernetes Job, a Google Compute En
 
 ## General
 - `Allowlist` now is called `Mutelist`.
-- The `--quiet` option has been deprecated, now use the `--status` flag to select the finding's status you want to get from PASS, FAIL or MANUAL.
-- All `INFO` finding's status has changed to `MANUAL`.
-- The CSV output format is common for all the providers.
+- The `--quiet` option has been deprecated. Use the `--status` flag to filter findings based on their status: PASS, FAIL, or MANUAL.
+- All findings with an `INFO` status have been reclassified as `MANUAL`.
+- The CSV output format is standardized across all providers.
 
-We have deprecated some of our outputs formats:
-- The native JSON is replaced for the JSON [OCSF](https://schema.ocsf.io/) v1.1.0, common for all the providers.
+**Deprecated Output Formats**
+
+The following formats are now deprecated:
+- Native JSON has been replaced with JSON in [OCSF] v1.1.0 format, which is standardized across all providers (https://schema.ocsf.io/).
 
 ## AWS
-- Deprecate the AWS flag --sts-endpoint-region since we use AWS STS regional tokens.
-- To send only FAILS to AWS Security Hub, now use either `--send-sh-only-fails` or `--security-hub --status FAIL`.
+
+**AWS Flag Deprecation**
+
+The flag --sts-endpoint-region has been deprecated due to the adoption of AWS STS regional tokens.
+
+**Sending FAIL Results to AWS Security Hub**
+
+- To send only FAILS to AWS Security Hub, use one of the following options: `--send-sh-only-fails` or `--security-hub --status FAIL`.
 
 
 # 📖 Documentation
 
-Install, Usage, Tutorials and Developer Guide is at https://docs.prowler.com/
+**Documentation Resources**
+
+For installation instructions, usage details, tutorials, and the Developer Guide, visit https://docs.prowler.com/
 
 # 📃 License
 
-Prowler is licensed as Apache License 2.0 as specified in each file. You may obtain a copy of the License at
-<http://www.apache.org/licenses/LICENSE-2.0>
+**Prowler License Information**
+
+Prowler is licensed under the Apache License 2.0, as indicated in each file within the repository. Obtaining a Copy of the License
+
+A copy of the License is available at <http://www.apache.org/licenses/LICENSE-2.0>

api/.env.example

@@ -23,6 +23,7 @@ DJANGO_SECRETS_ENCRYPTION_KEY=""
 DJANGO_MANAGE_DB_PARTITIONS=[True|False]
 DJANGO_CELERY_DEADLOCK_ATTEMPTS=5
 DJANGO_BROKER_VISIBILITY_TIMEOUT=86400
+DJANGO_SENTRY_DSN=
 
 # PostgreSQL settings
 # If running django and celery on host, use 'localhost', else use 'postgres-db'
@@ -39,3 +40,19 @@ POSTGRES_DB=prowler_db
 VALKEY_HOST=[localhost|valkey]
 VALKEY_PORT=6379
 VALKEY_DB=0
+
+# Sentry settings
+SENTRY_ENVIRONMENT=local
+SENTRY_RELEASE=local
+
+# Social login credentials
+DJANGO_GOOGLE_OAUTH_CLIENT_ID=""
+DJANGO_GOOGLE_OAUTH_CLIENT_SECRET=""
+DJANGO_GOOGLE_OAUTH_CALLBACK_URL=""
+
+DJANGO_GITHUB_OAUTH_CLIENT_ID=""
+DJANGO_GITHUB_OAUTH_CLIENT_SECRET=""
+DJANGO_GITHUB_OAUTH_CALLBACK_URL=""
+
+# Deletion Task Batch Size
+DJANGO_DELETION_BATCH_SIZE=5000

api/.pre-commit-config.yaml

@@ -80,7 +80,7 @@ repos:
       - 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'
+        entry: bash -c 'poetry run safety check --ignore 70612,66963,74429'
         language: system
 
       - id: vulture

api/CHANGELOG.md

@@ -2,19 +2,113 @@
 
 All notable changes to the **Prowler API** are documented in this file.
 
+## [v1.9.0] (Prowler UNRELEASED)
+
+### Added
+- Support GCP Service Account key. [(#7824)](https://github.com/prowler-cloud/prowler/pull/7824)
+
+### Changed
+- Renamed field encrypted_password to password for M365 provider [(#7784)](https://github.com/prowler-cloud/prowler/pull/7784)
+
 ---
 
-## [Unreleased]
+## [v1.8.2] (Prowler v5.7.2)
+
+### Fixed
+- Fixed task lookup to use task_kwargs instead of task_args for scan report resolution. [(#7830)](https://github.com/prowler-cloud/prowler/pull/7830)
+
+---
+
+## [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
+- Added huge improvements to `/findings/metadata` and resource related filters for findings [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
+- Added improvements to `/overviews` endpoints [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
+- Added new queue to perform backfill background tasks [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
+- Added new endpoints to retrieve latest findings and metadata [(#7743)](https://github.com/prowler-cloud/prowler/pull/7743).
+- Added export support for Prowler ThreatScore in M365 [(7783)](https://github.com/prowler-cloud/prowler/pull/7783)
+
+---
+
+## [v1.7.0] (Prowler v5.6.0)
+
+### Added
+
+- Added M365 as a new provider [(#7563)](https://github.com/prowler-cloud/prowler/pull/7563).
+- Added a `compliance/` folder and ZIP‐export functionality for all compliance reports.[(#7653)](https://github.com/prowler-cloud/prowler/pull/7653).
+- Added a new 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).
+- Added missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318).
+
+---
+
+## [v1.5.4] (Prowler v5.4.4)
+
+### Fixed
+- Fixed a 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).
+
+---
+
+## [v1.5.2] (Prowler v5.4.2)
+
+### Changed
+- Refactored deletion logic and implemented retry mechanism for deletion tasks [(#7349)](https://github.com/prowler-cloud/prowler/pull/7349).
+
+---
+
+## [v1.5.1] (Prowler v5.4.1)
+
+### Fixed
+- 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).
 
 
 ---
 
-## [v1.4.0] (Prowler v5.3.0) - 2025-02-10
+## [v1.5.0] (Prowler v5.4.0)
+
+### 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).
+- 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).
+
+---
+
+## [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).
-- Increase the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869).
+- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869).
 
 ---

api/Dockerfile

@@ -1,13 +1,33 @@
-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=${POWERSHELL_VERSION}
+
+# hadolint ignore=DL3008
+RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install PowerShell
+RUN ARCH=$(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
@@ -17,27 +37,23 @@ COPY pyproject.toml ./
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir poetry
 
-COPY src/backend/  ./backend/
+COPY src/backend/ ./backend/
 
 ENV PATH="/home/prowler/.local/bin:$PATH"
 
-RUN poetry install && \
+# Add `--no-root` to avoid installing the current project as a package
+RUN poetry install --no-root && \
     rm -rf ~/.cache/pip
 
 COPY docker-entrypoint.sh ./docker-entrypoint.sh
 
+RUN poetry run python "$(poetry env info --path)/src/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py"
+
 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
 
@@ -269,3 +270,66 @@ poetry shell
 cd src/backend
 pytest
 ```
+
+# Custom commands
+
+Django provides a way to create custom commands that can be run from the command line.
+
+> These commands can be found in: ```prowler/api/src/backend/api/management/commands```
+
+To run a custom command, you need to be in the `prowler/api/src/backend` directory and run:
+
+```console
+poetry shell
+python manage.py <command_name>
+```
+
+## Generate dummy data
+
+```console
+python manage.py findings --tenant
+<TENANT_ID> --findings <NUM_FINDINGS> --re
+sources <NUM_RESOURCES> --batch <TRANSACTION_BATCH_SIZE> --alias <ALIAS>
+```
+
+This command creates, for a given tenant, a provider, scan and a set of findings and resources related altogether.
+
+> Scan progress and state are updated in real time.
+> - 0-33%: Create resources.
+> - 33-66%: Create findings.
+> - 66%: Create resource-finding mapping.
+>
+> The last step is required to access the findings details, since the UI needs that to print all the information.
+
+### Example
+
+```console
+~/backend $ poetry run python manage.py findings --tenant
+fffb1893-3fc7-4623-a5d9-fae47da1c528 --findings 25000 --re
+sources 1000 --batch 5000 --alias test-script
+
+Starting data population
+	Tenant: fffb1893-3fc7-4623-a5d9-fae47da1c528
+	Alias: test-script
+	Resources: 1000
+	Findings: 25000
+	Batch size: 5000
+
+
+Creating resources...
+100%|███████████████████████| 1/1 [00:00<00:00,  7.72it/s]
+Resources created successfully.
+
+
+Creating findings...
+100%|███████████████████████| 5/5 [00:05<00:00,  1.09s/it]
+Findings created successfully.
+
+
+Creating resource-finding mappings...
+100%|███████████████████████| 5/5 [00:02<00:00,  1.81it/s]
+Resource-finding mappings created successfully.
+
+
+Successfully populated test data.
+```

api/docker-entrypoint.sh

@@ -28,7 +28,7 @@ start_prod_server() {
 
 start_worker() {
   echo "Starting the worker..."
-  poetry run python -m celery -A config.celery worker -l "${DJANGO_LOGGING_LEVEL:-info}" -Q celery,scans -E --max-tasks-per-child 1
+  poetry run python -m celery -A config.celery worker -l "${DJANGO_LOGGING_LEVEL:-info}" -Q celery,scans,scan-reports,deletion,backfill -E --max-tasks-per-child 1
 }
 
 start_worker_beat() {

api/pyproject.toml

@@ -2,37 +2,44 @@
 build-backend = "poetry.core.masonry.api"
 requires = ["poetry-core"]
 
-[tool.poetry]
-authors = ["Prowler Team"]
+[project]
+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==5.1.8",
+  "django-allauth==65.4.1",
+  "django-celery-beat (>=2.7.0,<3.0.0)",
+  "django-celery-results (>=2.5.1,<3.0.0)",
+  "django-cors-headers==4.4.0",
+  "django-environ==0.11.2",
+  "django-filter==24.3",
+  "django-guid==3.5.0",
+  "django-postgres-extra (>=2.0.8,<3.0.0)",
+  "djangorestframework==3.15.2",
+  "djangorestframework-jsonapi==7.0.2",
+  "djangorestframework-simplejwt (>=5.3.1,<6.0.0)",
+  "drf-nested-routers (>=0.94.1,<1.0.0)",
+  "drf-spectacular==0.27.2",
+  "drf-spectacular-jsonapi==0.5.1",
+  "gunicorn==23.0.0",
+  "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",
+  "openai (>=1.82.0,<2.0.0)"
+]
 description = "Prowler's API (Django/DRF)"
 license = "Apache-2.0"
 name = "prowler-api"
 package-mode = false
-version = "1.4.0"
+# Needed for the SDK compatibility
+requires-python = ">=3.11,<3.13"
+version = "1.9.0"
 
-[tool.poetry.dependencies]
-celery = {extras = ["pytest"], version = "^5.4.0"}
-django = "5.1.5"
-django-celery-beat = "^2.7.0"
-django-celery-results = "^2.5.1"
-django-cors-headers = "4.4.0"
-django-environ = "0.11.2"
-django-filter = "24.3"
-django-guid = "3.5.0"
-django-postgres-extra = "^2.0.8"
-djangorestframework = "3.15.2"
-djangorestframework-jsonapi = "7.0.2"
-djangorestframework-simplejwt = "^5.3.1"
-drf-nested-routers = "^0.94.1"
-drf-spectacular = "0.27.2"
-drf-spectacular-jsonapi = "0.5.1"
-gunicorn = "23.0.0"
-prowler = {git = "https://github.com/prowler-cloud/prowler.git", branch = "v5.3"}
-psycopg2-binary = "2.9.9"
-pytest-celery = {extras = ["redis"], version = "^1.0.1"}
-# Needed for prowler compatibility
-python = ">=3.11,<3.13"
-uuid6 = "2024.7.10"
+[project.scripts]
+celery = "src.backend.config.settings.celery"
 
 [tool.poetry.group.dev.dependencies]
 bandit = "1.7.9"
@@ -40,6 +47,7 @@ coverage = "7.5.4"
 django-silk = "5.3.2"
 docker = "7.1.0"
 freezegun = "1.5.1"
+marshmallow = ">=3.15.0,<4.0.0"
 mypy = "1.10.1"
 pylint = "3.2.5"
 pytest = "8.2.2"
@@ -50,7 +58,5 @@ pytest-randomly = "3.15.0"
 pytest-xdist = "3.6.1"
 ruff = "0.5.0"
 safety = "3.2.9"
+tqdm = "4.67.1"
 vulture = "2.14"
-
-[tool.poetry.scripts]
-celery = "src.backend.config.settings.celery"

api/src/backend/api/adapters.py

@@ -0,0 +1,61 @@
+from allauth.socialaccount.adapter import DefaultSocialAccountAdapter
+from django.db import transaction
+
+from api.db_router import MainRouter
+from api.db_utils import rls_transaction
+from api.models import Membership, Role, Tenant, User, UserRoleRelationship
+
+
+class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
+    @staticmethod
+    def get_user_by_email(email: str):
+        try:
+            return User.objects.get(email=email)
+        except User.DoesNotExist:
+            return None
+
+    def pre_social_login(self, request, sociallogin):
+        # Link existing accounts with the same email address
+        email = sociallogin.account.extra_data.get("email")
+        if email:
+            existing_user = self.get_user_by_email(email)
+            if existing_user:
+                sociallogin.connect(request, existing_user)
+
+    def save_user(self, request, sociallogin, form=None):
+        """
+        Called after the user data is fully populated from the provider
+        and is about to be saved to the DB for the first time.
+        """
+        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)
+
+            tenant = Tenant.objects.using(MainRouter.admin_db).create(
+                name=f"{user.email.split('@')[0]} default tenant"
+            )
+            with rls_transaction(str(tenant.id)):
+                Membership.objects.using(MainRouter.admin_db).create(
+                    user=user, tenant=tenant, role=Membership.RoleChoices.OWNER
+                )
+                role = Role.objects.using(MainRouter.admin_db).create(
+                    name="admin",
+                    tenant_id=tenant.id,
+                    manage_users=True,
+                    manage_account=True,
+                    manage_billing=True,
+                    manage_providers=True,
+                    manage_integrations=True,
+                    manage_scans=True,
+                    unlimited_visibility=True,
+                )
+                UserRoleRelationship.objects.using(MainRouter.admin_db).create(
+                    user=user,
+                    role=role,
+                    tenant_id=tenant.id,
+                )
+        return user

api/src/backend/api/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):

api/src/backend/api/db_router.py

@@ -1,22 +1,29 @@
+ALLOWED_APPS = ("django", "socialaccount", "account", "authtoken", "silk")
+
+
 class MainRouter:
     default_db = "default"
     admin_db = "admin"
 
     def db_for_read(self, model, **hints):  # noqa: F841
         model_table_name = model._meta.db_table
-        if model_table_name.startswith("django_") or model_table_name.startswith(
-            "silk_"
+        if model_table_name.startswith("django_") or any(
+            model_table_name.startswith(f"{app}_") for app in ALLOWED_APPS
         ):
             return self.admin_db
         return None
 
     def db_for_write(self, model, **hints):  # noqa: F841
         model_table_name = model._meta.db_table
-        if model_table_name.startswith("django_") or model_table_name.startswith(
-            "silk_"
-        ):
+        if any(model_table_name.startswith(f"{app}_") for app in ALLOWED_APPS):
             return self.admin_db
         return None
 
     def allow_migrate(self, db, app_label, model_name=None, **hints):  # noqa: F841
         return db == self.admin_db
+
+    def allow_relation(self, obj1, obj2, **hints):  # noqa: F841
+        # Allow relations if both objects are in either "default" or "admin" db connectors
+        if {obj1._state.db, obj2._state.db} <= {self.default_db, self.admin_db}:
+            return True
+        return None

api/src/backend/api/db_utils.py

@@ -6,6 +6,7 @@ from datetime import datetime, timedelta, timezone
 from django.conf import settings
 from django.contrib.auth.models import BaseUserManager
 from django.db import connection, models, transaction
+from django_celery_beat.models import PeriodicTask
 from psycopg2 import connect as psycopg2_connect
 from psycopg2.extensions import AsIs, new_type, register_adapter, register_type
 from rest_framework_json_api.serializers import ValidationError
@@ -105,11 +106,12 @@ def generate_random_token(length: int = 14, symbols: str | None = None) -> str:
     return "".join(secrets.choice(symbols or _symbols) for _ in range(length))
 
 
-def batch_delete(queryset, batch_size=5000):
+def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_SIZE):
     """
     Deletes objects in batches and returns the total number of deletions and a summary.
 
     Args:
+        tenant_id (str): Tenant ID the queryset belongs to.
         queryset (QuerySet): The queryset of objects to delete.
         batch_size (int): The number of objects to delete in each batch.
 
@@ -120,15 +122,16 @@ def batch_delete(queryset, batch_size=5000):
     deletion_summary = {}
 
     while True:
-        # Get a batch of IDs to delete
-        batch_ids = set(
-            queryset.values_list("id", flat=True).order_by("id")[:batch_size]
-        )
-        if not batch_ids:
-            # No more objects to delete
-            break
+        with rls_transaction(tenant_id, POSTGRES_TENANT_VAR):
+            # Get a batch of IDs to delete
+            batch_ids = set(
+                queryset.values_list("id", flat=True).order_by("id")[:batch_size]
+            )
+            if not batch_ids:
+                # No more objects to delete
+                break
 
-        deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
+            deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
 
         total_deleted += deleted_count
         for model_label, count in deleted_info.items():
@@ -137,6 +140,18 @@ def batch_delete(queryset, batch_size=5000):
     return total_deleted, deletion_summary
 
 
+def delete_related_daily_task(provider_id: str):
+    """
+    Deletes the periodic task associated with a specific provider.
+
+    Args:
+        provider_id (str): The unique identifier for the provider
+                           whose related periodic task should be deleted.
+    """
+    task_name = f"scan-perform-scheduled-{provider_id}"
+    PeriodicTask.objects.filter(name=task_name).delete()
+
+
 # Postgres Enums
 
 
@@ -212,6 +227,77 @@ def register_enum(apps, schema_editor, enum_class):  # noqa: F841
         register_adapter(enum_class, enum_adapter)
 
 
+def create_index_on_partitions(
+    apps,  # noqa: F841
+    schema_editor,
+    parent_table: str,
+    index_name: str,
+    columns: str,
+    method: str = "BTREE",
+    where: str = "",
+):
+    """
+    Create an index on every existing partition 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'".
+    """
+    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:
+        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
 
 
@@ -318,3 +404,15 @@ class InvitationStateEnum(EnumType):
 class InvitationStateEnumField(PostgresEnumField):
     def __init__(self, *args, **kwargs):
         super().__init__("invitation_state", *args, **kwargs)
+
+
+# Postgres enum definition for Integration type
+
+
+class IntegrationTypeEnum(EnumType):
+    enum_type_name = "integration_type"
+
+
+class IntegrationTypeEnumField(PostgresEnumField):
+    def __init__(self, *args, **kwargs):
+        super().__init__("integration_type", *args, **kwargs)

api/src/backend/api/decorators.py

@@ -7,7 +7,7 @@ from rest_framework_json_api.serializers import ValidationError
 from api.db_utils import POSTGRES_TENANT_VAR, SET_CONFIG_QUERY
 
 
-def set_tenant(func):
+def set_tenant(func=None, *, keep_tenant=False):
     """
     Decorator to set the tenant context for a Celery task based on the provided tenant_id.
 
@@ -40,20 +40,29 @@ def set_tenant(func):
         # The tenant context will be set before the task logic executes.
     """
 
-    @wraps(func)
-    @transaction.atomic
-    def wrapper(*args, **kwargs):
-        try:
-            tenant_id = kwargs.pop("tenant_id")
-        except KeyError:
-            raise KeyError("This task requires the tenant_id")
-        try:
-            uuid.UUID(tenant_id)
-        except ValueError:
-            raise ValidationError("Tenant ID must be a valid UUID")
-        with connection.cursor() as cursor:
-            cursor.execute(SET_CONFIG_QUERY, [POSTGRES_TENANT_VAR, tenant_id])
+    def decorator(func):
+        @wraps(func)
+        @transaction.atomic
+        def wrapper(*args, **kwargs):
+            try:
+                if not keep_tenant:
+                    tenant_id = kwargs.pop("tenant_id")
+                else:
+                    tenant_id = kwargs["tenant_id"]
+            except KeyError:
+                raise KeyError("This task requires the tenant_id")
+            try:
+                uuid.UUID(tenant_id)
+            except ValueError:
+                raise ValidationError("Tenant ID must be a valid UUID")
+            with connection.cursor() as cursor:
+                cursor.execute(SET_CONFIG_QUERY, [POSTGRES_TENANT_VAR, tenant_id])
 
-        return func(*args, **kwargs)
+            return func(*args, **kwargs)
 
-    return wrapper
+        return wrapper
+
+    if func is None:
+        return decorator
+    else:
+        return decorator(func)

api/src/backend/api/filters.py

@@ -24,6 +24,7 @@ from api.db_utils import (
 from api.models import (
     ComplianceOverview,
     Finding,
+    Integration,
     Invitation,
     Membership,
     PermissionChoices,
@@ -80,6 +81,114 @@ class ChoiceInFilter(BaseInFilter, ChoiceFilter):
     pass
 
 
+class CommonFindingFilters(FilterSet):
+    # We filter providers from the scan in findings
+    provider = UUIDFilter(field_name="scan__provider__id", lookup_expr="exact")
+    provider__in = UUIDInFilter(field_name="scan__provider__id", lookup_expr="in")
+    provider_type = ChoiceFilter(
+        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
+    )
+    provider_type__in = ChoiceInFilter(
+        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
+    )
+    provider_uid = CharFilter(field_name="scan__provider__uid", lookup_expr="exact")
+    provider_uid__in = CharInFilter(field_name="scan__provider__uid", lookup_expr="in")
+    provider_uid__icontains = CharFilter(
+        field_name="scan__provider__uid", lookup_expr="icontains"
+    )
+    provider_alias = CharFilter(field_name="scan__provider__alias", lookup_expr="exact")
+    provider_alias__in = CharInFilter(
+        field_name="scan__provider__alias", lookup_expr="in"
+    )
+    provider_alias__icontains = CharFilter(
+        field_name="scan__provider__alias", lookup_expr="icontains"
+    )
+
+    updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
+
+    uid = CharFilter(field_name="uid")
+    delta = ChoiceFilter(choices=Finding.DeltaChoices.choices)
+    status = ChoiceFilter(choices=StatusChoices.choices)
+    severity = ChoiceFilter(choices=SeverityChoices)
+    impact = ChoiceFilter(choices=SeverityChoices)
+    muted = BooleanFilter(
+        help_text="If this filter is not provided, muted and non-muted findings will be returned."
+    )
+
+    resources = UUIDInFilter(field_name="resource__id", lookup_expr="in")
+
+    region = CharFilter(method="filter_resource_region")
+    region__in = CharInFilter(field_name="resource_regions", lookup_expr="overlap")
+    region__icontains = CharFilter(
+        field_name="resource_regions", lookup_expr="icontains"
+    )
+
+    service = CharFilter(method="filter_resource_service")
+    service__in = CharInFilter(field_name="resource_services", lookup_expr="overlap")
+    service__icontains = CharFilter(
+        field_name="resource_services", lookup_expr="icontains"
+    )
+
+    resource_uid = CharFilter(field_name="resources__uid")
+    resource_uid__in = CharInFilter(field_name="resources__uid", lookup_expr="in")
+    resource_uid__icontains = CharFilter(
+        field_name="resources__uid", lookup_expr="icontains"
+    )
+
+    resource_name = CharFilter(field_name="resources__name")
+    resource_name__in = CharInFilter(field_name="resources__name", lookup_expr="in")
+    resource_name__icontains = CharFilter(
+        field_name="resources__name", lookup_expr="icontains"
+    )
+
+    resource_type = CharFilter(method="filter_resource_type")
+    resource_type__in = CharInFilter(field_name="resource_types", lookup_expr="overlap")
+    resource_type__icontains = CharFilter(
+        field_name="resources__type", lookup_expr="icontains"
+    )
+
+    # Temporarily disabled until we implement tag filtering in the UI
+    # resource_tag_key = CharFilter(field_name="resources__tags__key")
+    # resource_tag_key__in = CharInFilter(
+    #     field_name="resources__tags__key", lookup_expr="in"
+    # )
+    # resource_tag_key__icontains = CharFilter(
+    #     field_name="resources__tags__key", lookup_expr="icontains"
+    # )
+    # resource_tag_value = CharFilter(field_name="resources__tags__value")
+    # resource_tag_value__in = CharInFilter(
+    #     field_name="resources__tags__value", lookup_expr="in"
+    # )
+    # resource_tag_value__icontains = CharFilter(
+    #     field_name="resources__tags__value", lookup_expr="icontains"
+    # )
+    # resource_tags = CharInFilter(
+    #     method="filter_resource_tag",
+    #     lookup_expr="in",
+    #     help_text="Filter by resource tags `key:value` pairs.\nMultiple values may be "
+    #     "separated by commas.",
+    # )
+
+    def filter_resource_service(self, queryset, name, value):
+        return queryset.filter(resource_services__contains=[value])
+
+    def filter_resource_region(self, queryset, name, value):
+        return queryset.filter(resource_regions__contains=[value])
+
+    def filter_resource_type(self, queryset, name, value):
+        return queryset.filter(resource_types__contains=[value])
+
+    def filter_resource_tag(self, queryset, name, value):
+        overall_query = Q()
+        for key_value_pair in value:
+            tag_key, tag_value = key_value_pair.split(":", 1)
+            overall_query |= Q(
+                resources__tags__key__icontains=tag_key,
+                resources__tags__value__icontains=tag_value,
+            )
+        return queryset.filter(overall_query).distinct()
+
+
 class TenantFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
     updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
@@ -256,91 +365,7 @@ class ResourceFilter(ProviderRelationshipFilterSet):
         return queryset.filter(tags__text_search=value)
 
 
-class FindingFilter(FilterSet):
-    # We filter providers from the scan in findings
-    provider = UUIDFilter(field_name="scan__provider__id", lookup_expr="exact")
-    provider__in = UUIDInFilter(field_name="scan__provider__id", lookup_expr="in")
-    provider_type = ChoiceFilter(
-        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
-    )
-    provider_type__in = ChoiceInFilter(
-        choices=Provider.ProviderChoices.choices, field_name="scan__provider__provider"
-    )
-    provider_uid = CharFilter(field_name="scan__provider__uid", lookup_expr="exact")
-    provider_uid__in = CharInFilter(field_name="scan__provider__uid", lookup_expr="in")
-    provider_uid__icontains = CharFilter(
-        field_name="scan__provider__uid", lookup_expr="icontains"
-    )
-    provider_alias = CharFilter(field_name="scan__provider__alias", lookup_expr="exact")
-    provider_alias__in = CharInFilter(
-        field_name="scan__provider__alias", lookup_expr="in"
-    )
-    provider_alias__icontains = CharFilter(
-        field_name="scan__provider__alias", lookup_expr="icontains"
-    )
-
-    updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
-
-    uid = CharFilter(field_name="uid")
-    delta = ChoiceFilter(choices=Finding.DeltaChoices.choices)
-    status = ChoiceFilter(choices=StatusChoices.choices)
-    severity = ChoiceFilter(choices=SeverityChoices)
-    impact = ChoiceFilter(choices=SeverityChoices)
-
-    resources = UUIDInFilter(field_name="resource__id", lookup_expr="in")
-
-    region = CharFilter(field_name="resources__region")
-    region__in = CharInFilter(field_name="resources__region", lookup_expr="in")
-    region__icontains = CharFilter(
-        field_name="resources__region", lookup_expr="icontains"
-    )
-
-    service = CharFilter(field_name="resources__service")
-    service__in = CharInFilter(field_name="resources__service", lookup_expr="in")
-    service__icontains = CharFilter(
-        field_name="resources__service", lookup_expr="icontains"
-    )
-
-    resource_uid = CharFilter(field_name="resources__uid")
-    resource_uid__in = CharInFilter(field_name="resources__uid", lookup_expr="in")
-    resource_uid__icontains = CharFilter(
-        field_name="resources__uid", lookup_expr="icontains"
-    )
-
-    resource_name = CharFilter(field_name="resources__name")
-    resource_name__in = CharInFilter(field_name="resources__name", lookup_expr="in")
-    resource_name__icontains = CharFilter(
-        field_name="resources__name", lookup_expr="icontains"
-    )
-
-    resource_type = CharFilter(field_name="resources__type")
-    resource_type__in = CharInFilter(field_name="resources__type", lookup_expr="in")
-    resource_type__icontains = CharFilter(
-        field_name="resources__type", lookup_expr="icontains"
-    )
-
-    # Temporarily disabled until we implement tag filtering in the UI
-    # resource_tag_key = CharFilter(field_name="resources__tags__key")
-    # resource_tag_key__in = CharInFilter(
-    #     field_name="resources__tags__key", lookup_expr="in"
-    # )
-    # resource_tag_key__icontains = CharFilter(
-    #     field_name="resources__tags__key", lookup_expr="icontains"
-    # )
-    # resource_tag_value = CharFilter(field_name="resources__tags__value")
-    # resource_tag_value__in = CharInFilter(
-    #     field_name="resources__tags__value", lookup_expr="in"
-    # )
-    # resource_tag_value__icontains = CharFilter(
-    #     field_name="resources__tags__value", lookup_expr="icontains"
-    # )
-    # resource_tags = CharInFilter(
-    #     method="filter_resource_tag",
-    #     lookup_expr="in",
-    #     help_text="Filter by resource tags `key:value` pairs.\nMultiple values may be "
-    #     "separated by commas.",
-    # )
-
+class FindingFilter(CommonFindingFilters):
     scan = UUIDFilter(method="filter_scan_id")
     scan__in = UUIDInFilter(method="filter_scan_id_in")
 
@@ -381,6 +406,15 @@ class FindingFilter(FilterSet):
             },
         }
 
+    def filter_resource_type(self, queryset, name, value):
+        return queryset.filter(resource_types__contains=[value])
+
+    def filter_resource_region(self, queryset, name, value):
+        return queryset.filter(resource_regions__contains=[value])
+
+    def filter_resource_service(self, queryset, name, value):
+        return queryset.filter(resource_services__contains=[value])
+
     def filter_queryset(self, queryset):
         if not (self.data.get("scan") or self.data.get("scan__in")) and not (
             self.data.get("inserted_at")
@@ -447,9 +481,7 @@ class FindingFilter(FilterSet):
             )
 
         return (
-            queryset.filter(id__gte=start)
-            .filter(id__lt=end)
-            .filter(scan__id=value_uuid)
+            queryset.filter(id__gte=start).filter(id__lt=end).filter(scan_id=value_uuid)
         )
 
     def filter_scan_id_in(self, queryset, name, value):
@@ -474,41 +506,32 @@ class FindingFilter(FilterSet):
                 ]
             )
         if start == end:
-            return queryset.filter(id__gte=start).filter(scan__id__in=uuid_list)
+            return queryset.filter(id__gte=start).filter(scan_id__in=uuid_list)
         else:
             return (
                 queryset.filter(id__gte=start)
                 .filter(id__lt=end)
-                .filter(scan__id__in=uuid_list)
+                .filter(scan_id__in=uuid_list)
             )
 
     def filter_inserted_at(self, queryset, name, value):
-        value = self.maybe_date_to_datetime(value)
-        start = uuid7_start(datetime_to_uuid7(value))
+        datetime_value = self.maybe_date_to_datetime(value)
+        start = uuid7_start(datetime_to_uuid7(datetime_value))
+        end = uuid7_start(datetime_to_uuid7(datetime_value + timedelta(days=1)))
 
-        return queryset.filter(id__gte=start).filter(inserted_at__date=value)
+        return queryset.filter(id__gte=start, id__lt=end)
 
     def filter_inserted_at_gte(self, queryset, name, value):
-        value = self.maybe_date_to_datetime(value)
-        start = uuid7_start(datetime_to_uuid7(value))
+        datetime_value = self.maybe_date_to_datetime(value)
+        start = uuid7_start(datetime_to_uuid7(datetime_value))
 
-        return queryset.filter(id__gte=start).filter(inserted_at__gte=value)
+        return queryset.filter(id__gte=start)
 
     def filter_inserted_at_lte(self, queryset, name, value):
-        value = self.maybe_date_to_datetime(value)
-        end = uuid7_start(datetime_to_uuid7(value))
+        datetime_value = self.maybe_date_to_datetime(value)
+        end = uuid7_start(datetime_to_uuid7(datetime_value + timedelta(days=1)))
 
-        return queryset.filter(id__lte=end).filter(inserted_at__lte=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()
+        return queryset.filter(id__lt=end)
 
     @staticmethod
     def maybe_date_to_datetime(value):
@@ -518,6 +541,31 @@ class FindingFilter(FilterSet):
         return dt
 
 
+class LatestFindingFilter(CommonFindingFilters):
+    class Meta:
+        model = Finding
+        fields = {
+            "id": ["exact", "in"],
+            "uid": ["exact", "in"],
+            "delta": ["exact", "in"],
+            "status": ["exact", "in"],
+            "severity": ["exact", "in"],
+            "impact": ["exact", "in"],
+            "check_id": ["exact", "in", "icontains"],
+        }
+        filter_overrides = {
+            FindingDeltaEnumField: {
+                "filter_class": CharFilter,
+            },
+            StatusEnumField: {
+                "filter_class": CharFilter,
+            },
+            SeverityEnumField: {
+                "filter_class": CharFilter,
+            },
+        }
+
+
 class ProviderSecretFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
     updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
@@ -614,12 +662,6 @@ class ScanSummaryFilter(FilterSet):
         field_name="scan__provider__provider", choices=Provider.ProviderChoices.choices
     )
     region = CharFilter(field_name="region")
-    muted_findings = BooleanFilter(method="filter_muted_findings")
-
-    def filter_muted_findings(self, queryset, name, value):
-        if not value:
-            return queryset.exclude(muted__gt=0)
-        return queryset
 
     class Meta:
         model = ScanSummary
@@ -630,8 +672,6 @@ class ScanSummaryFilter(FilterSet):
 
 
 class ServiceOverviewFilter(ScanSummaryFilter):
-    muted_findings = None
-
     def is_valid(self):
         # Check if at least one of the inserted_at filters is present
         inserted_at_filters = [
@@ -649,3 +689,19 @@ class ServiceOverviewFilter(ScanSummaryFilter):
                 }
             )
         return super().is_valid()
+
+
+class IntegrationFilter(FilterSet):
+    inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
+    integration_type = ChoiceFilter(choices=Integration.IntegrationChoices.choices)
+    integration_type__in = ChoiceInFilter(
+        choices=Integration.IntegrationChoices.choices,
+        field_name="integration_type",
+        lookup_expr="in",
+    )
+
+    class Meta:
+        model = Integration
+        fields = {
+            "inserted_at": ["date", "gte", "lte"],
+        }

api/src/backend/api/fixtures/dev/2_dev_providers.json

@@ -122,6 +122,22 @@
       "scanner_args": {}
     }
   },
+  {
+    "model": "api.provider",
+    "pk": "7791914f-d646-4fe2-b2ed-73f2c6499a36",
+    "fields": {
+      "tenant": "12646005-9067-4d2a-a098-8bb378604362",
+      "inserted_at": "2024-10-18T10:45:26.352Z",
+      "updated_at": "2024-10-18T11:16:23.533Z",
+      "provider": "kubernetes",
+      "uid": "gke_lucky-coast-419309_us-central1_autopilot-cluster-2",
+      "alias": "k8s_testing_2",
+      "connected": true,
+      "connection_last_checked_at": "2024-10-18T11:16:23.503Z",
+      "metadata": {},
+      "scanner_args": {}
+    }
+  },
   {
     "model": "api.providersecret",
     "pk": "11491b47-75ae-4f71-ad8d-3e630a72182e",

api/src/backend/api/fixtures/dev/3_dev_scans.json

@@ -11,9 +11,7 @@
       "unique_resource_count": 1,
       "duration": 5,
       "scanner_args": {
-        "checks_to_execute": [
-          "accessanalyzer_enabled"
-        ]
+        "checks_to_execute": ["accessanalyzer_enabled"]
       },
       "inserted_at": "2024-09-01T17:25:27.050Z",
       "started_at": "2024-09-01T17:25:27.050Z",
@@ -33,9 +31,7 @@
       "unique_resource_count": 1,
       "duration": 20,
       "scanner_args": {
-        "checks_to_execute": [
-          "accessanalyzer_enabled"
-        ]
+        "checks_to_execute": ["accessanalyzer_enabled"]
       },
       "inserted_at": "2024-09-02T17:24:27.050Z",
       "started_at": "2024-09-02T17:24:27.050Z",
@@ -55,9 +51,7 @@
       "unique_resource_count": 10,
       "duration": 10,
       "scanner_args": {
-        "checks_to_execute": [
-          "cloudsql_instance_automated_backups"
-        ]
+        "checks_to_execute": ["cloudsql_instance_automated_backups"]
       },
       "inserted_at": "2024-09-02T19:26:27.050Z",
       "started_at": "2024-09-02T19:26:27.050Z",
@@ -77,9 +71,7 @@
       "unique_resource_count": 1,
       "duration": 35,
       "scanner_args": {
-        "checks_to_execute": [
-          "accessanalyzer_enabled"
-        ]
+        "checks_to_execute": ["accessanalyzer_enabled"]
       },
       "inserted_at": "2024-09-02T19:27:27.050Z",
       "started_at": "2024-09-02T19:27:27.050Z",
@@ -97,9 +89,7 @@
       "name": "test scheduled aws scan",
       "state": "available",
       "scanner_args": {
-        "checks_to_execute": [
-          "cloudformation_stack_outputs_find_secrets"
-        ]
+        "checks_to_execute": ["cloudformation_stack_outputs_find_secrets"]
       },
       "scheduled_at": "2030-09-02T19:20:27.050Z",
       "inserted_at": "2024-09-02T19:24:27.050Z",
@@ -178,9 +168,7 @@
       "unique_resource_count": 19,
       "progress": 100,
       "scanner_args": {
-        "checks_to_execute": [
-          "accessanalyzer_enabled"
-        ]
+        "checks_to_execute": ["accessanalyzer_enabled"]
       },
       "duration": 7,
       "scheduled_at": null,
@@ -190,6 +178,56 @@
       "completed_at": "2024-10-18T10:46:05.127Z"
     }
   },
+  {
+    "model": "api.scan",
+    "pk": "6dd8925f-a52d-48de-a546-d2d90db30ab1",
+    "fields": {
+      "tenant": "12646005-9067-4d2a-a098-8bb378604362",
+      "name": "real scan azure",
+      "provider": "1b59e032-3eb6-4694-93a5-df84cd9b3ce2",
+      "trigger": "manual",
+      "state": "completed",
+      "unique_resource_count": 20,
+      "progress": 100,
+      "scanner_args": {
+        "checks_to_execute": [
+          "accessanalyzer_enabled",
+          "account_security_contact_information_is_registered"
+        ]
+      },
+      "duration": 4,
+      "scheduled_at": null,
+      "inserted_at": "2024-10-18T11:16:21.358Z",
+      "updated_at": "2024-10-18T11:16:26.060Z",
+      "started_at": "2024-10-18T11:16:21.593Z",
+      "completed_at": "2024-10-18T11:16:26.060Z"
+    }
+  },
+  {
+    "model": "api.scan",
+    "pk": "4ca7ce89-3236-41a8-a369-8937bc152af5",
+    "fields": {
+      "tenant": "12646005-9067-4d2a-a098-8bb378604362",
+      "name": "real scan k8s",
+      "provider": "7791914f-d646-4fe2-b2ed-73f2c6499a36",
+      "trigger": "manual",
+      "state": "completed",
+      "unique_resource_count": 20,
+      "progress": 100,
+      "scanner_args": {
+        "checks_to_execute": [
+          "accessanalyzer_enabled",
+          "account_security_contact_information_is_registered"
+        ]
+      },
+      "duration": 4,
+      "scheduled_at": null,
+      "inserted_at": "2024-10-18T11:16:21.358Z",
+      "updated_at": "2024-10-18T11:16:26.060Z",
+      "started_at": "2024-10-18T11:16:21.593Z",
+      "completed_at": "2024-10-18T11:16:26.060Z"
+    }
+  },
   {
     "model": "api.scan",
     "pk": "01929f57-c0ee-7553-be0b-cbde006fb6f7",

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

@@ -0,0 +1,285 @@
+import random
+from datetime import datetime, timezone
+from math import ceil
+from uuid import uuid4
+
+from django.core.management.base import BaseCommand
+from tqdm import tqdm
+
+from api.db_utils import rls_transaction
+from api.models import (
+    Finding,
+    Provider,
+    Resource,
+    ResourceFindingMapping,
+    ResourceScanSummary,
+    Scan,
+    StatusChoices,
+)
+from prowler.lib.check.models import CheckMetadata
+
+
+class Command(BaseCommand):
+    help = "Populates the database with test data for performance testing."
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "--tenant",
+            type=str,
+            required=True,
+            help="Tenant id for which the data will be populated.",
+        )
+        parser.add_argument(
+            "--resources",
+            type=int,
+            required=True,
+            help="The number of resources to create.",
+        )
+        parser.add_argument(
+            "--findings",
+            type=int,
+            required=True,
+            help="The number of findings to create.",
+        )
+        parser.add_argument(
+            "--batch", type=int, required=True, help="The batch size for bulk creation."
+        )
+        parser.add_argument(
+            "--alias",
+            type=str,
+            required=False,
+            help="Optional alias for the provider and scan",
+        )
+
+    def handle(self, *args, **options):
+        tenant_id = options["tenant"]
+        num_resources = options["resources"]
+        num_findings = options["findings"]
+        batch_size = options["batch"]
+        alias = options["alias"] or "Testing"
+        uid_token = str(uuid4())
+
+        self.stdout.write(self.style.NOTICE("Starting data population"))
+        self.stdout.write(self.style.NOTICE(f"\tTenant: {tenant_id}"))
+        self.stdout.write(self.style.NOTICE(f"\tAlias: {alias}"))
+        self.stdout.write(self.style.NOTICE(f"\tResources: {num_resources}"))
+        self.stdout.write(self.style.NOTICE(f"\tFindings: {num_findings}"))
+        self.stdout.write(self.style.NOTICE(f"\tBatch size: {batch_size}\n\n"))
+
+        # Resource metadata
+        possible_regions = [
+            "us-east-1",
+            "us-east-2",
+            "us-west-1",
+            "us-west-2",
+            "ca-central-1",
+            "eu-central-1",
+            "eu-west-1",
+            "eu-west-2",
+            "eu-west-3",
+            "ap-southeast-1",
+            "ap-southeast-2",
+            "ap-northeast-1",
+            "ap-northeast-2",
+            "ap-south-1",
+            "sa-east-1",
+        ]
+        possible_services = []
+        possible_types = []
+
+        bulk_check_metadata = CheckMetadata.get_bulk(provider="aws")
+        for check_metadata in bulk_check_metadata.values():
+            if check_metadata.ServiceName not in possible_services:
+                possible_services.append(check_metadata.ServiceName)
+            if (
+                check_metadata.ResourceType
+                and check_metadata.ResourceType not in possible_types
+            ):
+                possible_types.append(check_metadata.ResourceType)
+
+        with rls_transaction(tenant_id):
+            provider, _ = Provider.all_objects.get_or_create(
+                tenant_id=tenant_id,
+                provider="aws",
+                connected=True,
+                uid=str(random.randint(100000000000, 999999999999)),
+                defaults={
+                    "alias": alias,
+                },
+            )
+
+        with rls_transaction(tenant_id):
+            scan = Scan.all_objects.create(
+                tenant_id=tenant_id,
+                provider=provider,
+                name=alias,
+                trigger="manual",
+                state="executing",
+                progress=0,
+                started_at=datetime.now(timezone.utc),
+            )
+        scan_state = "completed"
+
+        try:
+            # Create resources
+            resources = []
+
+            for i in range(num_resources):
+                resources.append(
+                    Resource(
+                        tenant_id=tenant_id,
+                        provider_id=provider.id,
+                        uid=f"testing-{uid_token}-{i}",
+                        name=f"Testing {uid_token}-{i}",
+                        region=random.choice(possible_regions),
+                        service=random.choice(possible_services),
+                        type=random.choice(possible_types),
+                        inserted_at="2024-10-01T00:00:00Z",
+                    )
+                )
+
+            num_batches = ceil(len(resources) / batch_size)
+            self.stdout.write(self.style.WARNING("Creating resources..."))
+            for i in tqdm(range(0, len(resources), batch_size), total=num_batches):
+                with rls_transaction(tenant_id):
+                    Resource.all_objects.bulk_create(resources[i : i + batch_size])
+            self.stdout.write(self.style.SUCCESS("Resources created successfully.\n\n"))
+
+            with rls_transaction(tenant_id):
+                scan.progress = 33
+                scan.save()
+
+            # Create Findings
+            findings = []
+            possible_deltas = ["new", "changed", None]
+            possible_severities = ["critical", "high", "medium", "low"]
+            findings_resources_mapping = []
+
+            for i in range(num_findings):
+                severity = random.choice(possible_severities)
+                check_id = random.randint(1, 1000)
+                assigned_resource_num = random.randint(0, len(resources) - 1)
+                assigned_resource = resources[assigned_resource_num]
+                findings_resources_mapping.append(assigned_resource_num)
+
+                findings.append(
+                    Finding(
+                        tenant_id=tenant_id,
+                        scan=scan,
+                        uid=f"testing-{uid_token}-{i}",
+                        delta=random.choice(possible_deltas),
+                        check_id=f"check-{check_id}",
+                        status=random.choice(list(StatusChoices)),
+                        severity=severity,
+                        impact=severity,
+                        raw_result={},
+                        check_metadata={
+                            "checktitle": f"Test title for check {check_id}",
+                            "risk": f"Testing risk {uid_token}-{i}",
+                            "provider": "aws",
+                            "severity": severity,
+                            "categories": ["category1", "category2", "category3"],
+                            "description": "This is a random description that should not matter for testing purposes.",
+                            "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",
+                    )
+                )
+
+            num_batches = ceil(len(findings) / batch_size)
+            self.stdout.write(self.style.WARNING("Creating findings..."))
+            for i in tqdm(range(0, len(findings), batch_size), total=num_batches):
+                with rls_transaction(tenant_id):
+                    Finding.all_objects.bulk_create(findings[i : i + batch_size])
+            self.stdout.write(self.style.SUCCESS("Findings created successfully.\n\n"))
+
+            with rls_transaction(tenant_id):
+                scan.progress = 66
+                scan.save()
+
+            # Create ResourceFindingMapping
+            mappings = []
+            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=resource_instance,
+                        finding=finding_instance,
+                    )
+                )
+                scan_resource_cache.add(
+                    (
+                        str(resource_instance.id),
+                        resource_instance.service,
+                        resource_instance.region,
+                        resource_instance.type,
+                    )
+                )
+
+            num_batches = ceil(len(mappings) / batch_size)
+            self.stdout.write(
+                self.style.WARNING("Creating resource-finding mappings...")
+            )
+            for i in tqdm(range(0, len(mappings), batch_size), total=num_batches):
+                with rls_transaction(tenant_id):
+                    ResourceFindingMapping.objects.bulk_create(
+                        mappings[i : i + batch_size]
+                    )
+            self.stdout.write(
+                self.style.SUCCESS(
+                    "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"
+        finally:
+            scan.completed_at = datetime.now(timezone.utc)
+            scan.duration = int(
+                (datetime.now(timezone.utc) - scan.started_at).total_seconds()
+            )
+            scan.progress = 100
+            scan.state = scan_state
+            scan.unique_resource_count = num_resources
+            with rls_transaction(tenant_id):
+                scan.save()
+
+        self.stdout.write(self.style.NOTICE("Successfully populated test data."))

api/src/backend/api/migrations/0010_findings_performance_indexes_partitions.py

@@ -0,0 +1,109 @@
+from functools import partial
+
+from django.db import connection, migrations
+
+
+def create_index_on_partitions(
+    apps, schema_editor, parent_table: str, index_name: str, index_details: str
+):
+    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()]
+    # Iterate over partitions and create index concurrently.
+    # Note: PostgreSQL does not allow CONCURRENTLY inside a transaction,
+    # so we need atomic = False for this migration.
+    for partition in partitions:
+        sql = (
+            f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {partition.replace('.', '_')}_{index_name} ON {partition} "
+            f"{index_details};"
+        )
+        schema_editor.execute(sql)
+
+
+def drop_index_on_partitions(apps, schema_editor, parent_table: str, index_name: str):
+    with schema_editor.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()]
+
+    # Iterate over partitions and drop index concurrently.
+    for partition in partitions:
+        partition_index = f"{partition.replace('.', '_')}_{index_name}"
+        sql = f"DROP INDEX CONCURRENTLY IF EXISTS {partition_index};"
+        schema_editor.execute(sql)
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0009_increase_provider_uid_maximum_length"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_tenant_and_id_idx",
+                index_details="(tenant_id, id)",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="findings_tenant_and_id_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_idx",
+                index_details="(tenant_id, scan_id)",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_id_idx",
+                index_details="(tenant_id, scan_id, id)",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="find_tenant_scan_id_idx",
+            ),
+        ),
+        migrations.RunPython(
+            partial(
+                create_index_on_partitions,
+                parent_table="findings",
+                index_name="find_delta_new_idx",
+                index_details="(tenant_id, id) where delta = 'new'",
+            ),
+            reverse_code=partial(
+                drop_index_on_partitions,
+                parent_table="findings",
+                index_name="find_delta_new_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0011_findings_performance_indexes_parent.py

@@ -0,0 +1,49 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0010_findings_performance_indexes_partitions"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                fields=["tenant_id", "id"], name="findings_tenant_and_id_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                fields=["tenant_id", "scan_id"], name="find_tenant_scan_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                fields=["tenant_id", "scan_id", "id"], name="find_tenant_scan_id_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="finding",
+            index=models.Index(
+                condition=models.Q(("delta", "new")),
+                fields=["tenant_id", "id"],
+                name="find_delta_new_idx",
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="resourcetagmapping",
+            index=models.Index(
+                fields=["tenant_id", "resource_id"], name="resource_tag_tenant_idx"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="resource",
+            index=models.Index(
+                fields=["tenant_id", "service", "region", "type"],
+                name="resource_tenant_metadata_idx",
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0012_scan_report_output.py

@@ -0,0 +1,15 @@
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0011_findings_performance_indexes_parent"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="scan",
+            name="output_location",
+            field=models.CharField(blank=True, max_length=200, null=True),
+        ),
+    ]

api/src/backend/api/migrations/0013_integrations_enum.py

@@ -0,0 +1,35 @@
+# 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 IntegrationTypeEnum, PostgresEnumMigration, register_enum
+from api.models import Integration
+
+IntegrationTypeEnumMigration = PostgresEnumMigration(
+    enum_name="integration_type",
+    enum_values=tuple(
+        integration_type[0]
+        for integration_type in Integration.IntegrationChoices.choices
+    ),
+)
+
+
+class Migration(migrations.Migration):
+    atomic = False
+
+    dependencies = [
+        ("api", "0012_scan_report_output"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            IntegrationTypeEnumMigration.create_enum_type,
+            reverse_code=IntegrationTypeEnumMigration.drop_enum_type,
+        ),
+        migrations.RunPython(
+            partial(register_enum, enum_class=IntegrationTypeEnum),
+            reverse_code=migrations.RunPython.noop,
+        ),
+    ]

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

@@ -0,0 +1,131 @@
+# Generated by Django 5.1.5 on 2025-03-03 15:46
+
+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", "0013_integrations_enum"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Integration",
+            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)),
+                ("enabled", models.BooleanField(default=False)),
+                ("connected", models.BooleanField(blank=True, null=True)),
+                (
+                    "connection_last_checked_at",
+                    models.DateTimeField(blank=True, null=True),
+                ),
+                (
+                    "integration_type",
+                    api.db_utils.IntegrationTypeEnumField(
+                        choices=[
+                            ("amazon_s3", "Amazon S3"),
+                            ("saml", "SAML"),
+                            ("aws_security_hub", "AWS Security Hub"),
+                            ("jira", "JIRA"),
+                            ("slack", "Slack"),
+                        ]
+                    ),
+                ),
+                ("configuration", models.JSONField(default=dict)),
+                ("_credentials", models.BinaryField(db_column="credentials")),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={"db_table": "integrations", "abstract": False},
+        ),
+        migrations.AddConstraint(
+            model_name="integration",
+            constraint=RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_integration",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+        migrations.CreateModel(
+            name="IntegrationProviderRelationship",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        primary_key=True,
+                        serialize=False,
+                    ),
+                ),
+                ("inserted_at", models.DateTimeField(auto_now_add=True)),
+                (
+                    "integration",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to="api.integration",
+                    ),
+                ),
+                (
+                    "provider",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.provider"
+                    ),
+                ),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "integration_provider_mappings",
+                "constraints": [
+                    models.UniqueConstraint(
+                        fields=("integration_id", "provider_id"),
+                        name="unique_integration_provider_rel",
+                    ),
+                ],
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="IntegrationProviderRelationship",
+            constraint=RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_integrationproviderrelationship",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+        migrations.AddField(
+            model_name="integration",
+            name="providers",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="integrations",
+                through="api.IntegrationProviderRelationship",
+                to="api.provider",
+            ),
+        ),
+    ]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,82 @@
+# Generated by Django 5.1.7 on 2025-04-10 14:54
+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", "0026_provider_secret_gcp_service_account"),
+    ]
+    operations = [
+        migrations.CreateModel(
+            name="LighthouseConfig",
+            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(
+                        max_length=100,
+                        validators=[django.core.validators.MinLengthValidator(3)],
+                    ),
+                ),
+                ("api_key", models.BinaryField()),
+                ("model", models.CharField(default="gpt-4o", max_length=50)),
+                ("temperature", models.FloatField(default=0.7)),
+                ("max_tokens", models.IntegerField(default=4000)),
+                (
+                    "business_context",
+                    models.TextField(
+                        blank=True,
+                        help_text="Additional business context for this AI model configuration",
+                        null=True,
+                    ),
+                ),
+                ("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,
+                "indexes": [
+                    models.Index(fields=["name"], name="lighthouse_config_name_idx"),
+                    models.Index(
+                        fields=["is_active"], name="lighthouse_config_active_idx"
+                    ),
+                ],
+                "constraints": [
+                    models.UniqueConstraint(
+                        fields=("tenant_id",),
+                        name="unique_lighthouse_config_per_tenant",
+                    ),
+                ],
+            },
+        ),
+        migrations.AddConstraint(
+            model_name="lighthouseconfig",
+            constraint=api.rls.RowLevelSecurityConstraint(
+                "tenant_id",
+                name="rls_on_lighthouseconfig",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+    ]

api/src/backend/api/models.py

@@ -1,10 +1,13 @@
 import json
+import logging
 import re
 from uuid import UUID, uuid4
 
-from cryptography.fernet import Fernet
+from config.custom_logging import BackendLogger
+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.core.validators import MinLengthValidator
@@ -21,6 +24,7 @@ from uuid6 import uuid7
 from api.db_utils import (
     CustomUserManager,
     FindingDeltaEnumField,
+    IntegrationTypeEnumField,
     InvitationStateEnumField,
     MemberRoleEnumField,
     ProviderEnumField,
@@ -47,6 +51,8 @@ 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):
     """
@@ -58,7 +64,6 @@ class StatusChoices(models.TextChoices):
     FAIL = "FAIL", _("Fail")
     PASS = "PASS", _("Pass")
     MANUAL = "MANUAL", _("Manual")
-    MUTED = "MUTED", _("Muted")
 
 
 class StateChoices(models.TextChoices):
@@ -191,6 +196,7 @@ class Provider(RowLevelSecurityProtectedModel):
         AZURE = "azure", _("Azure")
         GCP = "gcp", _("GCP")
         KUBERNETES = "kubernetes", _("Kubernetes")
+        M365 = "m365", _("M365")
 
     @staticmethod
     def validate_aws_uid(value):
@@ -214,6 +220,19 @@ 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):
@@ -414,6 +433,8 @@ class Scan(RowLevelSecurityProtectedModel):
     scheduler_task = models.ForeignKey(
         PeriodicTask, on_delete=models.CASCADE, null=True, blank=True
     )
+    output_location = models.CharField(blank=True, null=True, max_length=200)
+
     # TODO: mutelist foreign key
 
     class Meta(RowLevelSecurityProtectedModel.Meta):
@@ -436,6 +457,11 @@ 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:
@@ -517,6 +543,11 @@ class Resource(RowLevelSecurityProtectedModel):
         editable=False,
     )
 
+    metadata = models.TextField(blank=True, null=True)
+    details = models.TextField(blank=True, null=True)
+    partition = models.TextField(blank=True, null=True)
+
+    # Relationships
     tags = models.ManyToManyField(
         ResourceTag,
         verbose_name="Tags associated with the resource, by provider",
@@ -552,7 +583,16 @@ class Resource(RowLevelSecurityProtectedModel):
                 fields=["uid", "region", "service", "name"],
                 name="resource_uid_reg_serv_name_idx",
             ),
+            models.Index(
+                fields=["tenant_id", "service", "region", "type"],
+                name="resource_tenant_metadata_idx",
+            ),
             GinIndex(fields=["text_search"], name="gin_resources_search_idx"),
+            models.Index(fields=["tenant_id", "id"], name="resources_tenant_id_idx"),
+            models.Index(
+                fields=["tenant_id", "provider_id"],
+                name="resources_tenant_provider_idx",
+            ),
         ]
 
         constraints = [
@@ -599,6 +639,12 @@ class ResourceTagMapping(RowLevelSecurityProtectedModel):
             ),
         ]
 
+        indexes = [
+            models.Index(
+                fields=["tenant_id", "resource_id"], name="resource_tag_tenant_idx"
+            ),
+        ]
+
 
 class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
     """
@@ -644,6 +690,23 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
     tags = models.JSONField(default=dict, null=True, blank=True)
     check_id = models.CharField(max_length=100, blank=False, null=False)
     check_metadata = models.JSONField(default=dict, null=False)
+    muted = models.BooleanField(default=False, null=False)
+    compliance = models.JSONField(default=dict, null=True, blank=True)
+
+    # Denormalize resource data for performance
+    resource_regions = ArrayField(
+        models.CharField(max_length=100), blank=True, null=True
+    )
+    resource_services = ArrayField(
+        models.CharField(max_length=100),
+        blank=True,
+        null=True,
+    )
+    resource_types = ArrayField(
+        models.CharField(max_length=100),
+        blank=True,
+        null=True,
+    )
 
     # Relationships
     scan = models.ForeignKey(to=Scan, related_name="findings", on_delete=models.CASCADE)
@@ -685,32 +748,53 @@ 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"),
+            models.Index(
+                fields=["tenant_id", "scan_id", "id"], name="find_tenant_scan_id_idx"
+            ),
+            models.Index(
+                fields=["tenant_id", "id"],
+                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"),
         ]
 
     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()
 
 
@@ -770,6 +854,7 @@ 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)
@@ -1112,8 +1197,268 @@ 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:
         resource_name = "scan-summaries"
+
+
+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")
+
+    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)
+    enabled = models.BooleanField(default=False)
+    connected = models.BooleanField(null=True, blank=True)
+    connection_last_checked_at = models.DateTimeField(null=True, blank=True)
+    integration_type = IntegrationTypeEnumField(choices=IntegrationChoices.choices)
+    configuration = models.JSONField(default=dict)
+    _credentials = models.BinaryField(db_column="credentials")
+
+    providers = models.ManyToManyField(
+        Provider,
+        related_name="integrations",
+        through="IntegrationProviderRelationship",
+        blank=True,
+    )
+
+    class Meta(RowLevelSecurityProtectedModel.Meta):
+        db_table = "integrations"
+
+        constraints = [
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+
+    class JSONAPIMeta:
+        resource_name = "integrations"
+
+    @property
+    def credentials(self):
+        if isinstance(self._credentials, memoryview):
+            encrypted_bytes = self._credentials.tobytes()
+        elif isinstance(self._credentials, str):
+            encrypted_bytes = self._credentials.encode()
+        else:
+            encrypted_bytes = self._credentials
+        decrypted_data = fernet.decrypt(encrypted_bytes)
+        return json.loads(decrypted_data.decode())
+
+    @credentials.setter
+    def credentials(self, value):
+        encrypted_data = fernet.encrypt(json.dumps(value).encode())
+        self._credentials = encrypted_data
+
+
+class IntegrationProviderRelationship(RowLevelSecurityProtectedModel):
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
+    integration = models.ForeignKey(Integration, on_delete=models.CASCADE)
+    provider = models.ForeignKey(Provider, on_delete=models.CASCADE)
+    inserted_at = models.DateTimeField(auto_now_add=True)
+
+    class Meta:
+        db_table = "integration_provider_mappings"
+        constraints = [
+            models.UniqueConstraint(
+                fields=["integration_id", "provider_id"],
+                name="unique_integration_provider_rel",
+            ),
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+
+
+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,
+        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-configuration"

api/src/backend/api/rls.py

@@ -2,8 +2,7 @@ from typing import Any
 from uuid import uuid4
 
 from django.core.exceptions import ValidationError
-from django.db import DEFAULT_DB_ALIAS
-from django.db import models
+from django.db import DEFAULT_DB_ALIAS, models
 from django.db.backends.ddl_references import Statement, Table
 
 from api.db_utils import DB_USER, POSTGRES_TENANT_VAR
@@ -59,11 +58,11 @@ class RowLevelSecurityConstraint(models.BaseConstraint):
     drop_sql_query = """
         ALTER TABLE %(table_name)s NO FORCE ROW LEVEL SECURITY;
         ALTER TABLE %(table_name)s DISABLE ROW LEVEL SECURITY;
-        REVOKE ALL ON TABLE %(table_name) TO %(db_user)s;
+        REVOKE ALL ON TABLE %(table_name)s FROM %(db_user)s;
     """
 
     drop_policy_sql_query = """
-        DROP POLICY IF EXISTS %(db_user)s_%(table_name)s_{statement} on %(table_name)s;
+        DROP POLICY IF EXISTS %(db_user)s_%(raw_table_name)s_{statement} ON %(table_name)s;
     """
 
     def __init__(
@@ -88,9 +87,7 @@ class RowLevelSecurityConstraint(models.BaseConstraint):
                 f"{grant_queries}{self.grant_sql_query.format(statement=statement)}"
             )
 
-        full_create_sql_query = (
-            f"{self.rls_sql_query}" f"{policy_queries}" f"{grant_queries}"
-        )
+        full_create_sql_query = f"{self.rls_sql_query}{policy_queries}{grant_queries}"
 
         table_name = model._meta.db_table
         if self.partition_name:
@@ -107,16 +104,20 @@ class RowLevelSecurityConstraint(models.BaseConstraint):
 
     def remove_sql(self, model: Any, schema_editor: Any) -> Any:
         field_column = schema_editor.quote_name(self.target_field)
+        raw_table_name = model._meta.db_table
+        table_name = raw_table_name
+        if self.partition_name:
+            raw_table_name = f"{raw_table_name}_{self.partition_name}"
+            table_name = raw_table_name
+
         full_drop_sql_query = (
             f"{self.drop_sql_query}"
-            f"{''.join([self.drop_policy_sql_query.format(statement) for statement in self.statements])}"
+            f"{''.join([self.drop_policy_sql_query.format(statement=statement) for statement in self.statements])}"
         )
-        table_name = model._meta.db_table
-        if self.partition_name:
-            table_name = f"{table_name}_{self.partition_name}"
         return Statement(
             full_drop_sql_query,
             table_name=Table(table_name, schema_editor.quote_name),
+            raw_table_name=raw_table_name,
             field_column=field_column,
             db_user=DB_USER,
             partition_name=self.partition_name,

api/src/backend/api/signals.py

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

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

@@ -3,6 +3,8 @@ from conftest import TEST_PASSWORD, get_api_tokens, get_authorization_header
 from django.urls import reverse
 from rest_framework.test import APIClient
 
+from api.models import Membership, User
+
 
 @pytest.mark.django_db
 def test_basic_authentication():
@@ -177,3 +179,122 @@ def test_user_me_when_inviting_users(create_test_user, tenants_fixture, roles_fi
     user2_me = client.get(reverse("user-me"), headers=user2_headers)
     assert user2_me.status_code == 200
     assert user2_me.json()["data"]["attributes"]["email"] == user2_email
+
+
+@pytest.mark.django_db
+class TestTokenSwitchTenant:
+    def test_switch_tenant_with_valid_token(self, tenants_fixture, providers_fixture):
+        client = APIClient()
+
+        test_user = "test_email@prowler.com"
+        test_password = "test_password"
+
+        # Check that we can create a new user without any kind of authentication
+        user_creation_response = client.post(
+            reverse("user-list"),
+            data={
+                "data": {
+                    "type": "users",
+                    "attributes": {
+                        "name": "test",
+                        "email": test_user,
+                        "password": test_password,
+                    },
+                }
+            },
+            format="vnd.api+json",
+        )
+        assert user_creation_response.status_code == 201
+
+        # Create a new relationship between this user and another tenant
+        tenant_id = tenants_fixture[0].id
+        user_instance = User.objects.get(email=test_user)
+        Membership.objects.create(user=user_instance, tenant_id=tenant_id)
+
+        # Check that using our new user's credentials we can authenticate and get the providers
+        access_token, _ = get_api_tokens(client, test_user, test_password)
+        auth_headers = get_authorization_header(access_token)
+
+        user_me_response = client.get(
+            reverse("user-me"),
+            headers=auth_headers,
+        )
+        assert user_me_response.status_code == 200
+        # Assert this user belongs to two tenants
+        assert (
+            user_me_response.json()["data"]["relationships"]["memberships"]["meta"][
+                "count"
+            ]
+            == 2
+        )
+
+        provider_response = client.get(
+            reverse("provider-list"),
+            headers=auth_headers,
+        )
+        assert provider_response.status_code == 200
+        # Empty response since there are no providers in this tenant
+        assert not provider_response.json()["data"]
+
+        switch_tenant_response = client.post(
+            reverse("token-switch"),
+            data={
+                "data": {
+                    "type": "tokens-switch-tenant",
+                    "attributes": {"tenant_id": tenant_id},
+                }
+            },
+            headers=auth_headers,
+        )
+        assert switch_tenant_response.status_code == 200
+        new_access_token = switch_tenant_response.json()["data"]["attributes"]["access"]
+        new_auth_headers = get_authorization_header(new_access_token)
+
+        provider_response = client.get(
+            reverse("provider-list"),
+            headers=new_auth_headers,
+        )
+        assert provider_response.status_code == 200
+        # Now it must be data because we switched to another tenant with providers
+        assert provider_response.json()["data"]
+
+    def test_switch_tenant_with_invalid_token(self, create_test_user, tenants_fixture):
+        client = APIClient()
+
+        access_token, refresh_token = get_api_tokens(
+            client, create_test_user.email, TEST_PASSWORD
+        )
+        auth_headers = get_authorization_header(access_token)
+
+        invalid_token_response = client.post(
+            reverse("token-switch"),
+            data={
+                "data": {
+                    "type": "tokens-switch-tenant",
+                    "attributes": {"tenant_id": "invalid_tenant_id"},
+                }
+            },
+            headers=auth_headers,
+        )
+        assert invalid_token_response.status_code == 400
+        assert invalid_token_response.json()["errors"][0]["code"] == "invalid"
+        assert (
+            invalid_token_response.json()["errors"][0]["detail"]
+            == "Must be a valid UUID."
+        )
+
+        invalid_tenant_response = client.post(
+            reverse("token-switch"),
+            data={
+                "data": {
+                    "type": "tokens-switch-tenant",
+                    "attributes": {"tenant_id": tenants_fixture[-1].id},
+                }
+            },
+            headers=auth_headers,
+        )
+        assert invalid_tenant_response.status_code == 400
+        assert invalid_tenant_response.json()["errors"][0]["code"] == "invalid"
+        assert invalid_tenant_response.json()["errors"][0]["detail"] == (
+            "Tenant does not exist or user is not a " "member."
+        )

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

@@ -131,9 +131,10 @@ class TestBatchDelete:
         return provider_count
 
     @pytest.mark.django_db
-    def test_batch_delete(self, create_test_providers):
+    def test_batch_delete(self, tenants_fixture, create_test_providers):
+        tenant_id = str(tenants_fixture[0].id)
         _, summary = batch_delete(
-            Provider.objects.all(), batch_size=create_test_providers // 2
+            tenant_id, Provider.objects.all(), batch_size=create_test_providers // 2
         )
         assert Provider.objects.all().count() == 0
         assert summary == {"api.Provider": create_test_providers}

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

@@ -92,3 +92,31 @@ 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()

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

@@ -1,7 +1,19 @@
+from unittest.mock import ANY, Mock, patch
+
 import pytest
 from django.urls import reverse
 from rest_framework import status
-from unittest.mock import patch, ANY, Mock
+
+from api.models import (
+    Membership,
+    ProviderGroup,
+    ProviderGroupMembership,
+    Role,
+    RoleProviderGroupRelationship,
+    User,
+    UserRoleRelationship,
+)
+from api.v1.serializers import TokenSerializer
 
 
 @pytest.mark.django_db
@@ -304,3 +316,96 @@ class TestProviderViewSet:
             reverse("provider-connection", kwargs={"pk": provider.id})
         )
         assert response.status_code == status.HTTP_403_FORBIDDEN
+
+
+@pytest.mark.django_db
+class TestLimitedVisibility:
+    TEST_EMAIL = "rbac@rbac.com"
+    TEST_PASSWORD = "thisisapassword123"
+
+    @pytest.fixture
+    def limited_admin_user(
+        self, django_db_setup, django_db_blocker, tenants_fixture, providers_fixture
+    ):
+        with django_db_blocker.unblock():
+            tenant = tenants_fixture[0]
+            provider = providers_fixture[0]
+            user = User.objects.create_user(
+                name="testing",
+                email=self.TEST_EMAIL,
+                password=self.TEST_PASSWORD,
+            )
+            Membership.objects.create(
+                user=user,
+                tenant=tenant,
+                role=Membership.RoleChoices.OWNER,
+            )
+
+            role = Role.objects.create(
+                name="limited_visibility",
+                tenant=tenant,
+                manage_users=True,
+                manage_account=True,
+                manage_billing=True,
+                manage_providers=True,
+                manage_integrations=True,
+                manage_scans=True,
+                unlimited_visibility=False,
+            )
+            UserRoleRelationship.objects.create(
+                user=user,
+                role=role,
+                tenant=tenant,
+            )
+
+            provider_group = ProviderGroup.objects.create(
+                name="limited_visibility_group",
+                tenant=tenant,
+            )
+            ProviderGroupMembership.objects.create(
+                tenant=tenant,
+                provider=provider,
+                provider_group=provider_group,
+            )
+
+            RoleProviderGroupRelationship.objects.create(
+                tenant=tenant, role=role, provider_group=provider_group
+            )
+
+        return user
+
+    @pytest.fixture
+    def authenticated_client_rbac_limited(
+        self, limited_admin_user, tenants_fixture, client
+    ):
+        client.user = limited_admin_user
+        tenant_id = tenants_fixture[0].id
+        serializer = TokenSerializer(
+            data={
+                "type": "tokens",
+                "email": self.TEST_EMAIL,
+                "password": self.TEST_PASSWORD,
+                "tenant_id": tenant_id,
+            }
+        )
+        serializer.is_valid(raise_exception=True)
+        access_token = serializer.validated_data["access"]
+        client.defaults["HTTP_AUTHORIZATION"] = f"Bearer {access_token}"
+        return client
+
+    def test_integrations(
+        self, authenticated_client_rbac_limited, integrations_fixture, providers_fixture
+    ):
+        # Integration 2 is related to provider1 and provider 2
+        # This user cannot see provider 2
+        integration = integrations_fixture[1]
+
+        response = authenticated_client_rbac_limited.get(
+            reverse("integration-detail", kwargs={"pk": integration.id})
+        )
+
+        assert response.status_code == status.HTTP_200_OK
+        assert integration.providers.count() == 2
+        assert (
+            response.json()["data"]["relationships"]["providers"]["meta"]["count"] == 1
+        )

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

@@ -1,25 +1,25 @@
 from datetime import datetime, timedelta, timezone
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
+from rest_framework.exceptions import NotFound, ValidationError
+
+from api.db_router import MainRouter
+from api.exceptions import InvitationTokenExpiredException
+from api.models import Invitation, Provider
+from api.utils import (
+    get_prowler_provider_kwargs,
+    initialize_prowler_provider,
+    merge_dicts,
+    prowler_provider_connection_test,
+    return_prowler_provider,
+    validate_invitation,
+)
 from prowler.providers.aws.aws_provider import AwsProvider
 from prowler.providers.azure.azure_provider import AzureProvider
 from prowler.providers.gcp.gcp_provider import GcpProvider
 from prowler.providers.kubernetes.kubernetes_provider import KubernetesProvider
-from rest_framework.exceptions import ValidationError, NotFound
-
-from api.db_router import MainRouter
-from api.exceptions import InvitationTokenExpiredException
-from api.models import Invitation
-from api.models import Provider
-from api.utils import (
-    merge_dicts,
-    return_prowler_provider,
-    initialize_prowler_provider,
-    prowler_provider_connection_test,
-    get_prowler_provider_kwargs,
-)
-from api.utils import validate_invitation
+from prowler.providers.m365.m365_provider import M365Provider
 
 
 class TestMergeDicts:
@@ -105,6 +105,7 @@ class TestReturnProwlerProvider:
             (Provider.ProviderChoices.GCP.value, GcpProvider),
             (Provider.ProviderChoices.AZURE.value, AzureProvider),
             (Provider.ProviderChoices.KUBERNETES.value, KubernetesProvider),
+            (Provider.ProviderChoices.M365.value, M365Provider),
         ],
     )
     def test_return_prowler_provider(self, provider_type, expected_provider):
@@ -144,6 +145,18 @@ class TestProwlerProviderConnectionTest:
             key="value", provider_id="1234567890", raise_on_exception=False
         )
 
+    @pytest.mark.django_db
+    @patch("api.utils.return_prowler_provider")
+    def test_prowler_provider_connection_test_without_secret(
+        self, mock_return_prowler_provider, providers_fixture
+    ):
+        mock_return_prowler_provider.return_value = MagicMock()
+        connection = prowler_provider_connection_test(providers_fixture[0])
+
+        assert connection.is_connected is False
+        assert isinstance(connection.error, Provider.secret.RelatedObjectDoesNotExist)
+        assert str(connection.error) == "Provider has no secret."
+
 
 class TestGetProwlerProviderKwargs:
     @pytest.mark.parametrize(
@@ -165,6 +178,10 @@ class TestGetProwlerProviderKwargs:
                 Provider.ProviderChoices.KUBERNETES.value,
                 {"context": "provider_uid"},
             ),
+            (
+                Provider.ProviderChoices.M365.value,
+                {},
+            ),
         ],
     )
     def test_get_prowler_provider_kwargs(self, provider_type, expected_extra_kwargs):
@@ -274,9 +291,10 @@ class TestValidateInvitation:
         expired_time = datetime.now(timezone.utc) - timedelta(days=1)
         invitation.expires_at = expired_time
 
-        with patch("api.utils.Invitation.objects.using") as mock_using, patch(
-            "api.utils.datetime"
-        ) as mock_datetime:
+        with (
+            patch("api.utils.Invitation.objects.using") as mock_using,
+            patch("api.utils.datetime") as mock_datetime,
+        ):
             mock_db = mock_using.return_value
             mock_db.get.return_value = invitation
             mock_datetime.now.return_value = datetime.now(timezone.utc)

api/src/backend/api/utils.py

@@ -1,15 +1,29 @@
 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, 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 rest_framework.exceptions import ValidationError, NotFound
+from prowler.providers.m365.m365_provider import M365Provider
 
-from api.db_router import MainRouter
-from api.exceptions import InvitationTokenExpiredException
-from api.models import Provider, Invitation
+
+class CustomOAuth2Client(OAuth2Client):
+    def __init__(self, client_id, secret, *args, **kwargs):
+        # Remove any duplicate "scope_delimiter" from kwargs
+        # Bug present in dj-rest-auth after version v7.0.1
+        # https://github.com/iMerica/dj-rest-auth/issues/673
+        kwargs.pop("scope_delimiter", None)
+        super().__init__(client_id, secret, *args, **kwargs)
 
 
 def merge_dicts(default_dict: dict, replacement_dict: dict) -> dict:
@@ -41,14 +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.
@@ -62,6 +76,8 @@ def return_prowler_provider(
             prowler_provider = AzureProvider
         case Provider.ProviderChoices.KUBERNETES.value:
             prowler_provider = KubernetesProvider
+        case Provider.ProviderChoices.M365.value:
+            prowler_provider = M365Provider
         case _:
             raise ValueError(f"Provider type {provider.provider} not supported")
     return prowler_provider
@@ -94,15 +110,15 @@ def get_prowler_provider_kwargs(provider: Provider) -> dict:
 
 def initialize_prowler_provider(
     provider: Provider,
-) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider:
+) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider:
     """Initialize a Prowler provider instance based on the given provider type.
 
     Args:
         provider (Provider): The provider object containing the provider type and associated secrets.
 
     Returns:
-        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider: An instance of the corresponding provider class
-            (`AwsProvider`, `AzureProvider`, `GcpProvider`, or `KubernetesProvider`) initialized with the
+        AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: An instance of the corresponding provider class
+            (`AwsProvider`, `AzureProvider`, `GcpProvider`, `KubernetesProvider` or `M365Provider`) initialized with the
             provider's secrets.
     """
     prowler_provider = return_prowler_provider(provider)
@@ -120,7 +136,12 @@ def prowler_provider_connection_test(provider: Provider) -> Connection:
         Connection: A connection object representing the result of the connection test for the specified provider.
     """
     prowler_provider = return_prowler_provider(provider)
-    prowler_provider_kwargs = provider.secret.secret
+
+    try:
+        prowler_provider_kwargs = provider.secret.secret
+    except Provider.secret.RelatedObjectDoesNotExist as secret_error:
+        return Connection(is_connected=False, error=secret_error)
+
     return prowler_provider.test_connection(
         **prowler_provider_kwargs, provider_id=provider.uid, raise_on_exception=False
     )
@@ -187,3 +208,33 @@ def validate_invitation(
         )
 
     return invitation
+
+
+# ToRemove after removing the fallback mechanism in /findings/metadata
+def get_findings_metadata_no_aggregations(tenant_id: str, filtered_queryset):
+    filtered_ids = filtered_queryset.order_by().values("id")
+
+    relevant_resources = Resource.all_objects.filter(
+        tenant_id=tenant_id, findings__id__in=Subquery(filtered_ids)
+    ).only("service", "region", "type")
+
+    aggregation = relevant_resources.aggregate(
+        services=ArrayAgg("service", flat=True),
+        regions=ArrayAgg("region", flat=True),
+        resource_types=ArrayAgg("type", flat=True),
+    )
+
+    services = sorted(set(aggregation["services"] or []))
+    regions = sorted({region for region in aggregation["regions"] or [] if region})
+    resource_types = sorted(set(aggregation["resource_types"] or []))
+
+    result = {
+        "services": services,
+        "regions": regions,
+        "resource_types": resource_types,
+    }
+
+    serializer = FindingMetadataSerializer(data=result)
+    serializer.is_valid(raise_exception=True)
+
+    return serializer.data

api/src/backend/api/uuid_utils.py

@@ -106,7 +106,7 @@ def uuid7_end(uuid_obj: UUID, offset_months: int = 1) -> UUID:
 
     Args:
         uuid_obj: A UUIDv7 object.
-        offset_days: Number of months to offset from the given UUID's date. Defaults to 1 to handle if
+        offset_months: Number of months to offset from the given UUID's date. Defaults to 1 to handle if
         partitions are not being used, if so the value will be the one set at FINDINGS_TABLE_PARTITION_MONTHS.
 
     Returns:

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

@@ -0,0 +1,33 @@
+from rest_framework.response import Response
+
+
+class PaginateByPkMixin:
+    """
+    Mixin to paginate on a list of PKs (cheaper than heavy JOINs),
+    re-fetch the full objects with the desired select/prefetch,
+    re-sort them to preserve DB ordering, then serialize + return.
+    """
+
+    def paginate_by_pk(
+        self,
+        request,  # noqa: F841
+        base_queryset,
+        manager,
+        select_related: list[str] | None = None,
+        prefetch_related: list[str] | None = None,
+    ) -> Response:
+        pk_list = base_queryset.values_list("id", flat=True)
+        page = self.paginate_queryset(pk_list)
+        if page is None:
+            return Response(self.get_serializer(base_queryset, many=True).data)
+
+        queryset = manager.filter(id__in=page)
+        if select_related:
+            queryset = queryset.select_related(*select_related)
+        if prefetch_related:
+            queryset = queryset.prefetch_related(*prefetch_related)
+
+        queryset = sorted(queryset, key=lambda obj: page.index(obj.id))
+
+        serialized = self.get_serializer(queryset, many=True).data
+        return self.get_paginated_response(serialized)

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

@@ -0,0 +1,122 @@
+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
+
+
+class S3ConfigSerializer(BaseValidateSerializer):
+    bucket_name = serializers.CharField()
+    output_directory = serializers.CharField()
+
+    class Meta:
+        resource_name = "integrations"
+
+
+class AWSCredentialSerializer(BaseValidateSerializer):
+    role_arn = serializers.CharField(required=False)
+    external_id = serializers.CharField(required=False)
+    role_session_name = serializers.CharField(required=False)
+    session_duration = serializers.IntegerField(
+        required=False, min_value=900, max_value=43200
+    )
+    aws_access_key_id = serializers.CharField(required=False)
+    aws_secret_access_key = serializers.CharField(required=False)
+    aws_session_token = serializers.CharField(required=False)
+
+    class Meta:
+        resource_name = "integrations"
+
+
+@extend_schema_field(
+    {
+        "oneOf": [
+            {
+                "type": "object",
+                "title": "AWS Credentials",
+                "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=,.@_-]+$",
+                    },
+                },
+            },
+        ]
+    }
+)
+class IntegrationCredentialField(serializers.JSONField):
+    pass
+
+
+@extend_schema_field(
+    {
+        "oneOf": [
+            {
+                "type": "object",
+                "title": "Amazon S3",
+                "properties": {
+                    "bucket_name": {
+                        "type": "string",
+                        "description": "The name of the S3 bucket where files will be stored.",
+                    },
+                    "output_directory": {
+                        "type": "string",
+                        "description": "The directory path within the bucket where files will be saved.",
+                    },
+                },
+                "required": ["bucket_name", "output_directory"],
+            },
+        ]
+    }
+)
+class IntegrationConfigField(serializers.JSONField):
+    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

@@ -1,4 +1,5 @@
 import json
+import re
 from datetime import datetime, timedelta, timezone
 
 from django.conf import settings
@@ -16,8 +17,11 @@ from rest_framework_simplejwt.tokens import RefreshToken
 from api.models import (
     ComplianceOverview,
     Finding,
+    Integration,
+    IntegrationProviderRelationship,
     Invitation,
     InvitationRoleRelationship,
+    LighthouseConfiguration,
     Membership,
     Provider,
     ProviderGroup,
@@ -34,11 +38,76 @@ from api.models import (
     UserRoleRelationship,
 )
 from api.rls import Tenant
+from api.v1.serializer_utils.integrations import (
+    AWSCredentialSerializer,
+    IntegrationConfigField,
+    IntegrationCredentialField,
+    S3ConfigSerializer,
+)
+from api.v1.serializer_utils.providers import ProviderSecretField
 
 # Tokens
 
 
-class TokenSerializer(TokenObtainPairSerializer):
+def generate_tokens(user: User, tenant_id: str) -> dict:
+    try:
+        refresh = RefreshToken.for_user(user)
+    except InvalidKeyError:
+        # Handle invalid key error
+        raise ValidationError(
+            {
+                "detail": "Token generation failed due to invalid key configuration. Provide valid "
+                "DJANGO_TOKEN_SIGNING_KEY and DJANGO_TOKEN_VERIFYING_KEY in the environment."
+            }
+        )
+    except Exception as e:
+        raise ValidationError({"detail": str(e)})
+
+    # Post-process the tokens
+    # Set the tenant_id
+    refresh["tenant_id"] = tenant_id
+
+    # Set the nbf (not before) claim to the iat (issued at) claim. At this moment, simplejwt does not provide a
+    # way to set the nbf claim
+    refresh.payload["nbf"] = refresh["iat"]
+
+    # Get the access token
+    access = refresh.access_token
+
+    if settings.SIMPLE_JWT["UPDATE_LAST_LOGIN"]:
+        update_last_login(None, user)
+
+    return {"access": str(access), "refresh": str(refresh)}
+
+
+class BaseTokenSerializer(TokenObtainPairSerializer):
+    def custom_validate(self, attrs, social: bool = False):
+        email = attrs.get("email")
+        password = attrs.get("password")
+        tenant_id = str(attrs.get("tenant_id", ""))
+
+        # Authenticate user
+        user = (
+            User.objects.get(email=email)
+            if social
+            else authenticate(username=email, password=password)
+        )
+        if user is None:
+            raise ValidationError("Invalid credentials")
+
+        if tenant_id:
+            if not user.is_member_of_tenant(tenant_id):
+                raise ValidationError("Tenant does not exist or user is not a member.")
+        else:
+            first_membership = user.memberships.order_by("date_joined").first()
+            if first_membership is None:
+                raise ValidationError("User has no memberships.")
+            tenant_id = str(first_membership.tenant_id)
+
+        return generate_tokens(user, tenant_id)
+
+
+class TokenSerializer(BaseTokenSerializer):
     email = serializers.EmailField(write_only=True)
     password = serializers.CharField(write_only=True)
     tenant_id = serializers.UUIDField(
@@ -56,53 +125,25 @@ class TokenSerializer(TokenObtainPairSerializer):
         resource_name = "tokens"
 
     def validate(self, attrs):
-        email = attrs.get("email")
-        password = attrs.get("password")
-        tenant_id = str(attrs.get("tenant_id", ""))
+        return super().custom_validate(attrs)
 
-        # Authenticate user
-        user = authenticate(username=email, password=password)
-        if user is None:
-            raise ValidationError("Invalid credentials")
 
-        if tenant_id:
-            if not user.is_member_of_tenant(tenant_id):
-                raise ValidationError("Tenant does not exist or user is not a member.")
-        else:
-            first_membership = user.memberships.order_by("date_joined").first()
-            if first_membership is None:
-                raise ValidationError("User has no memberships.")
-            tenant_id = str(first_membership.tenant_id)
+class TokenSocialLoginSerializer(BaseTokenSerializer):
+    email = serializers.EmailField(write_only=True)
 
-        # Generate tokens
-        try:
-            refresh = RefreshToken.for_user(user)
-        except InvalidKeyError:
-            # Handle invalid key error
-            raise ValidationError(
-                {
-                    "detail": "Token generation failed due to invalid key configuration. Provide valid "
-                    "DJANGO_TOKEN_SIGNING_KEY and DJANGO_TOKEN_VERIFYING_KEY in the environment."
-                }
-            )
-        except Exception as e:
-            raise ValidationError({"detail": str(e)})
+    # Output tokens
+    refresh = serializers.CharField(read_only=True)
+    access = serializers.CharField(read_only=True)
 
-        # Post-process the tokens
-        # Set the tenant_id
-        refresh["tenant_id"] = tenant_id
+    class JSONAPIMeta:
+        resource_name = "tokens"
 
-        # Set the nbf (not before) claim to the iat (issued at) claim. At this moment, simplejwt does not provide a
-        # way to set the nbf claim
-        refresh.payload["nbf"] = refresh["iat"]
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.fields.pop("password", None)
 
-        # Get the access token
-        access = refresh.access_token
-
-        if settings.SIMPLE_JWT["UPDATE_LAST_LOGIN"]:
-            update_last_login(None, user)
-
-        return {"access": str(access), "refresh": str(refresh)}
+    def validate(self, attrs):
+        return super().custom_validate(attrs, social=True)
 
 
 # TODO: Check if we can change the parent class to TokenRefreshSerializer from rest_framework_simplejwt.serializers
@@ -140,6 +181,30 @@ class TokenRefreshSerializer(serializers.Serializer):
             raise ValidationError({"refresh": "Invalid or expired token"})
 
 
+class TokenSwitchTenantSerializer(serializers.Serializer):
+    tenant_id = serializers.UUIDField(
+        write_only=True, help_text="The tenant ID for which to request a new token."
+    )
+    access = serializers.CharField(read_only=True)
+    refresh = serializers.CharField(read_only=True)
+
+    class JSONAPIMeta:
+        resource_name = "tokens-switch-tenant"
+
+    def validate(self, attrs):
+        request = self.context["request"]
+        user = request.user
+
+        if not user.is_authenticated:
+            raise ValidationError("Invalid or expired token.")
+
+        tenant_id = str(attrs.get("tenant_id"))
+        if not user.is_member_of_tenant(tenant_id):
+            raise ValidationError("Tenant does not exist or user is not a member.")
+
+        return generate_tokens(user, tenant_id)
+
+
 # Base
 
 
@@ -691,6 +756,43 @@ class ProviderSerializer(RLSSerializer):
         }
 
 
+class ProviderIncludeSerializer(RLSSerializer):
+    """
+    Serializer for the Provider model.
+    """
+
+    provider = ProviderEnumSerializerField()
+    connection = serializers.SerializerMethodField(read_only=True)
+
+    class Meta:
+        model = Provider
+        fields = [
+            "id",
+            "inserted_at",
+            "updated_at",
+            "provider",
+            "uid",
+            "alias",
+            "connection",
+            # "scanner_args",
+        ]
+
+    @extend_schema_field(
+        {
+            "type": "object",
+            "properties": {
+                "connected": {"type": "boolean"},
+                "last_checked_at": {"type": "string", "format": "date-time"},
+            },
+        }
+    )
+    def get_connection(self, obj):
+        return {
+            "connected": obj.connected,
+            "last_checked_at": obj.connection_last_checked_at,
+        }
+
+
 class ProviderCreateSerializer(RLSSerializer, BaseWriteSerializer):
     class Meta:
         model = Provider
@@ -752,6 +854,39 @@ class ScanSerializer(RLSSerializer):
             "url",
         ]
 
+    included_serializers = {
+        "provider": "api.v1.serializers.ProviderIncludeSerializer",
+    }
+
+
+class ScanIncludeSerializer(RLSSerializer):
+    trigger = serializers.ChoiceField(
+        choices=Scan.TriggerChoices.choices, read_only=True
+    )
+    state = StateEnumSerializerField(read_only=True)
+
+    class Meta:
+        model = Scan
+        fields = [
+            "id",
+            "name",
+            "trigger",
+            "state",
+            "unique_resource_count",
+            "progress",
+            # "scanner_args",
+            "duration",
+            "inserted_at",
+            "started_at",
+            "completed_at",
+            "scheduled_at",
+            "provider",
+        ]
+
+    included_serializers = {
+        "provider": "api.v1.serializers.ProviderIncludeSerializer",
+    }
+
 
 class ScanCreateSerializer(RLSSerializer, BaseWriteSerializer):
     class Meta:
@@ -819,6 +954,23 @@ class ScanTaskSerializer(RLSSerializer):
         ]
 
 
+class ScanReportSerializer(serializers.Serializer):
+    id = serializers.CharField(source="scan")
+
+    class Meta:
+        resource_name = "scan-reports"
+        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
@@ -884,6 +1036,51 @@ class ResourceSerializer(RLSSerializer):
         return fields
 
 
+class ResourceIncludeSerializer(RLSSerializer):
+    """
+    Serializer for the Resource model.
+    """
+
+    tags = serializers.SerializerMethodField()
+    type_ = serializers.CharField(read_only=True)
+
+    class Meta:
+        model = Resource
+        fields = [
+            "id",
+            "inserted_at",
+            "updated_at",
+            "uid",
+            "name",
+            "region",
+            "service",
+            "type_",
+            "tags",
+        ]
+        extra_kwargs = {
+            "id": {"read_only": True},
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+        }
+
+    @extend_schema_field(
+        {
+            "type": "object",
+            "description": "Tags associated with the resource",
+            "example": {"env": "prod", "owner": "johndoe"},
+        }
+    )
+    def get_tags(self, obj):
+        return obj.get_tags(self.context.get("tenant_id"))
+
+    def get_fields(self):
+        """`type` is a Python reserved keyword."""
+        fields = super().get_fields()
+        type_ = fields.pop("type_")
+        fields["type"] = type_
+        return fields
+
+
 class FindingSerializer(RLSSerializer):
     """
     Serializer for the Finding model.
@@ -906,6 +1103,7 @@ class FindingSerializer(RLSSerializer):
             "inserted_at",
             "updated_at",
             "first_seen_at",
+            "muted",
             "url",
             # Relationships
             "scan",
@@ -913,8 +1111,8 @@ class FindingSerializer(RLSSerializer):
         ]
 
     included_serializers = {
-        "scan": ScanSerializer,
-        "resources": ResourceSerializer,
+        "scan": ScanIncludeSerializer,
+        "resources": ResourceIncludeSerializer,
     }
 
 
@@ -955,12 +1153,16 @@ class BaseWriteProviderSecretSerializer(BaseWriteSerializer):
                 serializer = GCPProviderSecret(data=secret)
             elif provider_type == Provider.ProviderChoices.KUBERNETES.value:
                 serializer = KubernetesProviderSecret(data=secret)
+            elif provider_type == Provider.ProviderChoices.M365.value:
+                serializer = M365ProviderSecret(data=secret)
             else:
                 raise serializers.ValidationError(
                     {"provider": f"Provider type not supported {provider_type}"}
                 )
         elif secret_type == ProviderSecret.TypeChoices.ROLE:
             serializer = AWSRoleAssumptionProviderSecret(data=secret)
+        elif secret_type == ProviderSecret.TypeChoices.SERVICE_ACCOUNT:
+            serializer = GCPServiceAccountProviderSecret(data=secret)
         else:
             raise serializers.ValidationError(
                 {"secret_type": f"Secret type not supported: {secret_type}"}
@@ -994,6 +1196,17 @@ class AzureProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
+class M365ProviderSecret(serializers.Serializer):
+    client_id = serializers.CharField()
+    client_secret = serializers.CharField()
+    tenant_id = serializers.CharField()
+    user = serializers.EmailField()
+    password = serializers.CharField()
+
+    class Meta:
+        resource_name = "provider-secrets"
+
+
 class GCPProviderSecret(serializers.Serializer):
     client_id = serializers.CharField()
     client_secret = serializers.CharField()
@@ -1003,6 +1216,13 @@ class GCPProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
+class GCPServiceAccountProviderSecret(serializers.Serializer):
+    service_account_key = serializers.JSONField()
+
+    class Meta:
+        resource_name = "provider-secrets"
+
+
 class KubernetesProviderSecret(serializers.Serializer):
     kubeconfig_content = serializers.CharField()
 
@@ -1025,141 +1245,6 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
         resource_name = "provider-secrets"
 
 
-@extend_schema_field(
-    {
-        "oneOf": [
-            {
-                "type": "object",
-                "title": "AWS Static Credentials",
-                "properties": {
-                    "aws_access_key_id": {
-                        "type": "string",
-                        "description": "The AWS access key ID. Required for environments where no IAM role is being "
-                        "assumed and direct AWS access is needed.",
-                    },
-                    "aws_secret_access_key": {
-                        "type": "string",
-                        "description": "The AWS secret access key. Must accompany 'aws_access_key_id' to authorize "
-                        "access to AWS resources.",
-                    },
-                    "aws_session_token": {
-                        "type": "string",
-                        "description": "The session token associated with temporary credentials. Only needed for "
-                        "session-based or temporary AWS access.",
-                    },
-                },
-                "required": ["aws_access_key_id", "aws_secret_access_key"],
-            },
-            {
-                "type": "object",
-                "title": "AWS Assume Role",
-                "properties": {
-                    "role_arn": {
-                        "type": "string",
-                        "description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
-                        "assumption.",
-                    },
-                    "external_id": {
-                        "type": "string",
-                        "description": "An identifier to enhance security for role assumption.",
-                    },
-                    "aws_access_key_id": {
-                        "type": "string",
-                        "description": "The AWS access key ID. Only required if the environment lacks pre-configured "
-                        "AWS credentials.",
-                    },
-                    "aws_secret_access_key": {
-                        "type": "string",
-                        "description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
-                        "no AWS credentials are pre-configured.",
-                    },
-                    "aws_session_token": {
-                        "type": "string",
-                        "description": "The session token for temporary credentials, if applicable.",
-                    },
-                    "session_duration": {
-                        "type": "integer",
-                        "minimum": 900,
-                        "maximum": 43200,
-                        "default": 3600,
-                        "description": "The duration (in seconds) for the role session.",
-                    },
-                    "role_session_name": {
-                        "type": "string",
-                        "description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
-                        "The regex used to validate this parameter is a string of characters consisting of "
-                        "upper- and lower-case alphanumeric characters with no spaces. You can also include "
-                        "underscores or any of the following characters: =,.@-\n\n"
-                        "Examples:\n"
-                        "- MySession123\n"
-                        "- User_Session-1\n"
-                        "- Test.Session@2",
-                        "pattern": "^[a-zA-Z0-9=,.@_-]+$",
-                    },
-                },
-                "required": ["role_arn", "external_id"],
-            },
-            {
-                "type": "object",
-                "title": "Azure Static Credentials",
-                "properties": {
-                    "client_id": {
-                        "type": "string",
-                        "description": "The Azure application (client) ID for authentication in Azure AD.",
-                    },
-                    "client_secret": {
-                        "type": "string",
-                        "description": "The client secret associated with the application (client) ID, providing "
-                        "secure access.",
-                    },
-                    "tenant_id": {
-                        "type": "string",
-                        "description": "The Azure tenant ID, representing the directory where the application is "
-                        "registered.",
-                    },
-                },
-                "required": ["client_id", "client_secret", "tenant_id"],
-            },
-            {
-                "type": "object",
-                "title": "GCP Static Credentials",
-                "properties": {
-                    "client_id": {
-                        "type": "string",
-                        "description": "The client ID from Google Cloud, used to identify the application for GCP "
-                        "access.",
-                    },
-                    "client_secret": {
-                        "type": "string",
-                        "description": "The client secret associated with the GCP client ID, required for secure "
-                        "access.",
-                    },
-                    "refresh_token": {
-                        "type": "string",
-                        "description": "A refresh token that allows the application to obtain new access tokens for "
-                        "extended use.",
-                    },
-                },
-                "required": ["client_id", "client_secret", "refresh_token"],
-            },
-            {
-                "type": "object",
-                "title": "Kubernetes Static Credentials",
-                "properties": {
-                    "kubeconfig_content": {
-                        "type": "string",
-                        "description": "The content of the Kubernetes kubeconfig file, encoded as a string.",
-                    }
-                },
-                "required": ["kubeconfig_content"],
-            },
-        ]
-    }
-)
-class ProviderSecretField(serializers.JSONField):
-    pass
-
-
 class ProviderSecretSerializer(RLSSerializer):
     """
     Serializer for the ProviderSecret model.
@@ -1433,8 +1518,8 @@ class RoleSerializer(RLSSerializer, BaseWriteSerializer):
             "manage_account",
             # Disable for the first release
             # "manage_billing",
-            # "manage_integrations",
             # /Disable for the first release
+            "manage_integrations",
             "manage_providers",
             "manage_scans",
             "permission_state",
@@ -1716,6 +1801,13 @@ class ComplianceOverviewFullSerializer(ComplianceOverviewSerializer):
         return obj.requirements
 
 
+class ComplianceOverviewMetadataSerializer(serializers.Serializer):
+    regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
+
+    class Meta:
+        resource_name = "compliance-overviews-metadata"
+
+
 # Overviews
 
 
@@ -1840,3 +1932,335 @@ class ScheduleDailyCreateSerializer(serializers.Serializer):
             if unknown_keys:
                 raise ValidationError(f"Invalid fields: {unknown_keys}")
         return data
+
+
+# Integrations
+
+
+class BaseWriteIntegrationSerializer(BaseWriteSerializer):
+    @staticmethod
+    def validate_integration_data(
+        integration_type: str,
+        providers: list[Provider],  # noqa
+        configuration: dict,
+        credentials: dict,
+    ):
+        if integration_type == Integration.IntegrationChoices.S3:
+            config_serializer = S3ConfigSerializer
+            credentials_serializers = [AWSCredentialSerializer]
+            # TODO: This will be required for AWS Security Hub
+            # if providers and not all(
+            #     provider.provider == Provider.ProviderChoices.AWS
+            #     for provider in providers
+            # ):
+            #     raise serializers.ValidationError(
+            #         {"providers": "All providers must be AWS for the S3 integration."}
+            #     )
+        else:
+            raise serializers.ValidationError(
+                {
+                    "integration_type": f"Integration type not supported yet: {integration_type}"
+                }
+            )
+
+        config_serializer(data=configuration).is_valid(raise_exception=True)
+
+        for cred_serializer in credentials_serializers:
+            try:
+                cred_serializer(data=credentials).is_valid(raise_exception=True)
+                break
+            except ValidationError:
+                continue
+        else:
+            raise ValidationError(
+                {"credentials": "Invalid credentials for the integration type."}
+            )
+
+
+class IntegrationSerializer(RLSSerializer):
+    """
+    Serializer for the Integration model.
+    """
+
+    providers = serializers.ResourceRelatedField(
+        queryset=Provider.objects.all(), many=True
+    )
+
+    class Meta:
+        model = Integration
+        fields = [
+            "id",
+            "inserted_at",
+            "updated_at",
+            "enabled",
+            "connected",
+            "connection_last_checked_at",
+            "integration_type",
+            "configuration",
+            "providers",
+            "url",
+        ]
+
+    included_serializers = {
+        "providers": "api.v1.serializers.ProviderIncludeSerializer",
+    }
+
+    def to_representation(self, instance):
+        representation = super().to_representation(instance)
+        allowed_providers = self.context.get("allowed_providers")
+        if allowed_providers:
+            allowed_provider_ids = {str(provider.id) for provider in allowed_providers}
+            representation["providers"] = [
+                provider
+                for provider in representation["providers"]
+                if provider["id"] in allowed_provider_ids
+            ]
+        return representation
+
+
+class IntegrationCreateSerializer(BaseWriteIntegrationSerializer):
+    credentials = IntegrationCredentialField(write_only=True)
+    configuration = IntegrationConfigField()
+    providers = serializers.ResourceRelatedField(
+        queryset=Provider.objects.all(), many=True, required=False
+    )
+
+    class Meta:
+        model = Integration
+        fields = [
+            "inserted_at",
+            "updated_at",
+            "enabled",
+            "connected",
+            "connection_last_checked_at",
+            "integration_type",
+            "configuration",
+            "credentials",
+            "providers",
+        ]
+        extra_kwargs = {
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+            "connected": {"read_only": True},
+            "enabled": {"read_only": True},
+            "connection_last_checked_at": {"read_only": True},
+        }
+
+    def validate(self, attrs):
+        integration_type = attrs.get("integration_type")
+        providers = attrs.get("providers")
+        configuration = attrs.get("configuration")
+        credentials = attrs.get("credentials")
+
+        validated_attrs = super().validate(attrs)
+        self.validate_integration_data(
+            integration_type, providers, configuration, credentials
+        )
+        return validated_attrs
+
+    def create(self, validated_data):
+        tenant_id = self.context.get("tenant_id")
+
+        providers = validated_data.pop("providers", [])
+        integration = Integration.objects.create(tenant_id=tenant_id, **validated_data)
+
+        through_model_instances = [
+            IntegrationProviderRelationship(
+                integration=integration,
+                provider=provider,
+                tenant_id=tenant_id,
+            )
+            for provider in providers
+        ]
+        IntegrationProviderRelationship.objects.bulk_create(through_model_instances)
+
+        return integration
+
+
+class IntegrationUpdateSerializer(BaseWriteIntegrationSerializer):
+    credentials = IntegrationCredentialField(write_only=True, required=False)
+    configuration = IntegrationConfigField(required=False)
+    providers = serializers.ResourceRelatedField(
+        queryset=Provider.objects.all(), many=True, required=False
+    )
+
+    class Meta:
+        model = Integration
+        fields = [
+            "inserted_at",
+            "updated_at",
+            "enabled",
+            "connected",
+            "connection_last_checked_at",
+            "integration_type",
+            "configuration",
+            "credentials",
+            "providers",
+        ]
+        extra_kwargs = {
+            "inserted_at": {"read_only": True},
+            "updated_at": {"read_only": True},
+            "connected": {"read_only": True},
+            "connection_last_checked_at": {"read_only": True},
+            "integration_type": {"read_only": True},
+        }
+
+    def validate(self, attrs):
+        integration_type = self.instance.integration_type
+        providers = attrs.get("providers")
+        configuration = attrs.get("configuration") or self.instance.configuration
+        credentials = attrs.get("credentials") or self.instance.credentials
+
+        validated_attrs = super().validate(attrs)
+        self.validate_integration_data(
+            integration_type, providers, configuration, credentials
+        )
+        return validated_attrs
+
+    def update(self, instance, validated_data):
+        tenant_id = self.context.get("tenant_id")
+        if validated_data.get("providers") is not None:
+            instance.providers.clear()
+            new_relationships = [
+                IntegrationProviderRelationship(
+                    integration=instance, provider=provider, tenant_id=tenant_id
+                )
+                for provider in validated_data["providers"]
+            ]
+            IntegrationProviderRelationship.objects.bulk_create(new_relationships)
+
+        return super().update(instance, validated_data)
+
+
+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},
+            "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},
+            "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")
+
+        # Validate API key format before creating the instance
+        if not api_key:
+            raise serializers.ValidationError({"api_key": "API key is required"})
+
+        # Validate OpenAI API key format
+        openai_key_pattern = r"^sk-[\w-]+T3BlbkFJ[\w-]+$"
+        if not re.match(openai_key_pattern, api_key):
+            raise serializers.ValidationError(
+                {"api_key": "Invalid OpenAI API key format."}
+            )
+
+        instance = super().create(validated_data)
+        instance.api_key_decoded = api_key
+        instance.save()
+        return instance
+
+
+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},
+            "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

@@ -6,9 +6,14 @@ from api.v1.views import (
     ComplianceOverviewViewSet,
     CustomTokenObtainView,
     CustomTokenRefreshView,
+    CustomTokenSwitchTenantView,
     FindingViewSet,
+    GithubSocialLoginView,
+    GoogleSocialLoginView,
+    IntegrationViewSet,
     InvitationAcceptViewSet,
     InvitationViewSet,
+    LighthouseConfigViewSet,
     MembershipViewSet,
     OverviewViewSet,
     ProviderGroupProvidersRelationshipView,
@@ -44,6 +49,12 @@ router.register(
 )
 router.register(r"overviews", OverviewViewSet, basename="overview")
 router.register(r"schedules", ScheduleViewSet, basename="schedule")
+router.register(r"integrations", IntegrationViewSet, basename="integration")
+router.register(
+    r"lighthouse-configuration",
+    LighthouseConfigViewSet,
+    basename="lighthouseconfiguration",
+)
 
 tenants_router = routers.NestedSimpleRouter(router, r"tenants", lookup="tenant")
 tenants_router.register(
@@ -56,6 +67,7 @@ users_router.register(r"memberships", MembershipViewSet, basename="user-membersh
 urlpatterns = [
     path("tokens", CustomTokenObtainView.as_view(), name="token-obtain"),
     path("tokens/refresh", CustomTokenRefreshView.as_view(), name="token-refresh"),
+    path("tokens/switch", CustomTokenSwitchTenantView.as_view(), name="token-switch"),
     path(
         "providers/secrets",
         ProviderSecretViewSet.as_view({"get": "list", "post": "create"}),
@@ -106,6 +118,8 @@ urlpatterns = [
         ),
         name="provider_group-providers-relationship",
     ),
+    path("tokens/google", GoogleSocialLoginView.as_view(), name="token-google"),
+    path("tokens/github", GithubSocialLoginView.as_view(), name="token-github"),
     path("", include(router.urls)),
     path("", include(tenants_router.urls)),
     path("", include(users_router.urls)),

api/src/backend/config/celery.py

@@ -50,9 +50,9 @@ class RLSTask(Task):
 
         tenant_id = kwargs.get("tenant_id")
         with rls_transaction(tenant_id):
-            APITask.objects.create(
+            APITask.objects.update_or_create(
                 id=task_result_instance.task_id,
                 tenant_id=tenant_id,
-                task_runner_task=task_result_instance,
+                defaults={"task_runner_task": task_result_instance},
             )
         return result

api/src/backend/config/custom_logging.py

@@ -2,9 +2,8 @@ import json
 import logging
 from enum import StrEnum
 
-from django_guid.log_filters import CorrelationId
-
 from config.env import env
+from django_guid.log_filters import CorrelationId
 
 
 class BackendLogger(StrEnum):
@@ -39,9 +38,9 @@ class NDJSONFormatter(logging.Formatter):
             "funcName": record.funcName,
             "process": record.process,
             "thread": record.thread,
-            "transaction_id": record.transaction_id
-            if hasattr(record, "transaction_id")
-            else None,
+            "transaction_id": (
+                record.transaction_id if hasattr(record, "transaction_id") else None
+            ),
         }
 
         # Add REST API extra fields

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

@@ -4,6 +4,8 @@ from config.custom_logging import LOGGING  # noqa
 from config.env import BASE_DIR, env  # noqa
 from config.settings.celery import *  # noqa
 from config.settings.partitions import *  # noqa
+from config.settings.sentry import *  # noqa
+from config.settings.social_login import *  # noqa
 
 SECRET_KEY = env("SECRET_KEY", default="secret")
 DEBUG = env.bool("DJANGO_DEBUG", default=False)
@@ -29,6 +31,13 @@ INSTALLED_APPS = [
     "django_celery_results",
     "django_celery_beat",
     "rest_framework_simplejwt.token_blacklist",
+    "allauth",
+    "allauth.account",
+    "allauth.socialaccount",
+    "allauth.socialaccount.providers.google",
+    "allauth.socialaccount.providers.github",
+    "dj_rest_auth.registration",
+    "rest_framework.authtoken",
 ]
 
 MIDDLEWARE = [
@@ -42,8 +51,11 @@ MIDDLEWARE = [
     "django.contrib.messages.middleware.MessageMiddleware",
     "django.middleware.clickjacking.XFrameOptionsMiddleware",
     "api.middleware.APILoggingMiddleware",
+    "allauth.account.middleware.AccountMiddleware",
 ]
 
+SITE_ID = 1
+
 CORS_ALLOWED_ORIGINS = ["http://localhost", "http://127.0.0.1"]
 
 ROOT_URLCONF = "config.urls"
@@ -99,6 +111,7 @@ SPECTACULAR_SETTINGS = {
     "PREPROCESSING_HOOKS": [
         "drf_spectacular_jsonapi.hooks.fix_nested_path_parameters",
     ],
+    "TITLE": "API Reference - Prowler",
 }
 
 WSGI_APPLICATION = "config.wsgi.application"
@@ -207,4 +220,27 @@ CACHE_STALE_WHILE_REVALIDATE = env.int("DJANGO_STALE_WHILE_REVALIDATE", 60)
 
 
 TESTING = False
+
 FINDINGS_MAX_DAYS_IN_RANGE = env.int("DJANGO_FINDINGS_MAX_DAYS_IN_RANGE", 7)
+
+
+# API export settings
+DJANGO_TMP_OUTPUT_DIRECTORY = env.str(
+    "DJANGO_TMP_OUTPUT_DIRECTORY", "/tmp/prowler_api_output"
+)
+DJANGO_FINDINGS_BATCH_SIZE = env.str("DJANGO_FINDINGS_BATCH_SIZE", 1000)
+
+DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET", "")
+DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = env.str("DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID", "")
+DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = env.str(
+    "DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY", ""
+)
+DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = env.str("DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN", "")
+DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION", "")
+
+# HTTP Security Headers
+SECURE_CONTENT_TYPE_NOSNIFF = True
+X_FRAME_OPTIONS = "DENY"
+SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
+
+DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)

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

@@ -0,0 +1,102 @@
+import sentry_sdk
+from config.env import env
+
+IGNORED_EXCEPTIONS = [
+    # Provider is not connected due to credentials errors
+    "is not connected",
+    # Authentication Errors from AWS
+    "InvalidToken",
+    "AccessDeniedException",
+    "AuthorizationErrorException",
+    "UnrecognizedClientException",
+    "UnauthorizedOperation",
+    "AuthFailure",
+    "InvalidClientTokenId",
+    "AWSInvalidProviderIdError",
+    "InternalServerErrorException",
+    "AccessDenied",
+    "No Shodan API Key",  # Shodan Check
+    "RequestLimitExceeded",  # For now we don't want to log the RequestLimitExceeded errors
+    "ThrottlingException",
+    "Rate exceeded",
+    "SubscriptionRequiredException",
+    "UnknownOperationException",
+    "OptInRequired",
+    "ReadTimeout",
+    "LimitExceeded",
+    "ConnectTimeoutError",
+    "ExpiredToken",
+    "IncompleteSignature",
+    "RegionDisabledException",
+    "TooManyRequestsException",
+    "SignatureDoesNotMatch",
+    "InvalidParameterValueException",
+    "InvalidInputException",
+    "ValidationException",
+    "AWSSecretAccessKeyInvalidError",
+    "InvalidAction",
+    "InvalidRequestException",
+    "RequestExpired",
+    "ConnectionClosedError",
+    "MaxRetryError",
+    "AWSAccessKeyIDInvalidError",
+    "AWSSessionTokenExpiredError",
+    "EndpointConnectionError",  # AWS Service is not available in a region
+    "Pool is closed",  # The following comes from urllib3: eu-west-1 -- HTTPClientError[126]: An HTTP Client raised an unhandled exception: AWSHTTPSConnectionPool(host='hostname.s3.eu-west-1.amazonaws.com', port=443): Pool is closed.
+    # Authentication Errors from GCP
+    "ClientAuthenticationError",
+    "AuthorizationFailed",
+    "Reauthentication is needed",
+    "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",
+    "AuthorizationFailed",
+    "Subscription Not Registered",
+    "AzureNotValidClientIdError",
+    "AzureNotValidClientSecretError",
+    "AzureNotValidTenantIdError",
+    "AzureInvalidProviderIdError",
+    "AzureTenantIdAndClientSecretNotBelongingToClientIdError",
+    "AzureTenantIdAndClientIdNotBelongingToClientSecretError",
+    "AzureClientIdAndClientSecretNotBelongingToTenantIdError",
+    "AzureHTTPResponseError",
+    "Error with credentials provided",
+]
+
+
+def before_send(event, hint):
+    """
+    before_send handles the Sentry events in order to sent them or not
+    """
+    # Ignore logs with the ignored_exceptions
+    # https://docs.python.org/3/library/logging.html#logrecord-objects
+    if "log_record" in 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
+    return event
+
+
+sentry_sdk.init(
+    dsn=env.str("DJANGO_SENTRY_DSN", ""),
+    # Add data like request headers and IP for users,
+    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
+    before_send=before_send,
+    send_default_pii=True,
+    _experiments={
+        # Set continuous_profiling_auto_start to True
+        # to automatically start the profiler on when
+        # possible.
+        "continuous_profiling_auto_start": True,
+    },
+    attach_stacktrace=True,
+    ignore_errors=IGNORED_EXCEPTIONS,
+)

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

@@ -0,0 +1,53 @@
+from config.env import env
+
+# Provider Oauth settings
+GOOGLE_OAUTH_CLIENT_ID = env("SOCIAL_GOOGLE_OAUTH_CLIENT_ID", default="")
+GOOGLE_OAUTH_CLIENT_SECRET = env("SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET", default="")
+GOOGLE_OAUTH_CALLBACK_URL = env("SOCIAL_GOOGLE_OAUTH_CALLBACK_URL", default="")
+
+GITHUB_OAUTH_CLIENT_ID = env("SOCIAL_GITHUB_OAUTH_CLIENT_ID", default="")
+GITHUB_OAUTH_CLIENT_SECRET = env("SOCIAL_GITHUB_OAUTH_CLIENT_SECRET", default="")
+GITHUB_OAUTH_CALLBACK_URL = env("SOCIAL_GITHUB_OAUTH_CALLBACK_URL", default="")
+
+# Allauth settings
+ACCOUNT_LOGIN_METHODS = {"email"}  # Use Email / Password authentication
+ACCOUNT_USERNAME_REQUIRED = False
+ACCOUNT_EMAIL_REQUIRED = True
+ACCOUNT_EMAIL_VERIFICATION = "none"  # Do not require email confirmation
+ACCOUNT_USER_MODEL_USERNAME_FIELD = None
+REST_AUTH = {
+    "TOKEN_MODEL": None,
+    "REST_USE_JWT": True,
+}
+# django-allauth (social)
+# Authenticate if local account with this email address already exists
+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"
+SOCIALACCOUNT_PROVIDERS = {
+    "google": {
+        "APP": {
+            "client_id": GOOGLE_OAUTH_CLIENT_ID,
+            "secret": GOOGLE_OAUTH_CLIENT_SECRET,
+            "key": "",
+        },
+        "SCOPE": [
+            "email",
+            "profile",
+        ],
+        "AUTH_PARAMS": {
+            "access_type": "online",
+        },
+    },
+    "github": {
+        "APP": {
+            "client_id": GITHUB_OAUTH_CLIENT_ID,
+            "secret": GITHUB_OAUTH_CLIENT_SECRET,
+        },
+        "SCOPE": [
+            "user",
+            "read:org",
+        ],
+    },
+}

api/src/backend/conftest.py

@@ -10,12 +10,16 @@ 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,
     Finding,
+    Integration,
+    IntegrationProviderRelationship,
     Invitation,
+    LighthouseConfiguration,
     Membership,
     Provider,
     ProviderGroup,
@@ -486,7 +490,7 @@ def scans_fixture(tenants_fixture, providers_fixture):
         name="Scan 1",
         provider=provider,
         trigger=Scan.TriggerChoices.MANUAL,
-        state=StateChoices.AVAILABLE,
+        state=StateChoices.COMPLETED,
         tenant_id=tenant.id,
         started_at="2024-01-02T00:00:00Z",
     )
@@ -653,6 +657,7 @@ def findings_fixture(scans_fixture, resources_fixture):
             "Description": "test description orange juice",
         },
         first_seen_at="2024-01-02T00:00:00Z",
+        muted=True,
     )
 
     finding2.add_resources([resource2])
@@ -877,6 +882,109 @@ def scan_summaries_fixture(tenants_fixture, providers_fixture):
     )
 
 
+@pytest.fixture
+def integrations_fixture(providers_fixture):
+    provider1, provider2, *_ = providers_fixture
+    tenant_id = provider1.tenant_id
+    integration1 = Integration.objects.create(
+        tenant_id=tenant_id,
+        enabled=True,
+        connected=True,
+        integration_type="amazon_s3",
+        configuration={"key": "value"},
+        credentials={"psswd": "1234"},
+    )
+    IntegrationProviderRelationship.objects.create(
+        tenant_id=tenant_id,
+        integration=integration1,
+        provider=provider1,
+    )
+
+    integration2 = Integration.objects.create(
+        tenant_id=tenant_id,
+        enabled=True,
+        connected=True,
+        integration_type="amazon_s3",
+        configuration={"key": "value"},
+        credentials={"psswd": "1234"},
+    )
+    IntegrationProviderRelationship.objects.create(
+        tenant_id=tenant_id,
+        integration=integration2,
+        provider=provider1,
+    )
+    IntegrationProviderRelationship.objects.create(
+        tenant_id=tenant_id,
+        integration=integration2,
+        provider=provider2,
+    )
+
+    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
+
+
 def get_authorization_header(access_token: str) -> dict:
     return {"Authorization": f"Bearer {access_token}"}
 

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/deletion.py

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

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

@@ -0,0 +1,253 @@
+import os
+import zipfile
+
+import boto3
+import config.django.base as base
+from botocore.exceptions import ClientError, NoCredentialsError, ParamValidationError
+from celery.utils.log import get_task_logger
+from django.conf import settings
+
+from prowler.config.config import (
+    csv_file_suffix,
+    html_file_suffix,
+    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.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
+
+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),
+    ],
+}
+
+
+# Predefined mapping for output formats and their configurations
+OUTPUT_FORMATS_MAPPING = {
+    "csv": {
+        "class": CSV,
+        "suffix": csv_file_suffix,
+        "kwargs": {},
+    },
+    "json-ocsf": {"class": OCSF, "suffix": json_ocsf_file_suffix, "kwargs": {}},
+    "html": {"class": HTML, "suffix": html_file_suffix, "kwargs": {"stats": {}}},
+}
+
+
+def _compress_output_files(output_directory: str) -> str:
+    """
+    Compress output files from all configured output formats into a ZIP archive.
+    Args:
+        output_directory (str): The directory where the output files are located.
+            The function looks up all known suffixes in OUTPUT_FORMATS_MAPPING
+            and compresses those files into a single ZIP.
+    Returns:
+        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 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
+
+
+def get_s3_client():
+    """
+    Create and return a boto3 S3 client using AWS credentials from environment variables.
+
+    This function attempts to initialize an S3 client by reading the AWS access key, secret key,
+    session token, and region from environment variables. It then validates the client by listing
+    available S3 buckets. If an error occurs during this process (for example, due to missing or
+    invalid credentials), it falls back to creating an S3 client without explicitly provided credentials,
+    which may rely on other configuration sources (e.g., IAM roles).
+
+    Returns:
+        boto3.client: A configured S3 client instance.
+
+    Raises:
+        ClientError, NoCredentialsError, or ParamValidationError if both attempts to create a client fail.
+    """
+    s3_client = None
+    try:
+        s3_client = boto3.client(
+            "s3",
+            aws_access_key_id=settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID,
+            aws_secret_access_key=settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY,
+            aws_session_token=settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN,
+            region_name=settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION,
+        )
+        s3_client.list_buckets()
+    except (ClientError, NoCredentialsError, ParamValidationError, ValueError):
+        s3_client = boto3.client("s3")
+        s3_client.list_buckets()
+
+    return s3_client
+
+
+def _upload_to_s3(tenant_id: str, zip_path: str, scan_id: str) -> str:
+    """
+    Upload the specified ZIP file to an S3 bucket.
+    If the S3 bucket environment variables are not configured,
+    the function returns None without performing an upload.
+    Args:
+        tenant_id (str): The tenant identifier, used as part of the S3 key prefix.
+        zip_path (str): The local file system path to the ZIP file to be uploaded.
+        scan_id (str): The scan identifier, used as part of the S3 key prefix.
+    Returns:
+        str: The S3 URI of the uploaded file (e.g., "s3://<bucket>/<key>") if successful.
+        None: If the required environment variables for the S3 bucket are not set.
+    Raises:
+        botocore.exceptions.ClientError: If the upload attempt to S3 fails for any reason.
+    """
+    bucket = base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET
+    if not bucket:
+        return None
+
+    try:
+        s3 = get_s3_client()
+
+        # 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=bucket,
+            Key=zip_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
+) -> tuple[str, str]:
+    """
+    Generate a file system path for the output directory of a prowler scan.
+
+    This function constructs the output directory path by combining a base
+    temporary output directory, the tenant ID, the scan ID, and details about
+    the prowler provider along with a timestamp. The resulting path is used to
+    store the output files of a prowler scan.
+
+    Note:
+        This function depends on one external variable:
+          - `output_file_timestamp`: A timestamp (as a string) used to uniquely identify the output.
+
+    Args:
+        output_directory (str): The base output directory.
+        prowler_provider (object): An identifier or descriptor for the prowler provider.
+                                   Typically, this is a string indicating the provider (e.g., "aws").
+        tenant_id (str): The unique identifier for the tenant.
+        scan_id (str): The unique identifier for the scan.
+
+    Returns:
+        str: The constructed file system path for the prowler scan 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/compliance/prowler-output-2023-02-15T12:34:56'
+    """
+    path = (
+        f"{output_directory}/{tenant_id}/{scan_id}/prowler-output-"
+        f"{prowler_provider}-{output_file_timestamp}"
+    )
+    os.makedirs("/".join(path.split("/")[:-1]), exist_ok=True)
+
+    compliance_path = (
+        f"{output_directory}/{tenant_id}/{scan_id}/compliance/prowler-output-"
+        f"{prowler_provider}-{output_file_timestamp}"
+    )
+    os.makedirs("/".join(compliance_path.split("/")[:-1]), exist_ok=True)
+
+    return path, compliance_path

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

@@ -1,3 +1,4 @@
+import json
 import time
 from copy import deepcopy
 from datetime import datetime, timezone
@@ -6,6 +7,7 @@ from celery.utils.log import get_task_logger
 from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
 from django.db import IntegrityError, OperationalError
 from django.db.models import Case, Count, IntegerField, Sum, When
+from tasks.utils import CustomEncoder
 
 from api.compliance import (
     PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
@@ -17,6 +19,7 @@ from api.models import (
     Finding,
     Provider,
     Resource,
+    ResourceScanSummary,
     ResourceTag,
     Scan,
     ScanSummary,
@@ -119,6 +122,7 @@ def perform_prowler_scan(
     check_status_by_region = {}
     exception = None
     unique_resources = set()
+    scan_resource_cache: set[tuple[str, str, str, str]] = set()
     start_time = time.time()
 
     with rls_transaction(tenant_id):
@@ -191,6 +195,17 @@ def perform_prowler_scan(
                         if resource_instance.type != finding.resource_type:
                             resource_instance.type = finding.resource_type
                             updated_fields.append("type")
+                        if resource_instance.metadata != finding.resource_metadata:
+                            resource_instance.metadata = json.dumps(
+                                finding.resource_metadata, cls=CustomEncoder
+                            )
+                            updated_fields.append("metadata")
+                        if resource_instance.details != finding.resource_details:
+                            resource_instance.details = finding.resource_details
+                            updated_fields.append("details")
+                        if resource_instance.partition != finding.partition:
+                            resource_instance.partition = finding.partition
+                            updated_fields.append("partition")
                         if updated_fields:
                             with rls_transaction(tenant_id):
                                 resource_instance.save(update_fields=updated_fields)
@@ -267,6 +282,8 @@ def perform_prowler_scan(
                         check_id=finding.check_id,
                         scan=scan_instance,
                         first_seen_at=last_first_seen_at,
+                        muted=finding.muted,
+                        compliance=finding.compliance,
                     )
                     finding_instance.add_resources([resource_instance])
 
@@ -280,6 +297,16 @@ def perform_prowler_scan(
                     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):
                 scan_instance.progress = progress
@@ -299,57 +326,90 @@ 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"],
-                    )
-                )
-        with rls_transaction(tenant_id):
-            ComplianceOverview.objects.bulk_create(compliance_overview_objects)
-
     if exception is not None:
         raise exception
 
+    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=500
+            )
+    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}"
+        )
+
+    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
 
@@ -393,21 +453,21 @@ def aggregate_findings(tenant_id: str, scan_id: str):
         ).annotate(
             fail=Sum(
                 Case(
-                    When(status="FAIL", then=1),
+                    When(status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             _pass=Sum(
                 Case(
-                    When(status="PASS", then=1),
+                    When(status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
-            muted=Sum(
+            muted_count=Sum(
                 Case(
-                    When(status="MUTED", then=1),
+                    When(muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
@@ -415,63 +475,63 @@ def aggregate_findings(tenant_id: str, scan_id: str):
             total=Count("id"),
             new=Sum(
                 Case(
-                    When(delta="new", then=1),
+                    When(delta="new", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             changed=Sum(
                 Case(
-                    When(delta="changed", then=1),
+                    When(delta="changed", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             unchanged=Sum(
                 Case(
-                    When(delta__isnull=True, then=1),
+                    When(delta__isnull=True, muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             fail_new=Sum(
                 Case(
-                    When(delta="new", status="FAIL", then=1),
+                    When(delta="new", status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             fail_changed=Sum(
                 Case(
-                    When(delta="changed", status="FAIL", then=1),
+                    When(delta="changed", status="FAIL", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             pass_new=Sum(
                 Case(
-                    When(delta="new", status="PASS", then=1),
+                    When(delta="new", status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             pass_changed=Sum(
                 Case(
-                    When(delta="changed", status="PASS", then=1),
+                    When(delta="changed", status="PASS", muted=False, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             muted_new=Sum(
                 Case(
-                    When(delta="new", status="MUTED", then=1),
+                    When(delta="new", muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
             ),
             muted_changed=Sum(
                 Case(
-                    When(delta="changed", status="MUTED", then=1),
+                    When(delta="changed", muted=True, then=1),
                     default=0,
                     output_field=IntegerField(),
                 )
@@ -489,7 +549,7 @@ def aggregate_findings(tenant_id: str, scan_id: str):
                 region=agg["resources__region"],
                 fail=agg["fail"],
                 _pass=agg["_pass"],
-                muted=agg["muted"],
+                muted=agg["muted_count"],
                 total=agg["total"],
                 new=agg["new"],
                 changed=agg["changed"],

api/src/backend/tasks/tasks.py

@@ -1,14 +1,36 @@
-from celery import shared_task
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from shutil import rmtree
+
+from celery import chain, shared_task
+from celery.utils.log import get_task_logger
 from config.celery import RLSTask
+from config.django.base import DJANGO_FINDINGS_BATCH_SIZE, DJANGO_TMP_OUTPUT_DIRECTORY
 from django_celery_beat.models import PeriodicTask
+from tasks.jobs.backfill import backfill_resource_scan_summaries
 from tasks.jobs.connection import check_provider_connection
 from tasks.jobs.deletion import delete_provider, delete_tenant
+from tasks.jobs.export import (
+    COMPLIANCE_CLASS_MAP,
+    OUTPUT_FORMATS_MAPPING,
+    _compress_output_files,
+    _generate_output_directory,
+    _upload_to_s3,
+)
 from tasks.jobs.scan import aggregate_findings, perform_prowler_scan
-from tasks.utils import get_next_execution_datetime
+from tasks.utils import batched, get_next_execution_datetime
 
+from api.compliance import get_compliance_frameworks
 from api.db_utils import rls_transaction
 from api.decorators import set_tenant
-from api.models import Scan, StateChoices
+from api.models import Finding, Provider, Scan, ScanSummary, StateChoices
+from api.utils import initialize_prowler_provider
+from api.v1.serializers import ScanTaskSerializer
+from prowler.lib.check.compliance_models import Compliance
+from prowler.lib.outputs.compliance.generic.generic import GenericCompliance
+from prowler.lib.outputs.finding import Finding as FindingOutput
+
+logger = get_task_logger(__name__)
 
 
 @shared_task(base=RLSTask, name="provider-connection-check")
@@ -28,9 +50,10 @@ def check_provider_connection_task(provider_id: str):
     return check_provider_connection(provider_id=provider_id)
 
 
-@shared_task(base=RLSTask, name="provider-deletion")
-@set_tenant
-def delete_provider_task(provider_id: str):
+@shared_task(
+    base=RLSTask, name="provider-deletion", queue="deletion", autoretry_for=(Exception,)
+)
+def delete_provider_task(provider_id: str, tenant_id: str):
     """
     Task to delete a specific Provider instance.
 
@@ -38,6 +61,7 @@ def delete_provider_task(provider_id: str):
 
     Args:
         provider_id (str): The primary key of the `Provider` instance to be deleted.
+        tenant_id (str): Tenant ID the provider belongs to.
 
     Returns:
         tuple: A tuple containing:
@@ -45,7 +69,7 @@ def delete_provider_task(provider_id: str):
             - A dictionary with the count of deleted instances per model,
               including related models if cascading deletes were triggered.
     """
-    return delete_provider(pk=provider_id)
+    return delete_provider(tenant_id=tenant_id, pk=provider_id)
 
 
 @shared_task(base=RLSTask, name="scan-perform", queue="scans")
@@ -68,13 +92,22 @@ def perform_scan_task(
     Returns:
         dict: The result of the scan execution, typically including the status and results of the performed checks.
     """
-    return perform_prowler_scan(
+    result = perform_prowler_scan(
         tenant_id=tenant_id,
         scan_id=scan_id,
         provider_id=provider_id,
         checks_to_execute=checks_to_execute,
     )
 
+    chain(
+        perform_scan_summary_task.si(tenant_id, scan_id),
+        generate_outputs.si(
+            scan_id=scan_id, provider_id=provider_id, tenant_id=tenant_id
+        ),
+    ).apply_async()
+
+    return result
+
 
 @shared_task(base=RLSTask, bind=True, name="scan-perform-scheduled", queue="scans")
 def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
@@ -102,6 +135,43 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
         periodic_task_instance = PeriodicTask.objects.get(
             name=f"scan-perform-scheduled-{provider_id}"
         )
+
+        executed_scan = Scan.objects.filter(
+            tenant_id=tenant_id,
+            provider_id=provider_id,
+            task__task_runner_task__task_id=task_id,
+        ).order_by("completed_at")
+
+        if (
+            Scan.objects.filter(
+                tenant_id=tenant_id,
+                provider_id=provider_id,
+                trigger=Scan.TriggerChoices.SCHEDULED,
+                state=StateChoices.EXECUTING,
+                scheduler_task_id=periodic_task_instance.id,
+                scheduled_at__date=datetime.now(timezone.utc).date(),
+            ).exists()
+            or executed_scan.exists()
+        ):
+            # Duplicated task execution due to visibility timeout or scan is already running
+            logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
+            try:
+                affected_scan = executed_scan.first()
+                if not affected_scan:
+                    raise ValueError(
+                        "Error retrieving affected scan details after detecting duplicated scheduled "
+                        "scan."
+                    )
+                # Return the affected scan details to avoid losing data
+                serializer = ScanTaskSerializer(instance=affected_scan)
+            except Exception as duplicated_scan_exception:
+                logger.error(
+                    f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
+                    f"{str(duplicated_scan_exception)}"
+                )
+                raise duplicated_scan_exception
+            return serializer.data
+
         next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
         scan_instance, _ = Scan.objects.get_or_create(
             tenant_id=tenant_id,
@@ -109,7 +179,11 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
             trigger=Scan.TriggerChoices.SCHEDULED,
             state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
             scheduler_task_id=periodic_task_instance.id,
-            defaults={"state": StateChoices.SCHEDULED},
+            defaults={
+                "state": StateChoices.SCHEDULED,
+                "name": "Daily scheduled scan",
+                "scheduled_at": next_scan_datetime - timedelta(days=1),
+            },
         )
 
         scan_instance.task_id = task_id
@@ -135,12 +209,13 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
                 scheduler_task_id=periodic_task_instance.id,
             )
 
-    perform_scan_summary_task.apply_async(
-        kwargs={
-            "tenant_id": tenant_id,
-            "scan_id": str(scan_instance.id),
-        }
-    )
+    chain(
+        perform_scan_summary_task.si(tenant_id, scan_instance.id),
+        generate_outputs.si(
+            scan_id=str(scan_instance.id), provider_id=provider_id, tenant_id=tenant_id
+        ),
+    ).apply_async()
+
     return result
 
 
@@ -149,6 +224,150 @@ def perform_scan_summary_task(tenant_id: str, scan_id: str):
     return aggregate_findings(tenant_id=tenant_id, scan_id=scan_id)
 
 
-@shared_task(name="tenant-deletion")
+@shared_task(name="tenant-deletion", queue="deletion", autoretry_for=(Exception,))
 def delete_tenant_task(tenant_id: str):
     return delete_tenant(pk=tenant_id)
+
+
+@shared_task(
+    base=RLSTask,
+    name="scan-report",
+    queue="scan-reports",
+)
+@set_tenant(keep_tenant=True)
+def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
+    """
+    Process findings in batches and generate output files in multiple formats.
+
+    This function retrieves findings associated with a scan, processes them
+    in batches of 50, and writes each batch to the corresponding output files.
+    It reuses output writer instances across batches, updates them with each
+    batch of transformed findings, and uses a flag to indicate when the final
+    batch is being processed. Finally, the output files are compressed and
+    uploaded to S3.
+
+    Args:
+        tenant_id (str): The tenant identifier.
+        scan_id (str): The scan identifier.
+        provider_id (str): The provider_id id to be used in generating outputs.
+    """
+    # Check if the scan has findings
+    if not ScanSummary.objects.filter(scan_id=scan_id).exists():
+        logger.info(f"No findings found for scan {scan_id}")
+        return {"upload": False}
+
+    provider_obj = Provider.objects.get(id=provider_id)
+    prowler_provider = initialize_prowler_provider(provider_obj)
+    provider_uid = provider_obj.uid
+    provider_type = provider_obj.provider
+
+    frameworks_bulk = Compliance.get_bulk(provider_type)
+    frameworks_avail = get_compliance_frameworks(provider_type)
+    out_dir, comp_dir = _generate_output_directory(
+        DJANGO_TMP_OUTPUT_DIRECTORY, provider_uid, tenant_id, scan_id
+    )
+
+    def get_writer(writer_map, name, factory, is_last):
+        """
+        Return existing writer_map[name] or create via factory().
+        In both cases set `.close_file = is_last`.
+        """
+        initialization = False
+        if name not in writer_map:
+            writer_map[name] = factory()
+            initialization = True
+        w = writer_map[name]
+        w.close_file = is_last
+
+        return w, initialization
+
+    output_writers = {}
+    compliance_writers = {}
+
+    scan_summary = FindingOutput._transform_findings_stats(
+        ScanSummary.objects.filter(scan_id=scan_id)
+    )
+
+    qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid").iterator()
+    for batch, is_last in batched(qs, DJANGO_FINDINGS_BATCH_SIZE):
+        fos = [FindingOutput.transform_api_finding(f, prowler_provider) for f in batch]
+
+        # Outputs
+        for mode, cfg in OUTPUT_FORMATS_MAPPING.items():
+            cls = cfg["class"]
+            suffix = cfg["suffix"]
+            extra = cfg.get("kwargs", {}).copy()
+            if mode == "html":
+                extra.update(provider=prowler_provider, stats=scan_summary)
+
+            writer, initialization = get_writer(
+                output_writers,
+                cls,
+                lambda cls=cls, fos=fos, suffix=suffix: cls(
+                    findings=fos,
+                    file_path=out_dir,
+                    file_extension=suffix,
+                    from_cli=False,
+                ),
+                is_last,
+            )
+            if not initialization:
+                writer.transform(fos)
+            writer.batch_write_data_to_file(**extra)
+            writer._data.clear()
+
+        # Compliance CSVs
+        for name in frameworks_avail:
+            compliance_obj = frameworks_bulk[name]
+
+            klass = GenericCompliance
+            for condition, cls in COMPLIANCE_CLASS_MAP.get(provider_type, []):
+                if condition(name):
+                    klass = cls
+                    break
+
+            filename = f"{comp_dir}_{name}.csv"
+
+            writer, initialization = get_writer(
+                compliance_writers,
+                name,
+                lambda klass=klass, fos=fos: klass(
+                    findings=fos,
+                    compliance=compliance_obj,
+                    file_path=filename,
+                    from_cli=False,
+                ),
+                is_last,
+            )
+            if not initialization:
+                writer.transform(fos, compliance_obj, name)
+            writer.batch_write_data_to_file()
+            writer._data.clear()
+
+    compressed = _compress_output_files(out_dir)
+    upload_uri = _upload_to_s3(tenant_id, compressed, scan_id)
+
+    if upload_uri:
+        try:
+            rmtree(Path(compressed).parent, ignore_errors=True)
+        except Exception as e:
+            logger.error(f"Error deleting output files: {e}")
+        final_location, did_upload = upload_uri, True
+    else:
+        final_location, did_upload = compressed, False
+
+    Scan.all_objects.filter(id=scan_id).update(output_location=final_location)
+    logger.info(f"Scan outputs at {final_location}")
+    return {"upload": did_upload}
+
+
+@shared_task(name="backfill-scan-resource-summaries", queue="backfill")
+def backfill_scan_resource_summaries_task(tenant_id: str, scan_id: str):
+    """
+    Tries to backfill the resource scan summaries table for a given scan.
+
+    Args:
+        tenant_id (str): The tenant identifier.
+        scan_id (str): The scan identifier.
+    """
+    return backfill_resource_scan_summaries(tenant_id=tenant_id, scan_id=scan_id)

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

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

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

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

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

@@ -0,0 +1,147 @@
+import os
+import zipfile
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+from botocore.exceptions import ClientError
+from tasks.jobs.export import (
+    _compress_output_files,
+    _generate_output_directory,
+    _upload_to_s3,
+    get_s3_client,
+)
+
+
+@pytest.mark.django_db
+class TestOutputs:
+    def test_compress_output_files_creates_zip(self, tmpdir):
+        base_tmp = Path(str(tmpdir.mkdir("compress_output")))
+        output_dir = base_tmp / "output"
+        output_dir.mkdir()
+        file_path = output_dir / "result.csv"
+        file_path.write_text("data")
+
+        zip_path = _compress_output_files(str(output_dir))
+
+        assert zip_path.endswith(".zip")
+        assert os.path.exists(zip_path)
+        with zipfile.ZipFile(zip_path, "r") as zipf:
+            assert "output/result.csv" in zipf.namelist()
+
+    @patch("tasks.jobs.export.boto3.client")
+    @patch("tasks.jobs.export.settings")
+    def test_get_s3_client_success(self, mock_settings, mock_boto_client):
+        mock_settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = "test"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = "test"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = "token"
+        mock_settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = "eu-west-1"
+
+        client_mock = MagicMock()
+        mock_boto_client.return_value = client_mock
+
+        client = get_s3_client()
+        assert client is not None
+        client_mock.list_buckets.assert_called()
+
+    @patch("tasks.jobs.export.boto3.client")
+    @patch("tasks.jobs.export.settings")
+    def test_get_s3_client_fallback(self, mock_settings, mock_boto_client):
+        mock_boto_client.side_effect = [
+            ClientError({"Error": {"Code": "403"}}, "ListBuckets"),
+            MagicMock(),
+        ]
+        client = get_s3_client()
+        assert client is not None
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_success(self, mock_base, mock_get_client, tmpdir):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
+
+        base_tmp = Path(str(tmpdir.mkdir("upload_success")))
+        zip_path = base_tmp / "outputs.zip"
+        zip_path.write_bytes(b"dummy")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "report.csv").write_text("ok")
+
+        client_mock = MagicMock()
+        mock_get_client.return_value = client_mock
+
+        result = _upload_to_s3("tenant-id", str(zip_path), "scan-id")
+
+        expected_uri = "s3://test-bucket/tenant-id/scan-id/outputs.zip"
+        assert result == expected_uri
+        assert client_mock.upload_file.call_count == 2
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_missing_bucket(self, mock_base, mock_get_client):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = ""
+        result = _upload_to_s3("tenant", "/tmp/fake.zip", "scan")
+        assert result is None
+
+    @patch("tasks.jobs.export.get_s3_client")
+    @patch("tasks.jobs.export.base")
+    def test_upload_to_s3_skips_non_files(self, mock_base, mock_get_client, tmpdir):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
+        base_tmp = Path(str(tmpdir.mkdir("upload_skips_non_files")))
+
+        zip_path = base_tmp / "results.zip"
+        zip_path.write_bytes(b"zip")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "subdir").mkdir()
+
+        client_mock = MagicMock()
+        mock_get_client.return_value = client_mock
+
+        result = _upload_to_s3("tenant", str(zip_path), "scan")
+
+        expected_uri = "s3://test-bucket/tenant/scan/results.zip"
+        assert result == expected_uri
+        client_mock.upload_file.assert_called_once()
+
+    @patch(
+        "tasks.jobs.export.get_s3_client",
+        side_effect=ClientError({"Error": {}}, "Upload"),
+    )
+    @patch("tasks.jobs.export.base")
+    @patch("tasks.jobs.export.logger.error")
+    def test_upload_to_s3_failure_logs_error(
+        self, mock_logger, mock_base, mock_get_client, tmpdir
+    ):
+        mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "bucket"
+
+        base_tmp = Path(str(tmpdir.mkdir("upload_failure_logs")))
+        zip_path = base_tmp / "zipfile.zip"
+        zip_path.write_bytes(b"zip")
+
+        compliance_dir = base_tmp / "compliance"
+        compliance_dir.mkdir()
+        (compliance_dir / "report.csv").write_text("csv")
+
+        _upload_to_s3("tenant", str(zip_path), "scan")
+        mock_logger.assert_called()
+
+    def test_generate_output_directory_creates_paths(self, tmpdir):
+        from prowler.config.config import output_file_timestamp
+
+        base_tmp = Path(str(tmpdir.mkdir("generate_output")))
+        base_dir = str(base_tmp)
+        tenant_id = "t1"
+        scan_id = "s1"
+        provider = "aws"
+
+        path, compliance = _generate_output_directory(
+            base_dir, provider, tenant_id, scan_id
+        )
+
+        assert os.path.isdir(os.path.dirname(path))
+        assert os.path.isdir(os.path.dirname(compliance))
+
+        assert path.endswith(f"{provider}-{output_file_timestamp}")
+        assert compliance.endswith(f"{provider}-{output_file_timestamp}")

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

@@ -1,3 +1,4 @@
+import json
 import uuid
 from unittest.mock import MagicMock, patch
 
@@ -7,6 +8,7 @@ from tasks.jobs.scan import (
     _store_resources,
     perform_prowler_scan,
 )
+from tasks.utils import CustomEncoder
 
 from api.models import (
     Finding,
@@ -107,7 +109,13 @@ class TestPerformScan:
             finding.service_name = "service_name"
             finding.resource_type = "resource_type"
             finding.resource_tags = {"tag1": "value1", "tag2": "value2"}
+            finding.muted = False
             finding.raw = {}
+            finding.resource_metadata = {"test": "metadata"}
+            finding.resource_details = {"details": "test"}
+            finding.partition = "partition"
+            finding.muted = True
+            finding.compliance = {"compliance1": "PASS"}
 
             # Mock the ProwlerScan instance
             mock_prowler_scan_instance = MagicMock()
@@ -145,6 +153,8 @@ class TestPerformScan:
         assert scan_finding.severity == finding.severity
         assert scan_finding.check_id == finding.check_id
         assert scan_finding.raw_result == finding.raw
+        assert scan_finding.muted
+        assert scan_finding.compliance == finding.compliance
 
         assert scan_resource.tenant == tenant
         assert scan_resource.uid == finding.resource_uid
@@ -152,6 +162,11 @@ class TestPerformScan:
         assert scan_resource.service == finding.service_name
         assert scan_resource.type == finding.resource_type
         assert scan_resource.name == finding.resource_name
+        assert scan_resource.metadata == json.dumps(
+            finding.resource_metadata, cls=CustomEncoder
+        )
+        assert scan_resource.details == f"{finding.resource_details}"
+        assert scan_resource.partition == finding.partition
 
         # Assert that the resource tags have been created and associated
         tags = scan_resource.tags.all()

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

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

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

@@ -4,7 +4,7 @@ from unittest.mock import patch
 import pytest
 from django_celery_beat.models import IntervalSchedule, PeriodicTask
 from django_celery_results.models import TaskResult
-from tasks.utils import get_next_execution_datetime
+from tasks.utils import batched, get_next_execution_datetime
 
 
 @pytest.mark.django_db
@@ -74,3 +74,29 @@ class TestGetNextExecutionDatetime:
             get_next_execution_datetime(
                 task_id=task_result.task_id, provider_id="nonexistent"
             )
+
+
+class TestBatchedFunction:
+    def test_empty_iterable(self):
+        result = list(batched([], 3))
+        assert result == [([], True)]
+
+    def test_exact_batches(self):
+        result = list(batched([1, 2, 3, 4], 2))
+        expected = [([1, 2], False), ([3, 4], False), ([], True)]
+        assert result == expected
+
+    def test_inexact_batches(self):
+        result = list(batched([1, 2, 3, 4, 5], 2))
+        expected = [([1, 2], False), ([3, 4], False), ([5], True)]
+        assert result == expected
+
+    def test_batch_size_one(self):
+        result = list(batched([1, 2, 3], 1))
+        expected = [([1], False), ([2], False), ([3], False), ([], True)]
+        assert result == expected
+
+    def test_batch_size_greater_than_length(self):
+        result = list(batched([1, 2, 3], 5))
+        expected = [([1, 2, 3], True)]
+        assert result == expected

api/src/backend/tasks/utils.py

@@ -1,9 +1,32 @@
+import json
 from datetime import datetime, timedelta, timezone
+from enum import Enum
 
 from django_celery_beat.models import PeriodicTask
 from django_celery_results.models import TaskResult
 
 
+class CustomEncoder(json.JSONEncoder):
+    def default(self, o):
+        # Enum serialization
+        if isinstance(o, Enum):
+            return o.value
+        # Datetime and timedelta serialization
+        if isinstance(o, datetime):
+            return o.isoformat(timespec="seconds")
+        if isinstance(o, timedelta):
+            return o.total_seconds()
+
+        # Custom object serialization
+        try:
+            return super().default(o)
+        except TypeError:
+            try:
+                return o.__dict__
+            except AttributeError:
+                return str(o)
+
+
 def get_next_execution_datetime(task_id: int, provider_id: str) -> datetime:
     task_instance = TaskResult.objects.get(task_id=task_id)
     try:
@@ -24,3 +47,27 @@ def get_next_execution_datetime(task_id: int, provider_id: str) -> datetime:
     )
 
     return current_scheduled_time + timedelta(**{interval.period: interval.every})
+
+
+def batched(iterable, batch_size):
+    """
+    Yield successive batches from an iterable.
+
+    Args:
+        iterable: An iterable source of items.
+        batch_size (int): The number of items per batch.
+
+    Yields:
+        tuple: A pair (batch, is_last_batch) where:
+            - batch (list): A list of items (with length equal to batch_size,
+              except possibly for the last batch).
+            - is_last_batch (bool): True if this is the final batch, False otherwise.
+    """
+    batch = []
+    for item in iterable:
+        batch.append(item)
+        if len(batch) == batch_size:
+            yield batch, False
+            batch = []
+
+    yield batch, True

api/tests/performance/benchmark.py

@@ -0,0 +1,156 @@
+#!/usr/bin/env python3
+import argparse
+import os
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import pandas as pd
+
+plt.style.use("ggplot")
+
+
+def run_locust(
+    locust_file: str,
+    host: str,
+    users: int,
+    hatch_rate: int,
+    run_time: str,
+    csv_prefix: Path,
+) -> Path:
+    artifacts_dir = Path("artifacts")
+    artifacts_dir.mkdir(parents=True, exist_ok=True)
+
+    cmd = [
+        "locust",
+        "-f",
+        f"scenarios/{locust_file}",
+        "--headless",
+        "-u",
+        str(users),
+        "-r",
+        str(hatch_rate),
+        "-t",
+        run_time,
+        "--host",
+        host,
+        "--csv",
+        str(artifacts_dir / csv_prefix.name),
+    ]
+    print(f"Running Locust: {' '.join(cmd)}")
+    process = subprocess.run(cmd)
+    if process.returncode:
+        sys.exit("Locust execution failed")
+
+    stats_file = artifacts_dir / f"{csv_prefix.stem}_stats.csv"
+    if not stats_file.exists():
+        sys.exit(f"Stats CSV not found: {stats_file}")
+    return stats_file
+
+
+def load_percentiles(csv_path: Path) -> pd.DataFrame:
+    df = pd.read_csv(csv_path)
+    mapping = {"50%": "p50", "75%": "p75", "90%": "p90", "95%": "p95"}
+    available = [col for col in mapping if col in df.columns]
+    renamed = {col: mapping[col] for col in available}
+    df = df.rename(columns=renamed).set_index("Name")[renamed.values()]
+    return df.drop(index=["Aggregated"], errors="ignore")
+
+
+def sanitize_label(label: str) -> str:
+    text = re.sub(r"[^\w]+", "_", label.strip().lower())
+    return text.strip("_")
+
+
+def plot_multi_comparison(metrics: dict[str, pd.DataFrame]) -> None:
+    common = sorted(set.intersection(*(set(df.index) for df in metrics.values())))
+    percentiles = list(next(iter(metrics.values())).columns)
+    groups = len(metrics)
+    width = 0.8 / groups
+
+    for endpoint in common:
+        fig, ax = plt.subplots(figsize=(10, 5), dpi=100)
+        for idx, (label, df) in enumerate(metrics.items()):
+            series = df.loc[endpoint]
+            positions = [
+                i + (idx - groups / 2) * width + width / 2
+                for i in range(len(percentiles))
+            ]
+            bars = ax.bar(positions, series.values, width, label=label)
+            for bar in bars:
+                height = bar.get_height()
+                ax.annotate(
+                    f"{int(height)}",
+                    xy=(bar.get_x() + bar.get_width() / 2, height),
+                    xytext=(0, 3),
+                    textcoords="offset points",
+                    ha="center",
+                    va="bottom",
+                    fontsize=8,
+                )
+
+        ax.set_xticks(range(len(percentiles)))
+        ax.set_xticklabels(percentiles)
+        ax.set_ylabel("Latency (ms)")
+        ax.set_title(endpoint, fontsize=12)
+        ax.grid(True, axis="y", linestyle="--", alpha=0.7)
+
+        fig.tight_layout()
+        fig.subplots_adjust(right=0.75)
+        ax.legend(loc="center left", bbox_to_anchor=(1, 0.5), framealpha=0.9)
+
+        output = Path("artifacts") / f"comparison_{sanitize_label(endpoint)}.png"
+        plt.savefig(output)
+        plt.close(fig)
+        print(f"Saved chart: {output}")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Run Locust and compare metrics")
+    parser.add_argument("--locustfile", required=True, help="Locust file in scenarios/")
+    parser.add_argument("--host", required=True, help="Target host URL")
+    parser.add_argument(
+        "--users", type=int, default=10, help="Number of simulated users"
+    )
+    parser.add_argument("--rate", type=int, default=1, help="Hatch rate per second")
+    parser.add_argument("--time", default="1m", help="Test duration (e.g. 30s, 1m)")
+    parser.add_argument(
+        "--metrics-dir", default="baselines", help="Directory with CSV baselines"
+    )
+    parser.add_argument("--version", default="current", help="Test version")
+    args = parser.parse_args()
+
+    metrics_dir = Path(args.metrics_dir)
+    os.makedirs(metrics_dir, exist_ok=True)
+
+    metrics_data: dict[str, pd.DataFrame] = {}
+    for csv_file in sorted(metrics_dir.glob("*.csv")):
+        metrics_data[csv_file.stem] = load_percentiles(csv_file)
+
+    current_prefix = Path(args.version)
+    current_csv = run_locust(
+        locust_file=args.locustfile,
+        host=args.host,
+        users=args.users,
+        hatch_rate=args.rate,
+        run_time=args.time,
+        csv_prefix=current_prefix,
+    )
+    metrics_data[args.version] = load_percentiles(current_csv)
+
+    for endpoint in sorted(
+        set.intersection(*(set(df.index) for df in metrics_data.values()))
+    ):
+        parts = [endpoint]
+        for label, df in metrics_data.items():
+            s = df.loc[endpoint]
+            parts.append(f"{label}: p50 {s.p50}, p75 {s.p75}, p90 {s.p90}, p95 {s.p95}")
+        print(" | ".join(parts))
+
+    plot_multi_comparison(metrics_data)
+
+
+if __name__ == "__main__":
+    main()