Compare commits

..

3 Commits

Author SHA1 Message Date
Alan Buscaglia 173659ae0b fix(ci): prevent grep exit code 1 from failing empty dir check
- Add || true to grep -v that filters empty lines from VALID_PATHS
- GitHub Actions bash uses set -eo pipefail, so grep returning 1 (no
  matches) killed the script before reaching the graceful exit 0
2026-03-12 11:33:33 +01:00
Alan Buscaglia 37abe6b47e test(ci): add path resolution tests and architecture documentation
- Add test script for E2E path resolution logic (18 edge case scenarios)
- Add developer guide for test impact analysis system
2026-03-12 10:13:00 +01:00
Alan Buscaglia 7b2ad97317 fix(ci): gracefully skip E2E when test directories are empty
- Filter out resolved test paths that contain no spec/test files
- Exit gracefully instead of failing with Playwright "No tests found"
- Supports forward-looking e2e patterns for modules without tests yet
2026-03-12 09:58:41 +01:00
398 changed files with 3580 additions and 20833 deletions
+2 -10
View File
@@ -26,18 +26,10 @@ runs:
if: github.event_name == 'pull_request' && github.base_ref == 'master' && github.repository == 'prowler-cloud/prowler'
shell: bash
working-directory: ${{ inputs.working-directory }}
env:
HEAD_REPO: ${{ github.event.pull_request.head.repo.full_name }}
run: |
BRANCH_NAME="${GITHUB_HEAD_REF:-${GITHUB_REF_NAME}}"
UPSTREAM="prowler-cloud/prowler"
if [ "$HEAD_REPO" != "$UPSTREAM" ]; then
echo "Fork PR detected (${HEAD_REPO}), rewriting VCS URL to fork"
sed -i "s|git+https://github.com/prowler-cloud/prowler\([^@]*\)@master|git+https://github.com/${HEAD_REPO}\1@$BRANCH_NAME|g" pyproject.toml
else
echo "Same-repo PR, using branch: $BRANCH_NAME"
sed -i "s|\(git+https://github.com/prowler-cloud/prowler[^@]*\)@master|\1@$BRANCH_NAME|g" pyproject.toml
fi
echo "Using branch: $BRANCH_NAME"
sed -i "s|\(git+https://github.com/prowler-cloud/prowler[^@]*\)@master|\1@$BRANCH_NAME|g" pyproject.toml
- name: Install poetry
shell: bash
+7 -7
View File
@@ -28,7 +28,7 @@ jobs:
current_api_version: ${{ steps.get_api_version.outputs.current_api_version }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -80,7 +80,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -118,7 +118,7 @@ jobs:
git --no-pager diff
- name: Create PR for next API minor version to master
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -137,7 +137,7 @@ jobs:
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
- name: Checkout version branch
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: v${{ needs.detect-release-type.outputs.major_version }}.${{ needs.detect-release-type.outputs.minor_version }}
persist-credentials: false
@@ -177,7 +177,7 @@ jobs:
git --no-pager diff
- name: Create PR for first API patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -205,7 +205,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -255,7 +255,7 @@ jobs:
git --no-pager diff
- name: Create PR for next API patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+2 -2
View File
@@ -33,14 +33,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for API changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
api/**
+3 -3
View File
@@ -42,17 +42,17 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Initialize CodeQL
uses: github/codeql-action/init@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/init@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/api-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/analyze@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
category: '/language:${{ matrix.language }}'
@@ -57,7 +57,7 @@ jobs:
message-ts: ${{ steps.slack-notification.outputs.ts }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -95,12 +95,12 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -111,7 +111,7 @@ jobs:
- name: Build and push API container for ${{ matrix.arch }}
id: container-push
if: github.event_name == 'push' || github.event_name == 'release' || github.event_name == 'workflow_dispatch'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.WORKING_DIRECTORY }}
push: true
@@ -129,7 +129,7 @@ jobs:
steps:
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -161,7 +161,7 @@ jobs:
- name: Install regctl
if: always()
uses: regclient/actions/regctl-installer@da9319db8e44e8b062b3a147e1dfb2f574d41a03 # main
uses: regclient/actions/regctl-installer@f61d18f46c86af724a9c804cb9ff2a6fec741c7c # main
- name: Cleanup intermediate architecture tags
if: always()
@@ -180,7 +180,7 @@ jobs:
timeout-minutes: 5
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+5 -5
View File
@@ -28,14 +28,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check if Dockerfile changed
id: dockerfile-changed
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: api/Dockerfile
@@ -66,14 +66,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for API changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: api/**
files_ignore: |
@@ -88,7 +88,7 @@ jobs:
- name: Build container for ${{ matrix.arch }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.API_WORKING_DIR }}
push: false
+3 -4
View File
@@ -33,14 +33,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for API changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
api/**
@@ -64,9 +64,8 @@ jobs:
- name: Safety
if: steps.check-changes.outputs.any_changed == 'true'
run: poetry run safety check --ignore 79023,79027,86217
run: poetry run safety check --ignore 79023,79027
# TODO: 79023 & 79027 knack ReDoS until `azure-cli-core` (via `cartography`) allows `knack` >=0.13.0
# TODO: 86217 because `alibabacloud-tea-openapi == 0.4.3` don't let us upgrade `cryptography >= 46.0.0`
- name: Vulture
if: steps.check-changes.outputs.any_changed == 'true'
+2 -2
View File
@@ -73,14 +73,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for API changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
api/**
+1 -1
View File
@@ -34,7 +34,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+7 -7
View File
@@ -28,7 +28,7 @@ jobs:
current_docs_version: ${{ steps.get_docs_version.outputs.current_docs_version }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -80,7 +80,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -114,7 +114,7 @@ jobs:
git --no-pager diff
- name: Create PR for documentation update to master
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -137,7 +137,7 @@ jobs:
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
- name: Checkout version branch
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: v${{ needs.detect-release-type.outputs.major_version }}.${{ needs.detect-release-type.outputs.minor_version }}
persist-credentials: false
@@ -174,7 +174,7 @@ jobs:
git --no-pager diff
- name: Create PR for documentation update to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -205,7 +205,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -245,7 +245,7 @@ jobs:
git --no-pager diff
- name: Create PR for documentation update to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+1 -1
View File
@@ -23,7 +23,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
fetch-depth: 0
persist-credentials: false
@@ -56,7 +56,7 @@ jobs:
message-ts: ${{ steps.slack-notification.outputs.ts }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -93,12 +93,12 @@ jobs:
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -109,7 +109,7 @@ jobs:
- name: Build and push MCP container for ${{ matrix.arch }}
id: container-push
if: github.event_name == 'push' || github.event_name == 'release' || github.event_name == 'workflow_dispatch'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.WORKING_DIRECTORY }}
push: true
@@ -135,7 +135,7 @@ jobs:
steps:
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -186,7 +186,7 @@ jobs:
timeout-minutes: 5
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+5 -5
View File
@@ -28,14 +28,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check if Dockerfile changed
id: dockerfile-changed
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: mcp_server/Dockerfile
@@ -65,14 +65,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for MCP changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: mcp_server/**
files_ignore: |
@@ -85,7 +85,7 @@ jobs:
- name: Build MCP container for ${{ matrix.arch }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.MCP_WORKING_DIR }}
push: false
+2 -2
View File
@@ -60,7 +60,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -70,7 +70,7 @@ jobs:
enable-cache: false
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
+2 -2
View File
@@ -29,7 +29,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
fetch-depth: 0
# zizmor: ignore[artipacked]
@@ -37,7 +37,7 @@ jobs:
- name: Get changed files
id: changed-files
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
api/**
+2 -2
View File
@@ -26,7 +26,7 @@ jobs:
steps:
- name: Checkout PR head
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: ${{ github.event.pull_request.head.sha }}
fetch-depth: 0
@@ -34,7 +34,7 @@ jobs:
- name: Get changed files
id: changed-files
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: '**'
+3 -3
View File
@@ -27,14 +27,14 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
fetch-depth: 0
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: '3.12'
@@ -345,7 +345,7 @@ jobs:
- name: Create PR for API dependency update
if: ${{ env.PATCH_VERSION == '0' }}
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
commit-message: 'chore(api): update prowler dependency to ${{ env.BRANCH_NAME }} for release ${{ env.PROWLER_VERSION }}'
+6 -6
View File
@@ -67,7 +67,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -96,7 +96,7 @@ jobs:
git --no-pager diff
- name: Create PR for next minor version to master
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -115,7 +115,7 @@ jobs:
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
- name: Checkout version branch
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: v${{ needs.detect-release-type.outputs.major_version }}.${{ needs.detect-release-type.outputs.minor_version }}
persist-credentials: false
@@ -148,7 +148,7 @@ jobs:
git --no-pager diff
- name: Create PR for first patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -176,7 +176,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -211,7 +211,7 @@ jobs:
git --no-pager diff
- name: Create PR for next patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -20,7 +20,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+3 -3
View File
@@ -31,14 +31,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for SDK changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: ./**
files_ignore: |
@@ -67,7 +67,7 @@ jobs:
- name: Set up Python ${{ matrix.python-version }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ matrix.python-version }}
cache: 'poetry'
+3 -3
View File
@@ -49,17 +49,17 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Initialize CodeQL
uses: github/codeql-action/init@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/init@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/sdk-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/analyze@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
category: '/language:${{ matrix.language }}'
+10 -10
View File
@@ -61,12 +61,12 @@ jobs:
stable_tag: ${{ steps.get-prowler-version.outputs.stable_tag }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
@@ -117,7 +117,7 @@ jobs:
message-ts: ${{ steps.slack-notification.outputs.ts }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -155,18 +155,18 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to Public ECR
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
registry: public.ecr.aws
username: ${{ secrets.PUBLIC_ECR_AWS_ACCESS_KEY_ID }}
@@ -180,7 +180,7 @@ jobs:
- name: Build and push SDK container for ${{ matrix.arch }}
id: container-push
if: github.event_name == 'push' || github.event_name == 'release' || github.event_name == 'workflow_dispatch'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: .
file: ${{ env.DOCKERFILE_PATH }}
@@ -199,13 +199,13 @@ jobs:
steps:
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to Public ECR
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
registry: public.ecr.aws
username: ${{ secrets.PUBLIC_ECR_AWS_ACCESS_KEY_ID }}
@@ -266,7 +266,7 @@ jobs:
timeout-minutes: 5
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+5 -5
View File
@@ -27,14 +27,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check if Dockerfile changed
id: dockerfile-changed
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: Dockerfile
@@ -65,14 +65,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for SDK changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: ./**
files_ignore: |
@@ -101,7 +101,7 @@ jobs:
- name: Build SDK container for ${{ matrix.arch }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: .
push: false
+4 -4
View File
@@ -59,7 +59,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -67,7 +67,7 @@ jobs:
run: pipx install poetry==2.1.1
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
@@ -92,7 +92,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -100,7 +100,7 @@ jobs:
run: pipx install poetry==2.1.1
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
@@ -25,13 +25,13 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: 'master'
persist-credentials: false
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: 'pip'
@@ -40,7 +40,7 @@ jobs:
run: pip install boto3
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@8df5847569e6427dd6c4fb1cf565c83acfa8afa7 # v6.0.0
uses: aws-actions/configure-aws-credentials@61815dcd50bd041e203e49132bacad1fd04d2708 # v5.1.1
with:
aws-region: ${{ env.AWS_REGION }}
role-to-assume: ${{ secrets.DEV_IAM_ROLE_ARN }}
@@ -51,7 +51,7 @@ jobs:
- name: Create pull request
id: create-pr
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
author: 'prowler-bot <179230569+prowler-bot@users.noreply.github.com>'
@@ -23,13 +23,13 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: 'master'
persist-credentials: false
- name: Set up Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: 'pip'
@@ -48,7 +48,7 @@ jobs:
- name: Create pull request
id: create-pr
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
author: 'prowler-bot <179230569+prowler-bot@users.noreply.github.com>'
@@ -72,13 +72,12 @@ jobs:
This PR updates the `OCI_COMMERCIAL_REGIONS` dictionary in `prowler/providers/oraclecloud/config.py` with the latest regions fetched from the OCI Identity API (`list_regions()`).
- Government regions (`OCI_GOVERNMENT_REGIONS`) are preserved unchanged
- DOD regions (`OCI_US_DOD_REGIONS`) are preserved unchanged
- Region display names are mapped from Oracle's official documentation
### Checklist
- [x] This is an automated update from OCI official sources
- [x] Government regions (us-langley-1, us-luke-1) and DOD regions (us-gov-ashburn-1, us-gov-phoenix-1, us-gov-chicago-1) are preserved
- [x] Government regions (us-langley-1, us-luke-1) preserved
- [x] No manual review of region data required
### License
+3 -3
View File
@@ -24,14 +24,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for SDK changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files:
./**
@@ -62,7 +62,7 @@ jobs:
- name: Set up Python 3.12
if: steps.check-changes.outputs.any_changed == 'true'
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: '3.12'
cache: 'poetry'
+17 -17
View File
@@ -31,14 +31,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for SDK changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: ./**
files_ignore: |
@@ -67,7 +67,7 @@ jobs:
- name: Set up Python ${{ matrix.python-version }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with:
python-version: ${{ matrix.python-version }}
cache: 'poetry'
@@ -80,7 +80,7 @@ jobs:
- name: Check if AWS files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-aws
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/aws/**
@@ -210,7 +210,7 @@ jobs:
- name: Check if Azure files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-azure
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/azure/**
@@ -234,7 +234,7 @@ jobs:
- name: Check if GCP files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-gcp
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/gcp/**
@@ -258,7 +258,7 @@ jobs:
- name: Check if Kubernetes files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-kubernetes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/kubernetes/**
@@ -282,7 +282,7 @@ jobs:
- name: Check if GitHub files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-github
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/github/**
@@ -306,7 +306,7 @@ jobs:
- name: Check if NHN files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-nhn
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/nhn/**
@@ -330,7 +330,7 @@ jobs:
- name: Check if M365 files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-m365
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/m365/**
@@ -354,7 +354,7 @@ jobs:
- name: Check if IaC files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-iac
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/iac/**
@@ -378,7 +378,7 @@ jobs:
- name: Check if MongoDB Atlas files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-mongodbatlas
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/mongodbatlas/**
@@ -402,7 +402,7 @@ jobs:
- name: Check if OCI files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-oraclecloud
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/oraclecloud/**
@@ -426,7 +426,7 @@ jobs:
- name: Check if OpenStack files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-openstack
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/openstack/**
@@ -450,7 +450,7 @@ jobs:
- name: Check if Google Workspace files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-googleworkspace
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/**/googleworkspace/**
@@ -474,7 +474,7 @@ jobs:
- name: Check if Lib files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-lib
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/lib/**
@@ -498,7 +498,7 @@ jobs:
- name: Check if Config files changed
if: steps.check-changes.outputs.any_changed == 'true'
id: changed-config
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
./prowler/config/**
+3 -3
View File
@@ -48,17 +48,17 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Get changed files
id: changed-files
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
- name: Setup Python
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: '3.12'
+6 -6
View File
@@ -67,7 +67,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -95,7 +95,7 @@ jobs:
git --no-pager diff
- name: Create PR for next minor version to master
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -117,7 +117,7 @@ jobs:
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
- name: Checkout version branch
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
ref: v${{ needs.detect-release-type.outputs.major_version }}.${{ needs.detect-release-type.outputs.minor_version }}
persist-credentials: false
@@ -149,7 +149,7 @@ jobs:
git --no-pager diff
- name: Create PR for first patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
@@ -180,7 +180,7 @@ jobs:
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -214,7 +214,7 @@ jobs:
git --no-pager diff
- name: Create PR for next patch version to version branch
uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8.1.0
uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
+3 -3
View File
@@ -45,17 +45,17 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Initialize CodeQL
uses: github/codeql-action/init@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/init@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/ui-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@89a39a4e59826350b863aa6b6252a07ad50cf83e # v4.32.4
uses: github/codeql-action/analyze@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
with:
category: '/language:${{ matrix.language }}'
@@ -59,7 +59,7 @@ jobs:
message-ts: ${{ steps.slack-notification.outputs.ts }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -97,12 +97,12 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -113,7 +113,7 @@ jobs:
- name: Build and push UI container for ${{ matrix.arch }}
id: container-push
if: github.event_name == 'push' || github.event_name == 'release' || github.event_name == 'workflow_dispatch'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
@@ -134,7 +134,7 @@ jobs:
steps:
- name: Login to DockerHub
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3.7.0
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -185,7 +185,7 @@ jobs:
timeout-minutes: 5
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
+5 -5
View File
@@ -28,14 +28,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check if Dockerfile changed
id: dockerfile-changed
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: ui/Dockerfile
@@ -66,14 +66,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for UI changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: ui/**
files_ignore: |
@@ -87,7 +87,7 @@ jobs:
- name: Build UI container for ${{ matrix.arch }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6.19.2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
with:
context: ${{ env.UI_WORKING_DIR }}
target: prod
+4 -4
View File
@@ -78,7 +78,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -152,7 +152,7 @@ jobs:
'
- name: Setup Node.js
uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # v6.2.0
uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # v6.1.0
with:
node-version: '24.13.0'
@@ -166,7 +166,7 @@ jobs:
run: echo "STORE_PATH=$(pnpm store path --silent)" >> $GITHUB_ENV
- name: Setup pnpm and Next.js cache
uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
uses: actions/cache@9255dc7a253b0ccc959486e2bca901246202afeb # v5.0.1
with:
path: |
${{ env.STORE_PATH }}
@@ -186,7 +186,7 @@ jobs:
run: pnpm run build
- name: Cache Playwright browsers
uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
uses: actions/cache@9255dc7a253b0ccc959486e2bca901246202afeb # v5.0.1
id: playwright-cache
with:
path: ~/.cache/ms-playwright
+6 -6
View File
@@ -30,14 +30,14 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
# zizmor: ignore[artipacked]
persist-credentials: true # Required by tj-actions/changed-files to fetch PR branch
- name: Check for UI changes
id: check-changes
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
ui/**
@@ -50,7 +50,7 @@ jobs:
- name: Get changed source files for targeted tests
id: changed-source
if: steps.check-changes.outputs.any_changed == 'true'
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
ui/**/*.ts
@@ -66,7 +66,7 @@ jobs:
- name: Check for critical path changes (run all tests)
id: critical-changes
if: steps.check-changes.outputs.any_changed == 'true'
uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
uses: tj-actions/changed-files@e0021407031f5be11a464abee9a0776171c79891 # v47.0.1
with:
files: |
ui/lib/**
@@ -78,7 +78,7 @@ jobs:
- name: Setup Node.js ${{ env.NODE_VERSION }}
if: steps.check-changes.outputs.any_changed == 'true'
uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # v6.2.0
uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f # v6.1.0
with:
node-version: ${{ env.NODE_VERSION }}
@@ -96,7 +96,7 @@ jobs:
- name: Setup pnpm and Next.js cache
if: steps.check-changes.outputs.any_changed == 'true'
uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
uses: actions/cache@9255dc7a253b0ccc959486e2bca901246202afeb # v5.0.1
with:
path: |
${{ env.STORE_PATH }}
-3
View File
@@ -163,6 +163,3 @@ GEMINI.md
.codex/skills
.github/skills
.gemini/skills
# Claude Code
.claude/*
+1 -9
View File
@@ -22,13 +22,6 @@ repos:
args: [--autofix]
files: pyproject.toml
## GITHUB ACTIONS
- repo: https://github.com/zizmorcore/zizmor-pre-commit
rev: v1.6.0
hooks:
- id: zizmor
files: ^\.github/
## BASH
- repo: https://github.com/koalaman/shellcheck-precommit
rev: v0.10.0
@@ -127,8 +120,7 @@ repos:
description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
# TODO: Botocore needs urllib3 1.X so we need to ignore these vulnerabilities 77744,77745. Remove this once we upgrade to urllib3 2.X
# TODO: 79023 & 79027 knack ReDoS until `azure-cli-core` (via `cartography`) allows `knack` >=0.13.0
# TODO: 86217 because `alibabacloud-tea-openapi == 0.4.3` don't let us upgrade `cryptography >= 46.0.0`
entry: bash -c 'safety check --ignore 70612,66963,74429,76352,76353,77744,77745,79023,79027,86217'
entry: bash -c 'safety check --ignore 70612,66963,74429,76352,76353,77744,77745,79023,79027'
language: system
- id: vulture
+2 -4
View File
@@ -46,8 +46,6 @@ Use these skills for detailed patterns on-demand:
| `prowler-commit` | Professional commits (conventional-commits) | [SKILL.md](skills/prowler-commit/SKILL.md) |
| `prowler-pr` | Pull request conventions | [SKILL.md](skills/prowler-pr/SKILL.md) |
| `prowler-docs` | Documentation style guide | [SKILL.md](skills/prowler-docs/SKILL.md) |
| `django-migration-psql` | Django migration best practices for PostgreSQL | [SKILL.md](skills/django-migration-psql/SKILL.md) |
| `postgresql-indexing` | PostgreSQL indexing, EXPLAIN, monitoring, maintenance | [SKILL.md](skills/postgresql-indexing/SKILL.md) |
| `prowler-attack-paths-query` | Create Attack Paths openCypher queries | [SKILL.md](skills/prowler-attack-paths-query/SKILL.md) |
| `gh-aw` | GitHub Agentic Workflows (gh-aw) | [SKILL.md](skills/gh-aw/SKILL.md) |
| `skill-creator` | Create new AI agent skills | [SKILL.md](skills/skill-creator/SKILL.md) |
@@ -87,15 +85,15 @@ When performing these actions, ALWAYS invoke the corresponding skill FIRST:
| Fixing bug | `tdd` |
| General Prowler development questions | `prowler` |
| Implementing JSON:API endpoints | `django-drf` |
| Implementing feature | `tdd` |
| Importing Copilot Custom Agents into workflows | `gh-aw` |
| Implementing feature | `tdd` |
| Inspect PR CI checks and gates (.github/workflows/*) | `prowler-ci` |
| Inspect PR CI workflows (.github/workflows/*): conventional-commit, pr-check-changelog, pr-conflict-checker, labeler | `prowler-pr` |
| Mapping checks to compliance controls | `prowler-compliance` |
| Mocking AWS with moto in tests | `prowler-test-sdk` |
| Modifying API responses | `jsonapi` |
| Modifying component | `tdd` |
| Modifying gh-aw workflow frontmatter or safe-outputs | `gh-aw` |
| Modifying component | `tdd` |
| Refactoring code | `tdd` |
| Regenerate AGENTS.md Auto-invoke tables (sync.sh) | `skill-sync` |
| Review PR requirements: template, title conventions, changelog gate | `prowler-pr` |
-10
View File
@@ -4,8 +4,6 @@
> - [`prowler-api`](../skills/prowler-api/SKILL.md) - Models, Serializers, Views, RLS patterns
> - [`prowler-test-api`](../skills/prowler-test-api/SKILL.md) - Testing patterns (pytest-django)
> - [`prowler-attack-paths-query`](../skills/prowler-attack-paths-query/SKILL.md) - Attack Paths openCypher queries
> - [`django-migration-psql`](../skills/django-migration-psql/SKILL.md) - Migration best practices for PostgreSQL
> - [`postgresql-indexing`](../skills/postgresql-indexing/SKILL.md) - PostgreSQL indexing, EXPLAIN, monitoring, maintenance
> - [`django-drf`](../skills/django-drf/SKILL.md) - Generic DRF patterns
> - [`jsonapi`](../skills/jsonapi/SKILL.md) - Strict JSON:API v1.1 spec compliance
> - [`pytest`](../skills/pytest/SKILL.md) - Generic pytest patterns
@@ -18,20 +16,14 @@ When performing these actions, ALWAYS invoke the corresponding skill FIRST:
|--------|-------|
| Add changelog entry for a PR or feature | `prowler-changelog` |
| Adding DRF pagination or permissions | `django-drf` |
| Adding indexes or constraints to database tables | `django-migration-psql` |
| Adding privilege escalation detection queries | `prowler-attack-paths-query` |
| Analyzing query performance with EXPLAIN | `postgresql-indexing` |
| Committing changes | `prowler-commit` |
| Create PR that requires changelog entry | `prowler-changelog` |
| Creating API endpoints | `jsonapi` |
| Creating Attack Paths queries | `prowler-attack-paths-query` |
| Creating ViewSets, serializers, or filters in api/ | `django-drf` |
| Creating a git commit | `prowler-commit` |
| Creating or modifying PostgreSQL indexes | `postgresql-indexing` |
| Creating or reviewing Django migrations | `django-migration-psql` |
| Creating/modifying models, views, serializers | `prowler-api` |
| Debugging slow queries or missing indexes | `postgresql-indexing` |
| Dropping or reindexing PostgreSQL indexes | `postgresql-indexing` |
| Fixing bug | `tdd` |
| Implementing JSON:API endpoints | `django-drf` |
| Implementing feature | `tdd` |
@@ -40,14 +32,12 @@ When performing these actions, ALWAYS invoke the corresponding skill FIRST:
| Refactoring code | `tdd` |
| Review changelog format and conventions | `prowler-changelog` |
| Reviewing JSON:API compliance | `jsonapi` |
| Running makemigrations or pgmakemigrations | `django-migration-psql` |
| Testing RLS tenant isolation | `prowler-test-api` |
| Update CHANGELOG.md in any component | `prowler-changelog` |
| Updating existing Attack Paths queries | `prowler-attack-paths-query` |
| Working on task | `tdd` |
| Writing Prowler API tests | `prowler-test-api` |
| Writing Python tests with pytest | `pytest` |
| Writing data backfill or data migration | `django-migration-psql` |
---
+6 -33
View File
@@ -2,47 +2,20 @@
All notable changes to the **Prowler API** are documented in this file.
## [1.22.1] (Prowler v5.21.1)
### 🐞 Fixed
- ThreatScore aggregation query to eliminate unnecessary JOINs and `COUNT(DISTINCT)` overhead [(#10394)](https://github.com/prowler-cloud/prowler/pull/10394)
---
## [1.22.0] (Prowler v5.21.0)
### 🚀 Added
- `CORS_ALLOWED_ORIGINS` configurable via environment variable [(#10355)](https://github.com/prowler-cloud/prowler/pull/10355)
- Attack Paths: Tenant and provider related labels to the nodes so they can be easily filtered on custom queries [(#10308)](https://github.com/prowler-cloud/prowler/pull/10308)
### 🔄 Changed
- Attack Paths: Complete migration to private graph labels and properties, removing deprecated dual-write support [(#10268)](https://github.com/prowler-cloud/prowler/pull/10268)
- Attack Paths: Reduce sync and findings memory usage with smaller batches, cursor iteration, and sequential sessions [(#10359)](https://github.com/prowler-cloud/prowler/pull/10359)
### 🐞 Fixed
- Attack Paths: Recover `graph_data_ready` flag when scan fails during graph swap, preventing query endpoints from staying blocked until the next successful scan [(#10354)](https://github.com/prowler-cloud/prowler/pull/10354)
### 🔐 Security
- Use `psycopg2.sql` to safely compose DDL in `PostgresEnumMigration`, preventing SQL injection via f-string interpolation [(#10166)](https://github.com/prowler-cloud/prowler/pull/10166)
---
## [1.21.0] (Prowler v5.20.0)
## [1.21.0] (Prowler UNRELEASED)
### 🔄 Changed
- Attack Paths: Migrate network exposure queries from APOC to standard openCypher for Neo4j and Neptune compatibility [(#10266)](https://github.com/prowler-cloud/prowler/pull/10266)
- `POST /api/v1/providers` returns `409 Conflict` if already exists [(#10293)](https://github.com/prowler-cloud/prowler/pull/10293)
---
## [1.20.1] (Prowler UNRELEASED)
### 🐞 Fixed
- Attack Paths: Security hardening for custom query endpoint (Cypher blocklist, input validation, rate limiting, Helm lockdown) [(#10238)](https://github.com/prowler-cloud/prowler/pull/10238)
- Attack Paths: Missing logging for query execution and exception details in scan error handling [(#10269)](https://github.com/prowler-cloud/prowler/pull/10269)
- Attack Paths: Add missing logging for query execution and exception details in scan error handling [(#10269)](https://github.com/prowler-cloud/prowler/pull/10269)
- Attack Paths: Upgrade Cartography from 0.129.0 to 0.132.0, fixing `exposed_internet` not set on ELB/ELBv2 nodes [(#10272)](https://github.com/prowler-cloud/prowler/pull/10272)
---
+32 -382
View File
File diff suppressed because it is too large Load Diff
+2 -2
View File
@@ -24,7 +24,7 @@ dependencies = [
"drf-spectacular-jsonapi==0.5.1",
"gunicorn==23.0.0",
"lxml==5.3.2",
"prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.21",
"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)",
@@ -49,7 +49,7 @@ name = "prowler-api"
package-mode = false
# Needed for the SDK compatibility
requires-python = ">=3.11,<3.13"
version = "1.22.1"
version = "1.21.0"
[project.scripts]
celery = "src.backend.config.settings.celery"
+11 -41
View File
@@ -1,21 +1,24 @@
import atexit
import logging
import threading
from typing import Any
from contextlib import contextmanager
from typing import Any, Iterator
from typing import Iterator
from uuid import UUID
import neo4j
import neo4j.exceptions
from config.env import env
from django.conf import settings
from tasks.jobs.attack_paths.config import (
BATCH_SIZE,
PROVIDER_ID_PROPERTY,
PROVIDER_RESOURCE_LABEL,
)
from api.attack_paths.retryable_session import RetryableSession
from config.env import env
from tasks.jobs.attack_paths.config import (
BATCH_SIZE,
DEPRECATED_PROVIDER_RESOURCE_LABEL,
)
# Without this Celery goes crazy with Neo4j logging
logging.getLogger("neo4j").setLevel(logging.ERROR)
@@ -32,7 +35,6 @@ READ_EXCEPTION_CODES = [
"Neo.ClientError.Statement.AccessMode",
"Neo.ClientError.Procedure.ProcedureNotFound",
]
CLIENT_STATEMENT_EXCEPTION_PREFIX = "Neo.ClientError.Statement."
# Module-level process-wide driver singleton
_driver: neo4j.Driver | None = None
@@ -106,7 +108,6 @@ def get_session(
except neo4j.exceptions.Neo4jError as exc:
if (
default_access_mode == neo4j.READ_ACCESS
and exc.code
and exc.code in READ_EXCEPTION_CODES
):
message = "Read query not allowed"
@@ -114,10 +115,6 @@ def get_session(
raise WriteQueryNotAllowedException(message=message, code=code)
message = exc.message if exc.message is not None else str(exc)
if exc.code and exc.code.startswith(CLIENT_STATEMENT_EXCEPTION_PREFIX):
raise ClientStatementException(message=message, code=exc.code)
raise GraphDatabaseQueryException(message=message, code=exc.code)
finally:
@@ -175,7 +172,7 @@ def drop_subgraph(database: str, provider_id: str) -> int:
while deleted_count > 0:
result = session.run(
f"""
MATCH (n:{PROVIDER_RESOURCE_LABEL} {{{PROVIDER_ID_PROPERTY}: $provider_id}})
MATCH (n:{DEPRECATED_PROVIDER_RESOURCE_LABEL} {{provider_id: $provider_id}})
WITH n LIMIT $batch_size
DETACH DELETE n
RETURN COUNT(n) AS deleted_nodes_count
@@ -193,29 +190,6 @@ def drop_subgraph(database: str, provider_id: str) -> int:
return deleted_nodes
def has_provider_data(database: str, provider_id: str) -> bool:
"""
Check if any ProviderResource node exists for this provider.
Returns `False` if the database doesn't exist.
"""
query = (
f"MATCH (n:{PROVIDER_RESOURCE_LABEL} "
f"{{{PROVIDER_ID_PROPERTY}: $provider_id}}) "
"RETURN 1 LIMIT 1"
)
try:
with get_session(database, default_access_mode=neo4j.READ_ACCESS) as session:
result = session.run(query, {"provider_id": provider_id})
return result.single() is not None
except GraphDatabaseQueryException as exc:
if exc.code == "Neo.ClientError.Database.DatabaseNotFound":
return False
raise
def clear_cache(database: str) -> None:
query = "CALL db.clearQueryCaches()"
@@ -253,7 +227,3 @@ class GraphDatabaseQueryException(Exception):
class WriteQueryNotAllowedException(GraphDatabaseQueryException):
pass
class ClientStatementException(GraphDatabaseQueryException):
pass
@@ -3,7 +3,7 @@ from api.attack_paths.queries.types import (
AttackPathsQueryDefinition,
AttackPathsQueryParameterDefinition,
)
from tasks.jobs.attack_paths.config import PROVIDER_ID_PROPERTY, PROWLER_FINDING_LABEL
from tasks.jobs.attack_paths.config import PROWLER_FINDING_LABEL
# Custom Attack Path Queries
@@ -16,7 +16,7 @@ AWS_INTERNET_EXPOSED_EC2_SENSITIVE_S3_ACCESS = AttackPathsQueryDefinition(
description="Detect EC2 instances with SSH exposed to the internet that can assume higher-privileged roles to read tagged sensitive S3 buckets despite bucket-level public access blocks.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
MATCH path_s3 = (aws:AWSAccount {{id: $provider_uid}})--(s3:S3Bucket)--(t:AWSTag)
WHERE toLower(t.key) = toLower($tag_key) AND toLower(t.value) = toLower($tag_value)
@@ -179,7 +179,7 @@ AWS_EC2_INSTANCES_INTERNET_EXPOSED = AttackPathsQueryDefinition(
description="Find EC2 instances flagged as exposed to the internet within the selected account.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
MATCH path = (aws:AWSAccount {{id: $provider_uid}})--(ec2:EC2Instance)
WHERE ec2.exposed_internet = true
@@ -201,7 +201,7 @@ AWS_SECURITY_GROUPS_OPEN_INTERNET_FACING = AttackPathsQueryDefinition(
description="Find internet-facing resources associated with security groups that allow inbound access from '0.0.0.0/0'.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
// Match EC2 instances that are internet-exposed with open security groups (0.0.0.0/0)
MATCH path_ec2 = (aws:AWSAccount {{id: $provider_uid}})--(ec2:EC2Instance)--(sg:EC2SecurityGroup)--(ipi:IpPermissionInbound)--(ir:IpRange)
@@ -225,7 +225,7 @@ AWS_CLASSIC_ELB_INTERNET_EXPOSED = AttackPathsQueryDefinition(
description="Find Classic Load Balancers exposed to the internet along with their listeners.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
MATCH path = (aws:AWSAccount {{id: $provider_uid}})--(elb:LoadBalancer)--(listener:ELBListener)
WHERE elb.exposed_internet = true
@@ -247,7 +247,7 @@ AWS_ELBV2_INTERNET_EXPOSED = AttackPathsQueryDefinition(
description="Find ELBv2 load balancers exposed to the internet along with their listeners.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
MATCH path = (aws:AWSAccount {{id: $provider_uid}})--(elbv2:LoadBalancerV2)--(listener:ELBV2Listener)
WHERE elbv2.exposed_internet = true
@@ -269,7 +269,7 @@ AWS_PUBLIC_IP_RESOURCE_LOOKUP = AttackPathsQueryDefinition(
description="Given a public IP address, find the related AWS resource and its adjacent node within the selected account.",
provider="aws",
cypher=f"""
OPTIONAL MATCH (internet:Internet {{{PROVIDER_ID_PROPERTY}: $provider_id}})
OPTIONAL MATCH (internet:Internet {{_provider_id: $provider_id}})
MATCH path = (aws:AWSAccount {{id: $provider_uid}})-[r]-(x)-[q]-(y)
WHERE (x:EC2PrivateIp AND x.public_ip = $ip)
@@ -1,7 +1,7 @@
from tasks.jobs.attack_paths.config import PROVIDER_ID_PROPERTY, PROVIDER_RESOURCE_LABEL
from tasks.jobs.attack_paths.config import DEPRECATED_PROVIDER_RESOURCE_LABEL
CARTOGRAPHY_SCHEMA_METADATA = f"""
MATCH (n:{PROVIDER_RESOURCE_LABEL} {{{PROVIDER_ID_PROPERTY}: $provider_id}})
MATCH (n:{DEPRECATED_PROVIDER_RESOURCE_LABEL} {{provider_id: $provider_id}})
WHERE n._module_name STARTS WITH 'cartography:'
AND NOT n._module_name IN ['cartography:ontology', 'cartography:prowler']
AND n._module_version IS NOT NULL
@@ -1,5 +1,4 @@
import logging
import re
from typing import Any, Iterable
@@ -13,12 +12,7 @@ from api.attack_paths.queries.schema import (
RAW_SCHEMA_URL,
)
from config.custom_logging import BackendLogger
from tasks.jobs.attack_paths.config import (
INTERNAL_LABELS,
INTERNAL_PROPERTIES,
PROVIDER_ID_PROPERTY,
is_dynamic_isolation_label,
)
from tasks.jobs.attack_paths.config import INTERNAL_LABELS, INTERNAL_PROPERTIES
logger = logging.getLogger(BackendLogger.API)
@@ -123,38 +117,6 @@ def execute_query(
# Custom query helpers
# Patterns that indicate SSRF or dangerous procedure calls
# Defense-in-depth layer - the primary control is `neo4j.READ_ACCESS`
_BLOCKED_PATTERNS = [
re.compile(r"\bLOAD\s+CSV\b", re.IGNORECASE),
re.compile(r"\bapoc\.load\b", re.IGNORECASE),
re.compile(r"\bapoc\.import\b", re.IGNORECASE),
re.compile(r"\bapoc\.export\b", re.IGNORECASE),
re.compile(r"\bapoc\.cypher\b", re.IGNORECASE),
re.compile(r"\bapoc\.systemdb\b", re.IGNORECASE),
re.compile(r"\bapoc\.config\b", re.IGNORECASE),
re.compile(r"\bapoc\.periodic\b", re.IGNORECASE),
re.compile(r"\bapoc\.do\b", re.IGNORECASE),
re.compile(r"\bapoc\.trigger\b", re.IGNORECASE),
re.compile(r"\bapoc\.custom\b", re.IGNORECASE),
]
# Strip string literals so patterns inside quotes don't cause false positives
# Handles escaped quotes (\' and \") inside strings
_STRING_LITERALS = re.compile(r"'(?:[^'\\]|\\.)*'|\"(?:[^\"\\]|\\.)*\"")
def validate_custom_query(cypher: str) -> None:
"""Reject queries containing known SSRF or dangerous procedure patterns.
Raises ValidationError if a blocked pattern is found.
String literals are stripped before matching to avoid false positives.
"""
stripped = _STRING_LITERALS.sub("", cypher)
for pattern in _BLOCKED_PATTERNS:
if pattern.search(stripped):
raise ValidationError({"query": "Query contains a blocked operation"})
def normalize_custom_query_payload(raw_data):
if not isinstance(raw_data, dict):
@@ -173,8 +135,6 @@ def execute_custom_query(
cypher: str,
provider_id: str,
) -> dict[str, Any]:
validate_custom_query(cypher)
try:
graph = graph_database.execute_read_query(
database=database_name,
@@ -183,9 +143,6 @@ def execute_custom_query(
serialized = _serialize_graph(graph, provider_id)
return _truncate_graph(serialized)
except graph_database.ClientStatementException as exc:
raise ValidationError({"query": exc.message})
except graph_database.WriteQueryNotAllowedException:
raise PermissionDenied(
"Attack Paths query execution failed: read-only queries are enforced"
@@ -258,7 +215,7 @@ def _serialize_graph(graph, provider_id: str) -> dict[str, Any]:
nodes = []
kept_node_ids = set()
for node in graph.nodes:
if node._properties.get(PROVIDER_ID_PROPERTY) != provider_id:
if node._properties.get("provider_id") != provider_id:
continue
kept_node_ids.add(node.element_id)
@@ -270,15 +227,9 @@ def _serialize_graph(graph, provider_id: str) -> dict[str, Any]:
},
)
filtered_count = len(graph.nodes) - len(nodes)
if filtered_count > 0:
logger.debug(
f"Filtered {filtered_count} nodes without matching provider_id={provider_id}"
)
relationships = []
for relationship in graph.relationships:
if relationship._properties.get(PROVIDER_ID_PROPERTY) != provider_id:
if relationship._properties.get("provider_id") != provider_id:
continue
if (
@@ -306,11 +257,7 @@ def _serialize_graph(graph, provider_id: str) -> dict[str, Any]:
def _filter_labels(labels: Iterable[str]) -> list[str]:
return [
label
for label in labels
if label not in INTERNAL_LABELS and not is_dynamic_isolation_label(label)
]
return [label for label in labels if label not in INTERNAL_LABELS]
def _serialize_properties(properties: dict[str, Any]) -> dict[str, Any]:
+3 -12
View File
@@ -18,7 +18,6 @@ from django.db import (
)
from django_celery_beat.models import PeriodicTask
from psycopg2 import connect as psycopg2_connect
from psycopg2 import sql as psycopg2_sql
from psycopg2.extensions import AsIs, new_type, register_adapter, register_type
from rest_framework_json_api.serializers import ValidationError
@@ -281,23 +280,15 @@ class PostgresEnumMigration:
self.enum_values = enum_values
def create_enum_type(self, apps, schema_editor): # noqa: F841
string_enum_values = ", ".join([f"'{value}'" for value in self.enum_values])
with schema_editor.connection.cursor() as cursor:
cursor.execute(
psycopg2_sql.SQL("CREATE TYPE {} AS ENUM ({})").format(
psycopg2_sql.Identifier(self.enum_name),
psycopg2_sql.SQL(", ").join(
psycopg2_sql.Literal(v) for v in self.enum_values
),
)
f"CREATE TYPE {self.enum_name} AS ENUM ({string_enum_values});"
)
def drop_enum_type(self, apps, schema_editor): # noqa: F841
with schema_editor.connection.cursor() as cursor:
cursor.execute(
psycopg2_sql.SQL("DROP TYPE {}").format(
psycopg2_sql.Identifier(self.enum_name)
)
)
cursor.execute(f"DROP TYPE {self.enum_name};")
class PostgresEnumField(models.Field):
+1 -1
View File
@@ -1,7 +1,7 @@
openapi: 3.0.3
info:
title: Prowler API
version: 1.22.1
version: 1.21.0
description: |-
Prowler API specification.
+15 -91
View File
@@ -9,10 +9,6 @@ from rest_framework.exceptions import APIException, PermissionDenied, Validation
from api.attack_paths import database as graph_database
from api.attack_paths import views_helpers
from tasks.jobs.attack_paths.config import (
PROVIDER_ELEMENT_ID_PROPERTY,
PROVIDER_ID_PROPERTY,
)
def _make_neo4j_error(message, code):
@@ -112,7 +108,7 @@ def test_execute_query_serializes_graph(
labels=["AWSAccount"],
properties={
"name": "account",
PROVIDER_ID_PROPERTY: provider_id,
"provider_id": provider_id,
"complex": {
"items": [
attack_paths_graph_stub_classes.NativeValue("value"),
@@ -122,14 +118,14 @@ def test_execute_query_serializes_graph(
},
)
node_2 = attack_paths_graph_stub_classes.Node(
"node-2", ["RDSInstance"], {PROVIDER_ID_PROPERTY: provider_id}
"node-2", ["RDSInstance"], {"provider_id": provider_id}
)
relationship = attack_paths_graph_stub_classes.Relationship(
element_id="rel-1",
rel_type="OWNS",
start_node=node,
end_node=node_2,
properties={"weight": 1, PROVIDER_ID_PROPERTY: provider_id},
properties={"weight": 1, "provider_id": provider_id},
)
graph = SimpleNamespace(nodes=[node, node_2], relationships=[relationship])
@@ -217,20 +213,20 @@ def test_serialize_graph_filters_by_provider_id(attack_paths_graph_stub_classes)
provider_id = "provider-keep"
node_keep = attack_paths_graph_stub_classes.Node(
"n1", ["AWSAccount"], {PROVIDER_ID_PROPERTY: provider_id}
"n1", ["AWSAccount"], {"provider_id": provider_id}
)
node_drop = attack_paths_graph_stub_classes.Node(
"n2", ["AWSAccount"], {PROVIDER_ID_PROPERTY: "provider-other"}
"n2", ["AWSAccount"], {"provider_id": "provider-other"}
)
rel_keep = attack_paths_graph_stub_classes.Relationship(
"r1", "OWNS", node_keep, node_keep, {PROVIDER_ID_PROPERTY: provider_id}
"r1", "OWNS", node_keep, node_keep, {"provider_id": provider_id}
)
rel_drop_by_provider = attack_paths_graph_stub_classes.Relationship(
"r2", "OWNS", node_keep, node_drop, {PROVIDER_ID_PROPERTY: "provider-other"}
"r2", "OWNS", node_keep, node_drop, {"provider_id": "provider-other"}
)
rel_drop_orphaned = attack_paths_graph_stub_classes.Relationship(
"r3", "OWNS", node_keep, node_drop, {PROVIDER_ID_PROPERTY: provider_id}
"r3", "OWNS", node_keep, node_drop, {"provider_id": provider_id}
)
graph = SimpleNamespace(
@@ -354,8 +350,10 @@ def test_serialize_properties_filters_internal_fields():
"_module_name": "cartography:aws",
"_module_version": "0.98.0",
# Provider isolation
PROVIDER_ID_PROPERTY: "42",
PROVIDER_ELEMENT_ID_PROPERTY: "42:abc123",
"_provider_id": "42",
"_provider_element_id": "42:abc123",
"provider_id": "42",
"provider_element_id": "42:abc123",
}
result = views_helpers._serialize_properties(properties)
@@ -363,14 +361,6 @@ def test_serialize_properties_filters_internal_fields():
assert result == {"name": "prod"}
def test_filter_labels_strips_dynamic_isolation_labels():
labels = ["AWSRole", "_Tenant_abc123", "_Provider_def456", "_ProviderResource"]
result = views_helpers._filter_labels(labels)
assert result == ["AWSRole"]
def test_serialize_graph_as_text_node_without_properties():
graph = {
"nodes": [{"id": "n1", "labels": ["AWSAccount"], "properties": {}}],
@@ -450,13 +440,13 @@ def test_execute_custom_query_serializes_graph(
):
provider_id = "test-provider-123"
node_1 = attack_paths_graph_stub_classes.Node(
"node-1", ["AWSAccount"], {PROVIDER_ID_PROPERTY: provider_id}
"node-1", ["AWSAccount"], {"provider_id": provider_id}
)
node_2 = attack_paths_graph_stub_classes.Node(
"node-2", ["RDSInstance"], {PROVIDER_ID_PROPERTY: provider_id}
"node-2", ["RDSInstance"], {"provider_id": provider_id}
)
relationship = attack_paths_graph_stub_classes.Relationship(
"rel-1", "OWNS", node_1, node_2, {PROVIDER_ID_PROPERTY: provider_id}
"rel-1", "OWNS", node_1, node_2, {"provider_id": provider_id}
)
graph_result = MagicMock()
@@ -511,72 +501,6 @@ def test_execute_custom_query_wraps_graph_errors():
mock_logger.error.assert_called_once()
# -- validate_custom_query ------------------------------------------------
@pytest.mark.parametrize(
"cypher",
[
"LOAD CSV FROM 'http://169.254.169.254/' AS x RETURN x",
"load csv from 'http://evil.com' as row return row",
"CALL apoc.load.json('http://evil.com/') YIELD value RETURN value",
"CALL apoc.load.csvParams('http://evil.com/', {}, null) YIELD list RETURN list",
"CALL apoc.import.csv([{fileName: 'f'}], [], {}) YIELD node RETURN node",
"CALL apoc.export.csv.all('file.csv', {})",
"CALL apoc.cypher.run('CREATE (n)', {}) YIELD value RETURN value",
"CALL apoc.systemdb.graph() YIELD nodes RETURN nodes",
"CALL apoc.config.list() YIELD key, value RETURN key, value",
"CALL apoc.periodic.iterate('MATCH (n) RETURN n', 'DELETE n', {batchSize: 100})",
"CALL apoc.do.when(true, 'CREATE (n) RETURN n', '', {}) YIELD value RETURN value",
"CALL apoc.trigger.add('t', 'RETURN 1', {phase: 'before'})",
"CALL apoc.custom.asProcedure('myProc', 'RETURN 1')",
],
ids=[
"LOAD_CSV",
"LOAD_CSV_lowercase",
"apoc.load.json",
"apoc.load.csvParams",
"apoc.import.csv",
"apoc.export.csv",
"apoc.cypher.run",
"apoc.systemdb.graph",
"apoc.config.list",
"apoc.periodic.iterate",
"apoc.do.when",
"apoc.trigger.add",
"apoc.custom.asProcedure",
],
)
def test_validate_custom_query_rejects_blocked_patterns(cypher):
with pytest.raises(ValidationError) as exc:
views_helpers.validate_custom_query(cypher)
assert "blocked operation" in str(exc.value.detail)
@pytest.mark.parametrize(
"cypher",
[
"MATCH (n:AWSAccount) RETURN n LIMIT 10",
"MATCH (a)-[r]->(b) RETURN a, r, b",
"MATCH (n) WHERE n.name CONTAINS 'load' RETURN n",
"CALL apoc.create.vNode(['Label'], {}) YIELD node RETURN node",
"MATCH (n) WHERE n.name = 'apoc.load.json' RETURN n",
'MATCH (n) WHERE n.description = "LOAD CSV is cool" RETURN n',
],
ids=[
"simple_match",
"traversal",
"contains_load_substring",
"apoc_virtual_node",
"apoc_load_inside_single_quotes",
"load_csv_inside_double_quotes",
],
)
def test_validate_custom_query_allows_clean_queries(cypher):
views_helpers.validate_custom_query(cypher)
# -- _truncate_graph ----------------------------------------------------------
@@ -442,78 +442,3 @@ class TestThreadSafety:
# All threads got the same driver instance
assert all(r is mock_driver for r in results)
assert len(results) == 10
class TestHasProviderData:
"""Test has_provider_data helper for checking provider nodes in Neo4j."""
def test_returns_true_when_nodes_exist(self):
import api.attack_paths.database as db_module
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.single.return_value = MagicMock() # non-None record
mock_session.run.return_value = mock_result
session_ctx = MagicMock()
session_ctx.__enter__.return_value = mock_session
session_ctx.__exit__.return_value = False
with patch(
"api.attack_paths.database.get_session",
return_value=session_ctx,
):
assert db_module.has_provider_data("db-tenant-abc", "provider-123") is True
mock_session.run.assert_called_once()
def test_returns_false_when_no_nodes(self):
import api.attack_paths.database as db_module
mock_session = MagicMock()
mock_result = MagicMock()
mock_result.single.return_value = None
mock_session.run.return_value = mock_result
session_ctx = MagicMock()
session_ctx.__enter__.return_value = mock_session
session_ctx.__exit__.return_value = False
with patch(
"api.attack_paths.database.get_session",
return_value=session_ctx,
):
assert db_module.has_provider_data("db-tenant-abc", "provider-123") is False
def test_returns_false_when_database_not_found(self):
import api.attack_paths.database as db_module
session_ctx = MagicMock()
session_ctx.__enter__.side_effect = db_module.GraphDatabaseQueryException(
message="Database does not exist",
code="Neo.ClientError.Database.DatabaseNotFound",
)
with patch(
"api.attack_paths.database.get_session",
return_value=session_ctx,
):
assert (
db_module.has_provider_data("db-tenant-gone", "provider-123") is False
)
def test_raises_on_other_errors(self):
import api.attack_paths.database as db_module
session_ctx = MagicMock()
session_ctx.__enter__.side_effect = db_module.GraphDatabaseQueryException(
message="Connection refused",
code="Neo.TransientError.General.UnknownError",
)
with patch(
"api.attack_paths.database.get_session",
return_value=session_ctx,
):
with pytest.raises(db_module.GraphDatabaseQueryException):
db_module.has_provider_data("db-tenant-abc", "provider-123")
@@ -6,12 +6,10 @@ import pytest
from django.conf import settings
from django.db import DEFAULT_DB_ALIAS, OperationalError
from freezegun import freeze_time
from psycopg2 import sql as psycopg2_sql
from rest_framework_json_api.serializers import ValidationError
from api.db_utils import (
POSTGRES_TENANT_VAR,
PostgresEnumMigration,
_should_create_index_on_partition,
batch_delete,
create_objects_in_batches,
@@ -912,61 +910,3 @@ class TestRlsTransaction:
cursor.execute("SELECT 1")
result = cursor.fetchone()
assert result[0] == 1
class TestPostgresEnumMigration:
"""
Verify that PostgresEnumMigration builds DDL statements via psycopg2.sql
so that enum type names and values are always properly quoted — preventing
SQL injection through f-string interpolation.
"""
def _make_mock_schema_editor(self):
mock_cursor = MagicMock()
mock_conn = MagicMock()
mock_conn.cursor.return_value.__enter__ = MagicMock(return_value=mock_cursor)
mock_conn.cursor.return_value.__exit__ = MagicMock(return_value=False)
mock_schema_editor = MagicMock()
mock_schema_editor.connection = mock_conn
return mock_schema_editor, mock_cursor
def test_create_enum_type_generates_correct_sql(self):
"""create_enum_type builds a proper CREATE TYPE … AS ENUM via psycopg2.sql."""
migration = PostgresEnumMigration("my_enum", ("val_a", "val_b"))
schema_editor, mock_cursor = self._make_mock_schema_editor()
migration.create_enum_type(apps=None, schema_editor=schema_editor)
mock_cursor.execute.assert_called_once()
query_arg = mock_cursor.execute.call_args[0][0]
assert isinstance(
query_arg, psycopg2_sql.Composable
), "create_enum_type must pass a psycopg2.sql.Composable, not a raw string."
# Verify the composed SQL structure: CREATE TYPE <Identifier> AS ENUM (<Literals>)
parts = query_arg.seq
assert parts[0] == psycopg2_sql.SQL("CREATE TYPE ")
assert isinstance(parts[1], psycopg2_sql.Identifier)
assert parts[1].strings == ("my_enum",)
assert parts[2] == psycopg2_sql.SQL(" AS ENUM (")
# The enum values are a Composed of Literal items joined by ", "
enum_literals = [p for p in parts[3].seq if isinstance(p, psycopg2_sql.Literal)]
assert [lit._wrapped for lit in enum_literals] == ["val_a", "val_b"]
assert parts[4] == psycopg2_sql.SQL(")")
def test_drop_enum_type_generates_correct_sql(self):
"""drop_enum_type builds a proper DROP TYPE via psycopg2.sql."""
migration = PostgresEnumMigration("my_enum", ("val_a",))
schema_editor, mock_cursor = self._make_mock_schema_editor()
migration.drop_enum_type(apps=None, schema_editor=schema_editor)
mock_cursor.execute.assert_called_once()
query_arg = mock_cursor.execute.call_args[0][0]
assert isinstance(
query_arg, psycopg2_sql.Composable
), "drop_enum_type must pass a psycopg2.sql.Composable, not a raw string."
# Verify the composed SQL structure: DROP TYPE <Identifier>
parts = query_arg.seq
assert parts[0] == psycopg2_sql.SQL("DROP TYPE ")
assert isinstance(parts[1], psycopg2_sql.Identifier)
assert parts[1].strings == ("my_enum",)
+11 -347
View File
@@ -3810,12 +3810,6 @@ class TestTaskViewSet:
@pytest.mark.django_db
class TestAttackPathsScanViewSet:
@pytest.fixture(autouse=True)
def _clear_throttle_cache(self):
from django.core.cache import cache
cache.clear()
@staticmethod
def _run_payload(query_id="aws-rds", parameters=None):
return {
@@ -4417,6 +4411,8 @@ class TestAttackPathsScanViewSet:
}
}
# TODO: Remove skip once queries/custom and schema endpoints are unblocked
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_run_custom_query_returns_graph(
self,
authenticated_client,
@@ -4474,6 +4470,7 @@ class TestAttackPathsScanViewSet:
assert attributes["total_nodes"] == 1
assert attributes["truncated"] is False
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_run_custom_query_returns_text_when_accept_text_plain(
self,
authenticated_client,
@@ -4528,6 +4525,7 @@ class TestAttackPathsScanViewSet:
assert "## Relationships (0)" in body
assert "## Summary" in body
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_run_custom_query_returns_404_when_no_nodes(
self,
authenticated_client,
@@ -4569,6 +4567,7 @@ class TestAttackPathsScanViewSet:
assert response.status_code == status.HTTP_404_NOT_FOUND
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_run_custom_query_returns_400_when_graph_not_ready(
self,
authenticated_client,
@@ -4595,6 +4594,7 @@ class TestAttackPathsScanViewSet:
assert response.status_code == status.HTTP_400_BAD_REQUEST
assert "not available" in response.json()["errors"][0]["detail"]
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_run_custom_query_returns_403_for_write_query(
self,
authenticated_client,
@@ -4632,343 +4632,9 @@ class TestAttackPathsScanViewSet:
assert response.status_code == status.HTTP_403_FORBIDDEN
# -- SSRF blocklist (HTTP level) ----------------------------------------------
@pytest.mark.parametrize(
"cypher",
[
"LOAD CSV FROM 'http://169.254.169.254/' AS x RETURN x",
"CALL apoc.load.json('http://evil.com/') YIELD value RETURN value",
"CALL apoc.import.csv([{fileName: 'f'}], [], {}) YIELD node RETURN node",
"CALL apoc.export.csv.all('file.csv', {})",
"CALL apoc.cypher.run('CREATE (n)', {}) YIELD value RETURN value",
"CALL apoc.systemdb.graph() YIELD nodes RETURN nodes",
],
ids=[
"LOAD_CSV",
"apoc.load",
"apoc.import",
"apoc.export",
"apoc.cypher.run",
"apoc.systemdb",
],
)
def test_run_custom_query_rejects_ssrf_patterns(
self,
authenticated_client,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
cypher,
):
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
with patch(
"api.v1.views.graph_database.get_database_name",
return_value="db-test",
):
response = authenticated_client.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(cypher),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_400_BAD_REQUEST
assert "blocked" in response.json()["errors"][0]["detail"].lower()
# -- Cross-tenant isolation ---------------------------------------------------
def test_run_custom_query_returns_404_for_foreign_tenant(
self,
authenticated_client,
create_attack_paths_scan,
):
from api.models import Provider, Tenant
foreign_tenant = Tenant.objects.create(name="foreign-tenant")
foreign_provider = Provider.objects.create(
tenant=foreign_tenant,
provider="aws",
uid="123456789999",
)
attack_paths_scan = create_attack_paths_scan(
foreign_provider,
graph_data_ready=True,
)
with patch(
"api.v1.views.graph_database.get_database_name",
return_value="db-test",
):
response = authenticated_client.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_404_NOT_FOUND
def test_cartography_schema_returns_404_for_foreign_tenant(
self,
authenticated_client,
create_attack_paths_scan,
):
from api.models import Provider, Tenant
foreign_tenant = Tenant.objects.create(name="foreign-tenant-schema")
foreign_provider = Provider.objects.create(
tenant=foreign_tenant,
provider="aws",
uid="123456789998",
)
attack_paths_scan = create_attack_paths_scan(
foreign_provider,
graph_data_ready=True,
)
response = authenticated_client.get(
reverse(
"attack-paths-scans-schema",
kwargs={"pk": attack_paths_scan.id},
)
)
assert response.status_code == status.HTTP_404_NOT_FOUND
# -- Authentication / authorization -------------------------------------------
def test_run_custom_query_returns_401_unauthenticated(
self,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
from rest_framework.test import APIClient
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
unauthenticated = APIClient()
response = unauthenticated.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_401_UNAUTHORIZED
def test_cartography_schema_returns_401_unauthenticated(
self,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
from rest_framework.test import APIClient
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
unauthenticated = APIClient()
response = unauthenticated.get(
reverse(
"attack-paths-scans-schema",
kwargs={"pk": attack_paths_scan.id},
)
)
assert response.status_code == status.HTTP_401_UNAUTHORIZED
def test_run_custom_query_returns_403_no_manage_scans(
self,
authenticated_client_no_permissions_rbac,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
response = authenticated_client_no_permissions_rbac.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_403_FORBIDDEN
# -- Error leakage ------------------------------------------------------------
def test_run_custom_query_does_not_leak_internals_on_error(
self,
authenticated_client,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
from rest_framework.exceptions import APIException
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
with (
patch(
"api.v1.views.attack_paths_views_helpers.execute_custom_query",
side_effect=APIException(
"Attack Paths query execution failed due to a database error"
),
),
patch(
"api.v1.views.graph_database.get_database_name",
return_value="db-test",
),
):
response = authenticated_client.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_500_INTERNAL_SERVER_ERROR
body = json.dumps(response.json()).lower()
for forbidden_term in ["neo4j", "bolt://", "syntaxerror", "db-tenant-"]:
assert forbidden_term not in body
# -- Rate limiting (throttle) -------------------------------------------------
def test_run_custom_query_throttled_after_limit(
self,
authenticated_client,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
mock_graph = {
"nodes": [{"id": "n1", "labels": ["Test"], "properties": {}}],
"relationships": [],
"total_nodes": 1,
"truncated": False,
}
url = reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
)
payload = self._custom_query_payload()
with (
patch(
"api.v1.views.attack_paths_views_helpers.execute_custom_query",
return_value=mock_graph,
),
patch(
"api.v1.views.graph_database.get_database_name",
return_value="db-test",
),
patch(
"api.v1.views.graph_database.clear_cache",
),
):
for i in range(11):
response = authenticated_client.post(
url,
data=payload,
content_type=API_JSON_CONTENT_TYPE,
)
if i < 10:
assert (
response.status_code == status.HTTP_200_OK
), f"Request {i + 1} should succeed with 200 OK, got {response.status_code}"
else:
assert (
response.status_code == status.HTTP_429_TOO_MANY_REQUESTS
), f"Request {i + 1} should be throttled"
# -- Timeout simulation -------------------------------------------------------
def test_run_custom_query_returns_500_on_database_timeout(
self,
authenticated_client,
providers_fixture,
scans_fixture,
create_attack_paths_scan,
):
from rest_framework.exceptions import APIException
provider = providers_fixture[0]
attack_paths_scan = create_attack_paths_scan(
provider,
scan=scans_fixture[0],
graph_data_ready=True,
)
with (
patch(
"api.v1.views.attack_paths_views_helpers.execute_custom_query",
side_effect=APIException(
"Attack Paths query execution failed due to a database error"
),
),
patch(
"api.v1.views.graph_database.get_database_name",
return_value="db-test",
),
):
response = authenticated_client.post(
reverse(
"attack-paths-scans-queries-custom",
kwargs={"pk": attack_paths_scan.id},
),
data=self._custom_query_payload(),
content_type=API_JSON_CONTENT_TYPE,
)
assert response.status_code == status.HTTP_500_INTERNAL_SERVER_ERROR
# -- cartography_schema action ------------------------------------------------
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_cartography_schema_returns_urls(
self,
authenticated_client,
@@ -5018,6 +4684,7 @@ class TestAttackPathsScanViewSet:
assert "schema.md" in attributes["schema_url"]
assert "raw.githubusercontent.com" in attributes["raw_schema_url"]
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_cartography_schema_returns_404_when_no_metadata(
self,
authenticated_client,
@@ -5052,6 +4719,7 @@ class TestAttackPathsScanViewSet:
assert response.status_code == status.HTTP_404_NOT_FOUND
assert "No cartography schema metadata" in str(response.json())
@pytest.mark.skip(reason="Endpoint temporarily blocked")
def test_cartography_schema_returns_400_when_graph_not_ready(
self,
authenticated_client,
@@ -7858,12 +7526,8 @@ class TestUserRoleRelationshipViewSet:
assert response.status_code == status.HTTP_204_NO_CONTENT
relationships = UserRoleRelationship.objects.filter(user=create_test_user.id)
assert relationships.count() == 4
# Use set membership instead of positional slicing — QuerySet ordering is
# non-deterministic without an explicit order_by, which makes slice-based
# checks intermittently fail.
added_role_ids = {r.id for r in roles_fixture[:2]}
relationship_role_ids = {rel.role.id for rel in relationships}
assert added_role_ids.issubset(relationship_role_ids)
for relationship in relationships[2:]: # Skip admin role
assert relationship.role.id in [r.id for r in roles_fixture[:2]]
def test_create_relationship_already_exists(
self, authenticated_client, roles_fixture, create_test_user
+1 -1
View File
@@ -1241,7 +1241,7 @@ class AttackPathsQueryRunRequestSerializer(BaseSerializerV1):
class AttackPathsCustomQueryRunRequestSerializer(BaseSerializerV1):
query = serializers.CharField(max_length=10000, min_length=1, trim_whitespace=True)
query = serializers.CharField()
class JSONAPIMeta:
resource_name = "attack-paths-custom-query-run-requests"
+11 -7
View File
@@ -51,13 +51,6 @@ from api.v1.views import (
)
# This helper view is used to block any endpoints that should not be available
# To use it, add a new entry in the `urlpatterns` list, for example (old but real one):
# path(
# "attack-paths-scans/<uuid:pk>/queries/custom",
# _blocked_endpoint,
# name="attack-paths-scans-queries-custom-blocked",
# ),
@csrf_exempt
def _blocked_endpoint(request, *args, **kwargs):
return JsonResponse(
@@ -216,6 +209,17 @@ urlpatterns = [
path("tokens/saml", SAMLTokenValidateView.as_view(), name="token-saml"),
path("tokens/google", GoogleSocialLoginView.as_view(), name="token-google"),
path("tokens/github", GithubSocialLoginView.as_view(), name="token-github"),
# TODO: Remove these blocked endpoints once they are properly tested
path(
"attack-paths-scans/<uuid:pk>/queries/custom",
_blocked_endpoint,
name="attack-paths-scans-queries-custom-blocked",
),
path(
"attack-paths-scans/<uuid:pk>/schema",
_blocked_endpoint,
name="attack-paths-scans-schema-blocked",
),
path("", include(router.urls)),
path("", include(tenants_router.urls)),
path("", include(users_router.urls)),
+1 -6
View File
@@ -408,7 +408,7 @@ class SchemaView(SpectacularAPIView):
def get(self, request, *args, **kwargs):
spectacular_settings.TITLE = "Prowler API"
spectacular_settings.VERSION = "1.22.1"
spectacular_settings.VERSION = "1.21.0"
spectacular_settings.DESCRIPTION = (
"Prowler API specification.\n\nThis file is auto-generated."
)
@@ -2452,11 +2452,6 @@ class AttackPathsScanViewSet(BaseRLSViewSet):
# RBAC required permissions
required_permissions = [Permissions.MANAGE_SCANS]
def get_throttles(self):
if self.action == "run_custom_attack_paths_query":
self.throttle_scope = "attack-paths-custom-query"
return super().get_throttles()
def set_required_permissions(self):
if self.request.method in SAFE_METHODS:
self.required_permissions = []
+1 -4
View File
@@ -113,11 +113,8 @@ REST_FRAMEWORK = {
"rest_framework.throttling.ScopedRateThrottle",
],
"DEFAULT_THROTTLE_RATES": {
"dj_rest_auth": None,
"token-obtain": env("DJANGO_THROTTLE_TOKEN_OBTAIN", default=None),
"attack-paths-custom-query": env(
"DJANGO_THROTTLE_ATTACK_PATHS_CUSTOM_QUERY", default="10/min"
),
"dj_rest_auth": None,
},
}
@@ -3,10 +3,6 @@ from config.env import env
DEBUG = env.bool("DJANGO_DEBUG", default=False)
ALLOWED_HOSTS = env.list("DJANGO_ALLOWED_HOSTS", default=["localhost", "127.0.0.1"])
CORS_ALLOWED_ORIGINS = env.list(
"DJANGO_CORS_ALLOWED_ORIGINS",
default=["http://localhost", "http://127.0.0.1"],
)
# Database
# TODO Use Django database routers https://docs.djangoproject.com/en/5.0/topics/db/multi-db/#automatic-database-routing
@@ -1,30 +1,25 @@
from dataclasses import dataclass
from typing import Callable
from uuid import UUID
from config.env import env
from tasks.jobs.attack_paths import aws
# Batch size for Neo4j write operations (resource labeling, cleanup)
# Batch size for Neo4j operations
BATCH_SIZE = env.int("ATTACK_PATHS_BATCH_SIZE", 1000)
# Batch size for Postgres findings fetch (keyset pagination page size)
FINDINGS_BATCH_SIZE = env.int("ATTACK_PATHS_FINDINGS_BATCH_SIZE", 500)
# Batch size for temp-to-tenant graph sync (nodes and relationships per cursor page)
SYNC_BATCH_SIZE = env.int("ATTACK_PATHS_SYNC_BATCH_SIZE", 250)
# Neo4j internal labels (Prowler-specific, not provider-specific)
# - `Internet`: Singleton node representing external internet access for exposed-resource queries
# - `ProwlerFinding`: Label for finding nodes created by Prowler and linked to cloud resources
# - `_ProviderResource`: Added to ALL synced nodes for provider isolation and drop/query ops
INTERNET_NODE_LABEL = "Internet"
# - `Internet`: Singleton node representing external internet access for exposed-resource queries
PROWLER_FINDING_LABEL = "ProwlerFinding"
PROVIDER_RESOURCE_LABEL = "_ProviderResource"
INTERNET_NODE_LABEL = "Internet"
# Dynamic isolation labels that contain entity UUIDs and are added to every synced node during sync
# Format: _Tenant_{uuid_no_hyphens}, _Provider_{uuid_no_hyphens}
TENANT_LABEL_PREFIX = "_Tenant_"
PROVIDER_LABEL_PREFIX = "_Provider_"
DYNAMIC_ISOLATION_PREFIXES = [TENANT_LABEL_PREFIX, PROVIDER_LABEL_PREFIX]
# Phase 1 dual-write: deprecated label kept for drop_subgraph and infrastructure queries
# Remove in Phase 2 once all nodes use the private label exclusively
DEPRECATED_PROVIDER_RESOURCE_LABEL = "ProviderResource"
@dataclass(frozen=True)
@@ -36,6 +31,7 @@ class ProviderConfig:
uid_field: str # e.g., "arn"
# Label for resources connected to the account node, enabling indexed finding lookups.
resource_label: str # e.g., "_AWSResource"
deprecated_resource_label: str # e.g., "AWSResource"
ingestion_function: Callable
@@ -47,6 +43,7 @@ AWS_CONFIG = ProviderConfig(
root_node_label="AWSAccount",
uid_field="arn",
resource_label="_AWSResource",
deprecated_resource_label="AWSResource",
ingestion_function=aws.start_aws_ingestion,
)
@@ -59,16 +56,18 @@ PROVIDER_CONFIGS: dict[str, ProviderConfig] = {
INTERNAL_LABELS: list[str] = [
"Tenant", # From Cartography, but it looks like it's ours
PROVIDER_RESOURCE_LABEL,
DEPRECATED_PROVIDER_RESOURCE_LABEL,
# Add all provider-specific resource labels
*[config.resource_label for config in PROVIDER_CONFIGS.values()],
*[config.deprecated_resource_label for config in PROVIDER_CONFIGS.values()],
]
# Provider isolation properties
PROVIDER_ID_PROPERTY = "_provider_id"
PROVIDER_ELEMENT_ID_PROPERTY = "_provider_element_id"
PROVIDER_ISOLATION_PROPERTIES: list[str] = [
PROVIDER_ID_PROPERTY,
PROVIDER_ELEMENT_ID_PROPERTY,
"_provider_id",
"_provider_element_id",
"provider_id",
"provider_element_id",
]
# Cartography bookkeeping metadata
@@ -118,25 +117,7 @@ def get_provider_resource_label(provider_type: str) -> str:
return config.resource_label if config else "_UnknownProviderResource"
# Dynamic Isolation Label Helpers
# --------------------------------
def _normalize_uuid(value: str | UUID) -> str:
"""Strip hyphens from a UUID string for use in Neo4j labels."""
return str(value).replace("-", "")
def get_tenant_label(tenant_id: str | UUID) -> str:
"""Get the Neo4j label for a tenant (e.g., `_Tenant_019c41ee7df37deca684d839f95619f8`)."""
return f"{TENANT_LABEL_PREFIX}{_normalize_uuid(tenant_id)}"
def get_provider_label(provider_id: str | UUID) -> str:
"""Get the Neo4j label for a provider (e.g., `_Provider_019c41ee7df37deca684d839f95619f8`)."""
return f"{PROVIDER_LABEL_PREFIX}{_normalize_uuid(provider_id)}"
def is_dynamic_isolation_label(label: str) -> bool:
"""Check if a label is a dynamic tenant/provider isolation label."""
return any(label.startswith(prefix) for prefix in DYNAMIC_ISOLATION_PREFIXES)
def get_deprecated_provider_resource_label(provider_type: str) -> str:
"""Get the deprecated resource label for a provider type (e.g., `AWSResource`)."""
config = PROVIDER_CONFIGS.get(provider_type)
return config.deprecated_resource_label if config else "UnknownProviderResource"
@@ -3,13 +3,15 @@ from typing import Any
from cartography.config import Config as CartographyConfig
from celery.utils.log import get_task_logger
from tasks.jobs.attack_paths.config import is_provider_available
from api.attack_paths import database as graph_database
from api.db_utils import rls_transaction
from api.models import AttackPathsScan as ProwlerAPIAttackPathsScan
from api.models import Provider as ProwlerAPIProvider
from api.models import StateChoices
from api.models import (
AttackPathsScan as ProwlerAPIAttackPathsScan,
Provider as ProwlerAPIProvider,
StateChoices,
)
from tasks.jobs.attack_paths.config import is_provider_available
logger = get_task_logger(__name__)
@@ -153,37 +155,6 @@ def set_provider_graph_data_ready(
attack_paths_scan.refresh_from_db(fields=["graph_data_ready"])
def recover_graph_data_ready(
attack_paths_scan: ProwlerAPIAttackPathsScan,
) -> None:
"""
Best-effort recovery of `graph_data_ready` after a scan failure.
Queries Neo4j to check if the provider still has data in the tenant
database. If data exists, restores `graph_data_ready=True` for all scans
of this provider. Never raises.
Trade-off: if the worker crashed mid-sync, partial data may exist and
this will re-enable queries against it. We accept that because leaving
`graph_data_ready=False` permanently (blocking all queries until the
next successful scan) is a worse outcome for the user.
"""
try:
tenant_db = graph_database.get_database_name(attack_paths_scan.tenant_id)
if graph_database.has_provider_data(
tenant_db, str(attack_paths_scan.provider_id)
):
set_provider_graph_data_ready(attack_paths_scan, True)
logger.info(
f"Recovered `graph_data_ready` for provider {attack_paths_scan.provider_id}"
)
except Exception:
logger.exception(
f"Failed to recover `graph_data_ready` for provider {attack_paths_scan.provider_id}"
)
def fail_attack_paths_scan(
tenant_id: str,
scan_id: str,
@@ -214,5 +185,3 @@ def fail_attack_paths_scan(
StateChoices.FAILED,
{"global_error": error},
)
recover_graph_data_ready(attack_paths_scan)
@@ -9,15 +9,23 @@ This module handles:
"""
from collections import defaultdict
from dataclasses import asdict, dataclass, fields
from typing import Any, Generator
from uuid import UUID
import neo4j
from cartography.config import Config as CartographyConfig
from celery.utils.log import get_task_logger
from api.db_router import READ_REPLICA_ALIAS
from api.db_utils import rls_transaction
from api.models import Finding as FindingModel
from api.models import Provider, ResourceFindingMapping
from prowler.config import config as ProwlerConfig
from tasks.jobs.attack_paths.config import (
BATCH_SIZE,
FINDINGS_BATCH_SIZE,
get_deprecated_provider_resource_label,
get_node_uid_field,
get_provider_resource_label,
get_root_node_label,
@@ -30,54 +38,75 @@ from tasks.jobs.attack_paths.queries import (
render_cypher_template,
)
from api.db_router import READ_REPLICA_ALIAS
from api.db_utils import rls_transaction
from api.models import Finding as FindingModel
from api.models import Provider, ResourceFindingMapping
from prowler.config import config as ProwlerConfig
logger = get_task_logger(__name__)
# Django ORM field names for `.values()` queries
# Most map 1:1 to Neo4j property names, exceptions are remapped in `_to_neo4j_dict`
_DB_QUERY_FIELDS = [
"id",
"uid",
"inserted_at",
"updated_at",
"first_seen_at",
"scan_id",
"delta",
"status",
"status_extended",
"severity",
"check_id",
"check_metadata__checktitle",
"muted",
"muted_reason",
]
# Type Definitions
# -----------------
# Maps dataclass field names to Django ORM query field names
_DB_FIELD_MAP: dict[str, str] = {
"check_title": "check_metadata__checktitle",
}
def _to_neo4j_dict(record: dict[str, Any], resource_uid: str) -> dict[str, Any]:
"""Transform a Django `.values()` record into a `dict` ready for Neo4j ingestion."""
return {
"id": str(record["id"]),
"uid": record["uid"],
"inserted_at": record["inserted_at"],
"updated_at": record["updated_at"],
"first_seen_at": record["first_seen_at"],
"scan_id": str(record["scan_id"]),
"delta": record["delta"],
"status": record["status"],
"status_extended": record["status_extended"],
"severity": record["severity"],
"check_id": str(record["check_id"]),
"check_title": record["check_metadata__checktitle"],
"muted": record["muted"],
"muted_reason": record["muted_reason"],
"resource_uid": resource_uid,
}
@dataclass(slots=True)
class Finding:
"""
Finding data for Neo4j ingestion.
Can be created from a Django .values() query result using from_db_record().
"""
id: str
uid: str
inserted_at: str
updated_at: str
first_seen_at: str
scan_id: str
delta: str
status: str
status_extended: str
severity: str
check_id: str
check_title: str
muted: bool
muted_reason: str | None
resource_uid: str | None = None
@classmethod
def get_db_query_fields(cls) -> tuple[str, ...]:
"""Get field names for Django .values() query."""
return tuple(
_DB_FIELD_MAP.get(f.name, f.name)
for f in fields(cls)
if f.name != "resource_uid"
)
@classmethod
def from_db_record(cls, record: dict[str, Any], resource_uid: str) -> "Finding":
"""Create a Finding from a Django .values() query result."""
return cls(
id=str(record["id"]),
uid=record["uid"],
inserted_at=record["inserted_at"],
updated_at=record["updated_at"],
first_seen_at=record["first_seen_at"],
scan_id=str(record["scan_id"]),
delta=record["delta"],
status=record["status"],
status_extended=record["status_extended"],
severity=record["severity"],
check_id=str(record["check_id"]),
check_title=record["check_metadata__checktitle"],
muted=record["muted"],
muted_reason=record["muted_reason"],
resource_uid=resource_uid,
)
def to_dict(self) -> dict[str, Any]:
"""Convert to dict for Neo4j ingestion."""
return asdict(self)
# Public API
@@ -124,6 +153,9 @@ def add_resource_label(
{
"__ROOT_LABEL__": get_root_node_label(provider_type),
"__RESOURCE_LABEL__": get_provider_resource_label(provider_type),
"__DEPRECATED_RESOURCE_LABEL__": get_deprecated_provider_resource_label(
provider_type
),
},
)
@@ -152,7 +184,7 @@ def add_resource_label(
def load_findings(
neo4j_session: neo4j.Session,
findings_batches: Generator[list[dict[str, Any]], None, None],
findings_batches: Generator[list[Finding], None, None],
prowler_api_provider: Provider,
config: CartographyConfig,
) -> None:
@@ -181,7 +213,7 @@ def load_findings(
batch_size = len(batch)
total_records += batch_size
parameters["findings_data"] = batch
parameters["findings_data"] = [f.to_dict() for f in batch]
logger.info(f"Loading findings batch {batch_num} ({batch_size} records)")
neo4j_session.run(query, parameters)
@@ -219,17 +251,16 @@ def cleanup_findings(
def stream_findings_with_resources(
prowler_api_provider: Provider,
scan_id: str,
) -> Generator[list[dict[str, Any]], None, None]:
) -> Generator[list[Finding], None, None]:
"""
Stream findings with their associated resources in batches.
Uses keyset pagination for efficient traversal of large datasets.
Memory efficient: yields one batch at a time as dicts ready for Neo4j ingestion,
never holds all findings in memory.
Memory efficient: yields one batch at a time, never holds all findings in memory.
"""
logger.info(
f"Starting findings stream for scan {scan_id} "
f"(tenant {prowler_api_provider.tenant_id}) with batch size {FINDINGS_BATCH_SIZE}"
f"(tenant {prowler_api_provider.tenant_id}) with batch size {BATCH_SIZE}"
)
tenant_id = prowler_api_provider.tenant_id
@@ -278,14 +309,15 @@ def _fetch_findings_batch(
Uses read replica and RLS-scoped transaction.
"""
with rls_transaction(tenant_id, using=READ_REPLICA_ALIAS):
# Use `all_objects` to get `Findings` even on soft-deleted `Providers`
# But even the provider is already validated as active in this context
# Use all_objects to avoid the ActiveProviderManager's implicit JOIN
# through Scan -> Provider (to check is_deleted=False).
# The provider is already validated as active in this context.
qs = FindingModel.all_objects.filter(scan_id=scan_id).order_by("id")
if after_id is not None:
qs = qs.filter(id__gt=after_id)
return list(qs.values(*_DB_QUERY_FIELDS)[:FINDINGS_BATCH_SIZE])
return list(qs.values(*Finding.get_db_query_fields())[:BATCH_SIZE])
# Batch Enrichment
@@ -295,7 +327,7 @@ def _fetch_findings_batch(
def _enrich_batch_with_resources(
findings_batch: list[dict[str, Any]],
tenant_id: str,
) -> list[dict[str, Any]]:
) -> list[Finding]:
"""
Enrich findings with their resource UIDs.
@@ -306,7 +338,7 @@ def _enrich_batch_with_resources(
resource_map = _build_finding_resource_map(finding_ids, tenant_id)
return [
_to_neo4j_dict(finding, resource_uid)
Finding.from_db_record(finding, resource_uid)
for finding in findings_batch
for resource_uid in resource_map.get(finding["id"], [])
]
@@ -6,10 +6,9 @@ from cartography.client.core.tx import run_write_query
from celery.utils.log import get_task_logger
from tasks.jobs.attack_paths.config import (
DEPRECATED_PROVIDER_RESOURCE_LABEL,
INTERNET_NODE_LABEL,
PROWLER_FINDING_LABEL,
PROVIDER_ELEMENT_ID_PROPERTY,
PROVIDER_ID_PROPERTY,
PROVIDER_RESOURCE_LABEL,
)
@@ -28,6 +27,8 @@ FINDINGS_INDEX_STATEMENTS = [
# Resource indexes for Prowler Finding lookups
"CREATE INDEX aws_resource_arn IF NOT EXISTS FOR (n:_AWSResource) ON (n.arn);",
"CREATE INDEX aws_resource_id IF NOT EXISTS FOR (n:_AWSResource) ON (n.id);",
"CREATE INDEX deprecated_aws_resource_arn IF NOT EXISTS FOR (n:AWSResource) ON (n.arn);",
"CREATE INDEX deprecated_aws_resource_id IF NOT EXISTS FOR (n:AWSResource) ON (n.id);",
# Prowler Finding indexes
f"CREATE INDEX prowler_finding_id IF NOT EXISTS FOR (n:{PROWLER_FINDING_LABEL}) ON (n.id);",
f"CREATE INDEX prowler_finding_provider_uid IF NOT EXISTS FOR (n:{PROWLER_FINDING_LABEL}) ON (n.provider_uid);",
@@ -39,8 +40,10 @@ FINDINGS_INDEX_STATEMENTS = [
# Indexes for provider resource sync operations
SYNC_INDEX_STATEMENTS = [
f"CREATE INDEX provider_resource_element_id IF NOT EXISTS FOR (n:{PROVIDER_RESOURCE_LABEL}) ON (n.{PROVIDER_ELEMENT_ID_PROPERTY});",
f"CREATE INDEX provider_resource_provider_id IF NOT EXISTS FOR (n:{PROVIDER_RESOURCE_LABEL}) ON (n.{PROVIDER_ID_PROPERTY});",
f"CREATE INDEX provider_element_id IF NOT EXISTS FOR (n:{PROVIDER_RESOURCE_LABEL}) ON (n._provider_element_id);",
f"CREATE INDEX provider_resource_provider_id IF NOT EXISTS FOR (n:{PROVIDER_RESOURCE_LABEL}) ON (n._provider_id);",
f"CREATE INDEX deprecated_provider_element_id IF NOT EXISTS FOR (n:{DEPRECATED_PROVIDER_RESOURCE_LABEL}) ON (n.provider_element_id);",
f"CREATE INDEX deprecated_provider_resource_provider_id IF NOT EXISTS FOR (n:{DEPRECATED_PROVIDER_RESOURCE_LABEL}) ON (n.provider_id);",
]
@@ -2,8 +2,6 @@
from tasks.jobs.attack_paths.config import (
INTERNET_NODE_LABEL,
PROWLER_FINDING_LABEL,
PROVIDER_ELEMENT_ID_PROPERTY,
PROVIDER_ID_PROPERTY,
PROVIDER_RESOURCE_LABEL,
)
@@ -28,7 +26,7 @@ ADD_RESOURCE_LABEL_TEMPLATE = """
MATCH (account:__ROOT_LABEL__ {id: $provider_uid})-->(r)
WHERE NOT r:__ROOT_LABEL__ AND NOT r:__RESOURCE_LABEL__
WITH r LIMIT $batch_size
SET r:__RESOURCE_LABEL__
SET r:__RESOURCE_LABEL__:__DEPRECATED_RESOURCE_LABEL__
RETURN COUNT(r) AS labeled_count
"""
@@ -151,18 +149,22 @@ RELATIONSHIPS_FETCH_QUERY = """
LIMIT $batch_size
"""
NODE_SYNC_TEMPLATE = f"""
NODE_SYNC_TEMPLATE = """
UNWIND $rows AS row
MERGE (n:__NODE_LABELS__ {{{PROVIDER_ELEMENT_ID_PROPERTY}: row.provider_element_id}})
MERGE (n:__NODE_LABELS__ {_provider_element_id: row.provider_element_id})
SET n += row.props
SET n.{PROVIDER_ID_PROPERTY} = $provider_id
"""
SET n._provider_id = $provider_id
SET n.provider_element_id = row.provider_element_id
SET n.provider_id = $provider_id
""" # The last two lines are deprecated properties
RELATIONSHIP_SYNC_TEMPLATE = f"""
UNWIND $rows AS row
MATCH (s:{PROVIDER_RESOURCE_LABEL} {{{PROVIDER_ELEMENT_ID_PROPERTY}: row.start_element_id}})
MATCH (t:{PROVIDER_RESOURCE_LABEL} {{{PROVIDER_ELEMENT_ID_PROPERTY}: row.end_element_id}})
MERGE (s)-[r:__REL_TYPE__ {{{PROVIDER_ELEMENT_ID_PROPERTY}: row.provider_element_id}}]->(t)
MATCH (s:{PROVIDER_RESOURCE_LABEL} {{_provider_element_id: row.start_element_id}})
MATCH (t:{PROVIDER_RESOURCE_LABEL} {{_provider_element_id: row.end_element_id}})
MERGE (s)-[r:__REL_TYPE__ {{_provider_element_id: row.provider_element_id}}]->(t)
SET r += row.props
SET r.{PROVIDER_ID_PROPERTY} = $provider_id
"""
SET r._provider_id = $provider_id
SET r.provider_element_id = row.provider_element_id
SET r.provider_id = $provider_id
""" # The last two lines are deprecated properties
+10 -31
View File
@@ -55,6 +55,7 @@ exception propagates to Celery.
import logging
import time
from typing import Any
from cartography.config import Config as CartographyConfig
@@ -62,14 +63,16 @@ from cartography.intel import analysis as cartography_analysis
from cartography.intel import create_indexes as cartography_create_indexes
from cartography.intel import ontology as cartography_ontology
from celery.utils.log import get_task_logger
from tasks.jobs.attack_paths import db_utils, findings, internet, sync, utils
from tasks.jobs.attack_paths.config import get_cartography_ingestion_function
from api.attack_paths import database as graph_database
from api.db_utils import rls_transaction
from api.models import Provider as ProwlerAPIProvider
from api.models import StateChoices
from api.models import (
Provider as ProwlerAPIProvider,
StateChoices,
)
from api.utils import initialize_prowler_provider
from tasks.jobs.attack_paths import db_utils, findings, internet, sync, utils
from tasks.jobs.attack_paths.config import get_cartography_ingestion_function
# Without this Celery goes crazy with Cartography logging
logging.getLogger("cartography").setLevel(logging.ERROR)
@@ -144,10 +147,6 @@ def run(tenant_id: str, scan_id: str, task_id: str) -> dict[str, Any]:
attack_paths_scan, task_id, tenant_cartography_config
)
subgraph_dropped = False
sync_completed = False
provider_gated = False
try:
logger.info(
f"Creating Neo4j database {tmp_cartography_config.neo4j_database} for tenant {prowler_api_provider.tenant_id}"
@@ -226,12 +225,10 @@ def run(tenant_id: str, scan_id: str, task_id: str) -> dict[str, Any]:
logger.info(f"Deleting existing provider graph in {tenant_database_name}")
db_utils.set_provider_graph_data_ready(attack_paths_scan, False)
provider_gated = True
graph_database.drop_subgraph(
database=tenant_database_name,
provider_id=str(prowler_api_provider.id),
)
subgraph_dropped = True
db_utils.update_attack_paths_scan_progress(attack_paths_scan, 98)
logger.info(
@@ -240,10 +237,8 @@ def run(tenant_id: str, scan_id: str, task_id: str) -> dict[str, Any]:
sync.sync_graph(
source_database=tmp_database_name,
target_database=tenant_database_name,
tenant_id=str(prowler_api_provider.tenant_id),
provider_id=str(prowler_api_provider.id),
)
sync_completed = True
db_utils.set_graph_data_ready(attack_paths_scan, True)
db_utils.update_attack_paths_scan_progress(attack_paths_scan, 99)
@@ -268,39 +263,23 @@ def run(tenant_id: str, scan_id: str, task_id: str) -> dict[str, Any]:
logger.exception(exception_message)
ingestion_exceptions["global_error"] = exception_message
# Recover graph_data_ready based on how far the swap got.
# Partial drop (mid-batch failure) may leave `subgraph_dropped=False`
# with data partially deleted, so we prefer that over permanently blocked queries.
try:
if sync_completed:
db_utils.set_graph_data_ready(attack_paths_scan, True)
elif provider_gated and not subgraph_dropped:
db_utils.set_provider_graph_data_ready(attack_paths_scan, True)
except Exception:
logger.error(
f"Failed to recover `graph_data_ready` for provider {attack_paths_scan.provider_id}",
exc_info=True,
)
# Dropping the temporary database if it still exists
# Handling databases changes
try:
graph_database.drop_database(tmp_cartography_config.neo4j_database)
except Exception as e:
logger.error(
f"Failed to drop temporary Neo4j database `{tmp_cartography_config.neo4j_database}` during cleanup: {e}",
f"Failed to drop temporary Neo4j database {tmp_cartography_config.neo4j_database} during cleanup: {e}",
exc_info=True,
)
# Set Attack Paths scan state to FAILED
try:
db_utils.finish_attack_paths_scan(
attack_paths_scan, StateChoices.FAILED, ingestion_exceptions
)
except Exception as e:
logger.error(
f"Could not mark Attack Paths scan {attack_paths_scan.id} as `FAILED` (row may have been deleted): {e}",
f"Could not mark attack paths scan {attack_paths_scan.id} as FAILED (row may have been deleted): {e}",
exc_info=True,
)
+66 -85
View File
@@ -8,16 +8,14 @@ to the tenant database, adding provider isolation labels and properties.
from collections import defaultdict
from typing import Any
import neo4j
from celery.utils.log import get_task_logger
from api.attack_paths import database as graph_database
from tasks.jobs.attack_paths.config import (
BATCH_SIZE,
DEPRECATED_PROVIDER_RESOURCE_LABEL,
PROVIDER_ISOLATION_PROPERTIES,
PROVIDER_RESOURCE_LABEL,
SYNC_BATCH_SIZE,
get_provider_label,
get_tenant_label,
)
from tasks.jobs.attack_paths.indexes import IndexType, create_indexes
from tasks.jobs.attack_paths.queries import (
@@ -39,7 +37,6 @@ def create_sync_indexes(neo4j_session) -> None:
def sync_graph(
source_database: str,
target_database: str,
tenant_id: str,
provider_id: str,
) -> dict[str, int]:
"""
@@ -48,7 +45,6 @@ def sync_graph(
Args:
`source_database`: The temporary scan database
`target_database`: The tenant database
`tenant_id`: The tenant ID for isolation
`provider_id`: The provider ID for isolation
Returns:
@@ -57,7 +53,6 @@ def sync_graph(
nodes_synced = sync_nodes(
source_database,
target_database,
tenant_id,
provider_id,
)
relationships_synced = sync_relationships(
@@ -75,45 +70,50 @@ def sync_graph(
def sync_nodes(
source_database: str,
target_database: str,
tenant_id: str,
provider_id: str,
) -> int:
"""
Sync nodes from source to target database.
Adds `_ProviderResource` label and `_provider_id` property to all nodes.
Also adds dynamic `_Tenant_{id}` and `_Provider_{id}` isolation labels.
Source and target sessions are opened sequentially per batch to avoid
holding two Bolt connections simultaneously for the entire sync duration.
"""
last_id = -1
total_synced = 0
while True:
grouped: dict[tuple[str, ...], list[dict[str, Any]]] = defaultdict(list)
batch_count = 0
with graph_database.get_session(source_database) as source_session:
result = source_session.run(
NODE_FETCH_QUERY,
{"last_id": last_id, "batch_size": SYNC_BATCH_SIZE},
with (
graph_database.get_session(source_database) as source_session,
graph_database.get_session(target_database) as target_session,
):
while True:
rows = list(
source_session.run(
NODE_FETCH_QUERY,
{"last_id": last_id, "batch_size": BATCH_SIZE},
)
)
for record in result:
batch_count += 1
last_id = record["internal_id"]
key, value = _node_to_sync_dict(record, provider_id)
grouped[key].append(value)
if batch_count == 0:
break
if not rows:
break
last_id = rows[-1]["internal_id"]
grouped: dict[tuple[str, ...], list[dict[str, Any]]] = defaultdict(list)
for row in rows:
labels = tuple(sorted(set(row["labels"] or [])))
props = dict(row["props"] or {})
_strip_internal_properties(props)
provider_element_id = f"{provider_id}:{row['element_id']}"
grouped[labels].append(
{
"provider_element_id": provider_element_id,
"props": props,
}
)
with graph_database.get_session(target_database) as target_session:
for labels, batch in grouped.items():
label_set = set(labels)
label_set.add(PROVIDER_RESOURCE_LABEL)
label_set.add(get_tenant_label(tenant_id))
label_set.add(get_provider_label(provider_id))
label_set.add(DEPRECATED_PROVIDER_RESOURCE_LABEL)
node_labels = ":".join(f"`{label}`" for label in sorted(label_set))
query = render_cypher_template(
@@ -127,10 +127,10 @@ def sync_nodes(
},
)
total_synced += batch_count
logger.info(
f"Synced {total_synced} nodes from {source_database} to {target_database}"
)
total_synced += len(rows)
logger.info(
f"Synced {total_synced} nodes from {source_database} to {target_database}"
)
return total_synced
@@ -144,32 +144,41 @@ def sync_relationships(
Sync relationships from source to target database.
Adds `_provider_id` property to all relationships.
Source and target sessions are opened sequentially per batch to avoid
holding two Bolt connections simultaneously for the entire sync duration.
"""
last_id = -1
total_synced = 0
while True:
grouped: dict[str, list[dict[str, Any]]] = defaultdict(list)
batch_count = 0
with graph_database.get_session(source_database) as source_session:
result = source_session.run(
RELATIONSHIPS_FETCH_QUERY,
{"last_id": last_id, "batch_size": SYNC_BATCH_SIZE},
with (
graph_database.get_session(source_database) as source_session,
graph_database.get_session(target_database) as target_session,
):
while True:
rows = list(
source_session.run(
RELATIONSHIPS_FETCH_QUERY,
{"last_id": last_id, "batch_size": BATCH_SIZE},
)
)
for record in result:
batch_count += 1
last_id = record["internal_id"]
key, value = _rel_to_sync_dict(record, provider_id)
grouped[key].append(value)
if batch_count == 0:
break
if not rows:
break
last_id = rows[-1]["internal_id"]
grouped: dict[str, list[dict[str, Any]]] = defaultdict(list)
for row in rows:
props = dict(row["props"] or {})
_strip_internal_properties(props)
rel_type = row["rel_type"]
grouped[rel_type].append(
{
"start_element_id": f"{provider_id}:{row['start_element_id']}",
"end_element_id": f"{provider_id}:{row['end_element_id']}",
"provider_element_id": f"{provider_id}:{rel_type}:{row['internal_id']}",
"props": props,
}
)
with graph_database.get_session(target_database) as target_session:
for rel_type, batch in grouped.items():
query = render_cypher_template(
RELATIONSHIP_SYNC_TEMPLATE, {"__REL_TYPE__": rel_type}
@@ -182,42 +191,14 @@ def sync_relationships(
},
)
total_synced += batch_count
logger.info(
f"Synced {total_synced} relationships from {source_database} to {target_database}"
)
total_synced += len(rows)
logger.info(
f"Synced {total_synced} relationships from {source_database} to {target_database}"
)
return total_synced
def _node_to_sync_dict(
record: neo4j.Record, provider_id: str
) -> tuple[tuple[str, ...], dict[str, Any]]:
"""Transform a source node record into a (grouping_key, sync_dict) pair."""
props = dict(record["props"] or {})
_strip_internal_properties(props)
labels = tuple(sorted(set(record["labels"] or [])))
return labels, {
"provider_element_id": f"{provider_id}:{record['element_id']}",
"props": props,
}
def _rel_to_sync_dict(
record: neo4j.Record, provider_id: str
) -> tuple[str, dict[str, Any]]:
"""Transform a source relationship record into a (grouping_key, sync_dict) pair."""
props = dict(record["props"] or {})
_strip_internal_properties(props)
rel_type = record["rel_type"]
return rel_type, {
"start_element_id": f"{provider_id}:{record['start_element_id']}",
"end_element_id": f"{provider_id}:{record['end_element_id']}",
"provider_element_id": f"{provider_id}:{rel_type}:{record['internal_id']}",
"props": props,
}
def _strip_internal_properties(props: dict[str, Any]) -> None:
"""Remove provider isolation properties before the += spread in sync templates."""
for key in PROVIDER_ISOLATION_PROPERTIES:
@@ -4,7 +4,7 @@ from django.db.models import Count, Q
from api.db_router import READ_REPLICA_ALIAS
from api.db_utils import rls_transaction
from api.models import Finding, Scan, StatusChoices
from api.models import Finding, StatusChoices
from prowler.lib.outputs.finding import Finding as FindingOutput
logger = get_task_logger(__name__)
@@ -35,26 +35,25 @@ def _aggregate_requirement_statistics_from_database(
}
"""
requirement_statistics_by_check_id = {}
# TODO: review when finding-resource relation changes from 1:1
# TODO: take into account that now the relation is 1 finding == 1 resource, review this when the logic changes
with rls_transaction(tenant_id, using=READ_REPLICA_ALIAS):
# Pre-check: skip if the scan's provider is deleted (avoids JOINs in the main query)
if Scan.all_objects.filter(id=scan_id, provider__is_deleted=True).exists():
return requirement_statistics_by_check_id
aggregated_statistics_queryset = (
Finding.all_objects.filter(
tenant_id=tenant_id,
scan_id=scan_id,
muted=False,
resources__provider__is_deleted=False,
)
.values("check_id")
.annotate(
total_findings=Count(
"id",
distinct=True,
filter=Q(status__in=[StatusChoices.PASS, StatusChoices.FAIL]),
),
passed_findings=Count(
"id",
distinct=True,
filter=Q(status=StatusChoices.PASS),
),
)
File diff suppressed because it is too large Load Diff
+17 -9
View File
@@ -169,27 +169,35 @@ class TestAggregateRequirementStatistics:
assert result["check_1"]["passed"] == 1
assert result["check_1"]["total"] == 1
def test_skips_aggregation_for_deleted_provider(
self, tenants_fixture, scans_fixture
):
"""Verify aggregation returns empty when the scan's provider is soft-deleted."""
def test_excludes_findings_without_resources(self, tenants_fixture, scans_fixture):
"""Verify findings without resources are excluded from aggregation."""
tenant = tenants_fixture[0]
scan = scans_fixture[0]
# Finding WITH resource → should be counted
self._create_finding_with_resource(
tenant, scan, "finding-1", "check_1", StatusChoices.PASS
)
# Soft-delete the provider
provider = scan.provider
provider.is_deleted = True
provider.save(update_fields=["is_deleted"])
# Finding WITHOUT resource → should be EXCLUDED
Finding.objects.create(
tenant_id=tenant.id,
scan=scan,
uid="finding-2",
check_id="check_1",
status=StatusChoices.FAIL,
severity=Severity.high,
impact=Severity.high,
check_metadata={},
raw_result={},
)
result = _aggregate_requirement_statistics_from_database(
str(tenant.id), str(scan.id)
)
assert result == {}
assert result["check_1"]["passed"] == 1
assert result["check_1"]["total"] == 1
def test_multiple_resources_no_double_count(self, tenants_fixture, scans_fixture):
"""Verify a finding with multiple resources is only counted once."""
+3 -3
View File
@@ -558,9 +558,9 @@ neo4j:
# Neo4j Configuration (yaml format)
config:
dbms_security_procedures_allowlist: "apoc.*"
dbms_security_procedures_unrestricted: ""
dbms_security_procedures_unrestricted: "apoc.*"
apoc_config:
apoc.export.file.enabled: "false"
apoc.import.file.enabled: "false"
apoc.export.file.enabled: "true"
apoc.import.file.enabled: "true"
apoc.import.file.use_neo4j_config: "true"
@@ -1,20 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_rbi
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
]
return get_section_containers_rbi(aux, "REQUIREMENTS_ID")
@@ -1,20 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_rbi
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
]
return get_section_containers_rbi(aux, "REQUIREMENTS_ID")
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
-2
View File
@@ -80,8 +80,6 @@ def load_csv_files(csv_files):
result = result.replace("_M65", " - M65")
if "ALIBABACLOUD" in result:
result = result.replace("_ALIBABACLOUD", " - ALIBABACLOUD")
if "ORACLECLOUD" in result:
result = result.replace("_ORACLECLOUD", " - ORACLECLOUD")
results.append(result)
unique_results = set(results)
@@ -211,7 +211,7 @@ Also is important to keep all code examples as short as possible, including the
| email-security | Ensures detection and protection against phishing, spam, spoofing, etc. |
| forensics-ready | Ensures systems are instrumented to support post-incident investigations. Any digital trace or evidence (logs, volume snapshots, memory dumps, network captures, etc.) preserved immutably and accompanied by integrity guarantees, which can be used in a forensic analysis |
| software-supply-chain | Detects or prevents tampering, unauthorized packages, or third-party risks in software supply chain |
| e3 | M365 and Azure Entra checks enabled by or dependent on an E3 license (e.g., baseline security policies, conditional access) |
| e5 | M365 and Azure Entra checks enabled by or dependent on an E5 license (e.g., advanced threat protection, audit, DLP, and eDiscovery) |
| e3 | M365-specific controls enabled by or dependent on an E3 license (e.g., baseline security policies, conditional access) |
| e5 | M365-specific controls enabled by or dependent on an E5 license (e.g., advanced threat protection, audit, DLP, and eDiscovery) |
| privilege-escalation | Detects IAM policies or permissions that allow identities to elevate their privileges beyond their intended scope, potentially gaining administrator or higher-level access through specific action combinations |
| ec2-imdsv1 | Identifies EC2 instances using Instance Metadata Service version 1 (IMDSv1), which is vulnerable to SSRF attacks and should be replaced with IMDSv2 for enhanced security |
| ec2-imdsv1 | Identifies EC2 instances using Instance Metadata Service version 1 (IMDSv1), which is vulnerable to SSRF attacks and should be replaced with IMDSv2 for enhanced security |
@@ -121,8 +121,8 @@ To update the environment file:
Edit the `.env` file and change version values:
```env
PROWLER_UI_VERSION="5.21.0"
PROWLER_API_VERSION="5.21.0"
PROWLER_UI_VERSION="5.19.0"
PROWLER_API_VERSION="5.19.0"
```
<Note>
-6
View File
@@ -2,12 +2,6 @@
All notable changes to the **Prowler MCP Server** are documented in this file.
## [0.5.0] (Prowler v5.21.0)
### 🚀 Added
- Attack Path tool to get Neo4j DB schema [(#10321)](https://github.com/prowler-cloud/prowler/pull/10321)
## [0.4.0] (Prowler v5.19.0)
### 🚀 Added
+1 -1
View File
@@ -5,7 +5,7 @@ This package provides MCP tools for accessing:
- Prowler Hub: All security artifacts (detections, remediations and frameworks) supported by Prowler
"""
__version__ = "0.5.0"
__version__ = "0.4.0"
__author__ = "Prowler Team"
__email__ = "engineering@prowler.com"
@@ -118,51 +118,6 @@ class AttackPathScansListResponse(BaseModel):
)
class AttackPathCartographySchema(MinimalSerializerMixin, BaseModel):
"""Cartography graph schema metadata for a completed attack paths scan.
Contains the schema URL and provider info needed to fetch the full
Cartography schema markdown for openCypher query generation.
"""
model_config = ConfigDict(frozen=True)
id: str = Field(description="Unique identifier for the schema resource")
provider: str = Field(description="Cloud provider type (aws, azure, gcp, etc.)")
cartography_version: str = Field(description="Version of the Cartography schema")
schema_url: str = Field(description="URL to the Cartography schema page on GitHub")
raw_schema_url: str = Field(
description="Raw URL to fetch the Cartography schema markdown content"
)
schema_content: str | None = Field(
default=None,
description="Full Cartography schema markdown content (populated after fetch)",
)
@classmethod
def from_api_response(
cls, response: dict[str, Any]
) -> "AttackPathCartographySchema":
"""Transform JSON:API schema response to model.
Args:
response: Full API response with data and attributes
Returns:
AttackPathCartographySchema instance
"""
data = response.get("data", {})
attributes = data.get("attributes", {})
return cls(
id=data["id"],
provider=attributes["provider"],
cartography_version=attributes["cartography_version"],
schema_url=attributes["schema_url"],
raw_schema_url=attributes["raw_schema_url"],
)
class AttackPathQueryParameter(MinimalSerializerMixin, BaseModel):
"""Parameter definition for an attack paths query.
@@ -8,7 +8,6 @@ through cloud infrastructure relationships.
from typing import Any, Literal
from prowler_mcp_server.prowler_app.models.attack_paths import (
AttackPathCartographySchema,
AttackPathQuery,
AttackPathQueryResult,
AttackPathScansListResponse,
@@ -226,53 +225,3 @@ class AttackPathsTools(BaseTool):
f"Failed to run attack paths query '{query_id}' on scan {scan_id}: {e}"
)
return {"error": f"Failed to run attack paths query '{query_id}': {str(e)}"}
async def get_attack_paths_cartography_schema(
self,
scan_id: str = Field(
description="UUID of a COMPLETED attack paths scan. Use `prowler_app_list_attack_paths_scans` with state=['completed'] to find scan IDs"
),
) -> dict[str, Any]:
"""Retrieve the Cartography graph schema for a completed attack paths scan.
This tool fetches the full Cartography schema (node labels, relationships,
and properties) so the LLM can write accurate custom openCypher queries
for attack paths analysis.
Two-step flow:
1. Calls the Prowler API to get schema metadata (provider, version, URLs)
2. Fetches the raw Cartography schema markdown from GitHub
Returns:
- id: Schema resource identifier
- provider: Cloud provider type
- cartography_version: Schema version
- schema_url: GitHub page URL for reference
- raw_schema_url: Raw markdown URL
- schema_content: Full Cartography schema markdown with node/relationship definitions
Workflow:
1. Use prowler_app_list_attack_paths_scans to find a completed scan
2. Use this tool to get the schema for the scan's provider
3. Use the schema to craft custom openCypher queries
4. Execute queries with prowler_app_run_attack_paths_query
"""
try:
api_response = await self.api_client.get(
f"/attack-paths-scans/{scan_id}/schema"
)
schema = AttackPathCartographySchema.from_api_response(api_response)
schema_content = await self.api_client.fetch_external_url(
schema.raw_schema_url
)
return schema.model_copy(
update={"schema_content": schema_content}
).model_dump()
except Exception as e:
self.logger.error(
f"Failed to get cartography schema for scan {scan_id}: {e}"
)
return {"error": f"Failed to get cartography schema: {str(e)}"}
@@ -4,15 +4,11 @@ import asyncio
from datetime import datetime, timedelta
from enum import Enum
from typing import Any, Dict
from urllib.parse import urlparse
import httpx
from prowler_mcp_server import __version__
from prowler_mcp_server.lib.logger import logger
from prowler_mcp_server.prowler_app.utils.auth import ProwlerAppAuth
ALLOWED_EXTERNAL_DOMAINS: frozenset[str] = frozenset({"raw.githubusercontent.com"})
class HTTPMethod(str, Enum):
"""HTTP methods enum."""
@@ -191,47 +187,6 @@ class ProwlerAPIClient(metaclass=SingletonMeta):
"""
return await self._make_request(HTTPMethod.DELETE, path, params=params)
async def fetch_external_url(self, url: str) -> str:
"""Fetch content from an allowed external URL (unauthenticated).
Uses the existing singleton httpx client with a domain allowlist
to prevent SSRF attacks.
Args:
url: The external URL to fetch content from
Returns:
Raw text content from the URL
Raises:
ValueError: If the URL domain is not in the allowlist
Exception: If the HTTP request fails
"""
parsed = urlparse(url)
if parsed.scheme != "https":
raise ValueError(f"Only HTTPS URLs are allowed, got '{parsed.scheme}'")
if parsed.hostname not in ALLOWED_EXTERNAL_DOMAINS:
raise ValueError(
f"Domain '{parsed.hostname}' is not allowed. "
f"Allowed domains: {', '.join(sorted(ALLOWED_EXTERNAL_DOMAINS))}"
)
try:
response = await self.client.get(
url,
headers={"User-Agent": f"prowler-mcp-server/{__version__}"},
)
response.raise_for_status()
return response.text
except httpx.HTTPStatusError as e:
logger.error(f"HTTP error fetching external URL {url}: {e}")
raise Exception(
f"Failed to fetch external URL: {e.response.status_code}"
) from e
except Exception as e:
logger.error(f"Error fetching external URL {url}: {e}")
raise
async def poll_task_until_complete(
self,
task_id: str,
+1 -1
View File
@@ -11,7 +11,7 @@ description = "MCP server for Prowler ecosystem"
name = "prowler-mcp"
readme = "README.md"
requires-python = ">=3.12"
version = "0.5.0"
version = "0.4.0"
[project.scripts]
prowler-mcp = "prowler_mcp_server.main:main"
+1 -1
View File
@@ -717,7 +717,7 @@ wheels = [
[[package]]
name = "prowler-mcp"
version = "0.5.0"
version = "0.3.0"
source = { editable = "." }
dependencies = [
{ name = "fastmcp" },
Generated
+33 -13
View File
@@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 2.1.2 and should not be changed by hand.
# This file is automatically @generated by Poetry 2.3.0 and should not be changed by hand.
[[package]]
name = "about-time"
@@ -1908,6 +1908,7 @@ files = [
{file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
markers = {dev = "platform_system == \"Windows\" or sys_platform == \"win32\""}
[[package]]
name = "contextlib2"
@@ -2151,6 +2152,24 @@ files = [
{file = "defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69"},
]
[[package]]
name = "deprecated"
version = "1.2.18"
description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
groups = ["main"]
files = [
{file = "Deprecated-1.2.18-py2.py3-none-any.whl", hash = "sha256:bd5011788200372a32418f888e326a09ff80d0214bd961147cfed01b5c018eec"},
{file = "deprecated-1.2.18.tar.gz", hash = "sha256:422b6f6d859da6f2ef57857761bfb392480502a64c3028ca9bbe86085d72115d"},
]
[package.dependencies]
wrapt = ">=1.10,<2"
[package.extras]
dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "setuptools ; python_version >= \"3.12\"", "tox"]
[[package]]
name = "detect-secrets"
version = "1.5.0"
@@ -3137,7 +3156,7 @@ files = [
[package.dependencies]
attrs = ">=22.2.0"
jsonschema-specifications = ">=2023.03.6"
jsonschema-specifications = ">=2023.3.6"
referencing = ">=0.28.4"
rpds-py = ">=0.7.1"
@@ -3246,7 +3265,7 @@ files = [
]
[package.dependencies]
certifi = ">=14.05.14"
certifi = ">=14.5.14"
durationpy = ">=0.7"
google-auth = ">=1.0.1"
oauthlib = ">=3.2.2"
@@ -4856,7 +4875,7 @@ description = "C parser in Python"
optional = false
python-versions = ">=3.8"
groups = ["main", "dev"]
markers = "implementation_name != \"PyPy\" and platform_python_implementation != \"PyPy\""
markers = "platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\""
files = [
{file = "pycparser-2.22-py3-none-any.whl", hash = "sha256:c3702b6d3dd8c7abc1afa565d7e63d53a1d0bd86cdc24edd75470f4de499cfcc"},
{file = "pycparser-2.22.tar.gz", hash = "sha256:491c8be9c040f5390f5bf44a5b07752bd07f56edf992381b05c701439eec10f6"},
@@ -5032,21 +5051,22 @@ files = [
[[package]]
name = "pygithub"
version = "2.8.0"
version = "2.5.0"
description = "Use the full Github API v3"
optional = false
python-versions = ">=3.8"
groups = ["main"]
files = [
{file = "pygithub-2.8.0-py3-none-any.whl", hash = "sha256:11a3473c1c2f1c39c525d0ee8c559f369c6d46c272cb7321c9b0cabc7aa1ce7d"},
{file = "pygithub-2.8.0.tar.gz", hash = "sha256:72f5f2677d86bc3a8843aa720c6ce4c1c42fb7500243b136e3d5e14ddb5c3386"},
{file = "PyGithub-2.5.0-py3-none-any.whl", hash = "sha256:b0b635999a658ab8e08720bdd3318893ff20e2275f6446fcf35bf3f44f2c0fd2"},
{file = "pygithub-2.5.0.tar.gz", hash = "sha256:e1613ac508a9be710920d26eb18b1905ebd9926aa49398e88151c1b526aad3cf"},
]
[package.dependencies]
Deprecated = "*"
pyjwt = {version = ">=2.4.0", extras = ["crypto"]}
pynacl = ">=1.4.0"
requests = ">=2.14.0"
typing-extensions = ">=4.5.0"
typing-extensions = ">=4.0.0"
urllib3 = ">=1.26.0"
[[package]]
@@ -5098,7 +5118,7 @@ files = [
]
[package.dependencies]
astroid = ">=3.3.8,<=3.4.0-dev0"
astroid = ">=3.3.8,<=3.4.0.dev0"
colorama = {version = ">=0.4.5", markers = "sys_platform == \"win32\""}
dill = [
{version = ">=0.2", markers = "python_version < \"3.11\""},
@@ -5945,10 +5965,10 @@ files = [
]
[package.dependencies]
botocore = ">=1.37.4,<2.0a.0"
botocore = ">=1.37.4,<2.0a0"
[package.extras]
crt = ["botocore[crt] (>=1.37.4,<2.0a.0)"]
crt = ["botocore[crt] (>=1.37.4,<2.0a0)"]
[[package]]
name = "safety"
@@ -6500,7 +6520,7 @@ version = "1.17.2"
description = "Module for decorators, wrappers and monkey patching."
optional = false
python-versions = ">=3.8"
groups = ["dev"]
groups = ["main", "dev"]
files = [
{file = "wrapt-1.17.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3d57c572081fed831ad2d26fd430d565b76aa277ed1d30ff4d40670b1c0dd984"},
{file = "wrapt-1.17.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b5e251054542ae57ac7f3fba5d10bfff615b6c2fb09abeb37d2f1463f841ae22"},
@@ -6886,4 +6906,4 @@ files = [
[metadata]
lock-version = "2.1"
python-versions = ">3.9.1,<3.13"
content-hash = "fa67f98ae1b75ec5a54d1d6a1c33c5412d888ec60cf35fc407606dc48329c0bf"
content-hash = "386f6cf2bed49290cc4661aa2093ceb018aa6cdaf6864bdfab36f6c2c50e241e"
+4 -41
View File
@@ -2,53 +2,16 @@
All notable changes to the **Prowler SDK** are documented in this file.
## [5.21.0] (Prowler v5.21.0)
## [5.20.0] (Prowler UNRELEASED)
### 🚀 Added
- `misconfig` scanner as default for Image provider scans [(#10167)](https://github.com/prowler-cloud/prowler/pull/10167)
- `entra_conditional_access_policy_device_code_flow_blocked` check for M365 provider [(#10218)](https://github.com/prowler-cloud/prowler/pull/10218)
- RBI compliance for the Azure provider [(#10339)](https://github.com/prowler-cloud/prowler/pull/10339)
-`entra_conditional_access_policy_require_mfa_for_admin_portals` check for Azure provider and update CIS compliance [(#10330)](https://github.com/prowler-cloud/prowler/pull/10330)
- CheckMetadata Pydantic validators [(#8583)](https://github.com/prowler-cloud/prowler/pull/8583)
- `organization_repository_deletion_limited` check for GitHub provider [(#10185)](https://github.com/prowler-cloud/prowler/pull/10185)
- SecNumCloud 3.2 for the GCP provider [(#10364)](https://github.com/prowler-cloud/prowler/pull/10364)
- SecNumCloud 3.2 for the Azure provider [(#10358)](https://github.com/prowler-cloud/prowler/pull/10358)
- SecNumCloud 3.2 for the Alibaba Cloud provider [(#10370)](https://github.com/prowler-cloud/prowler/pull/10370)
- SecNumCloud 3.2 for the Oracle Cloud provider [(#10371)](https://github.com/prowler-cloud/prowler/pull/10371)
### 🔄 Changed
- Bump `pygithub` from 2.5.0 to 2.8.0 to use native Organization properties
- Update M365 SharePoint service metadata to new format [(#9684)](https://github.com/prowler-cloud/prowler/pull/9684)
- Update M365 Exchange service metadata to new format [(#9683)](https://github.com/prowler-cloud/prowler/pull/9683)
- Update M365 Teams service metadata to new format [(#9685)](https://github.com/prowler-cloud/prowler/pull/9685)
- Update M365 Entra ID service metadata to new format [(#9682)](https://github.com/prowler-cloud/prowler/pull/9682)
- Update ResourceType and Categories for Azure Entra ID service metadata [(#10334)](https://github.com/prowler-cloud/prowler/pull/10334)
- Update OCI Regions to include US DoD regions [(#10375)](https://github.com/prowler-cloud/prowler/pull/10376)
### 🐞 Fixed
- Route53 dangling IP check false positive when using `--region` flag [(#9952)](https://github.com/prowler-cloud/prowler/pull/9952)
- RBI compliance framework support on Prowler Dashboard for the Azure provider [(#10360)](https://github.com/prowler-cloud/prowler/pull/10360)
- CheckMetadata strict validators rejecting valid external tool provider data (image, iac, llm) [(#10363)](https://github.com/prowler-cloud/prowler/pull/10363)
### 🔐 Security
- Bump `multipart` to 1.3.1 to fix [GHSA-p2m9-wcp5-6qw3](https://github.com/defnull/multipart/security/advisories/GHSA-p2m9-wcp5-6qw3) [(#10331)](https://github.com/prowler-cloud/prowler/pull/10331)
---
## [5.20.0] (Prowler v5.20.0)
### 🚀 Added
- `entra_conditional_access_policy_approved_client_app_required_for_mobile` check for M365 provider [(#10216)](https://github.com/prowler-cloud/prowler/pull/10216)
- `entra_conditional_access_policy_approved_client_app_required_for_mobile` check for m365 provider [(#10216)](https://github.com/prowler-cloud/prowler/pull/10216)
- `entra_conditional_access_policy_compliant_device_hybrid_joined_device_mfa_required` check for M365 provider [(#10197)](https://github.com/prowler-cloud/prowler/pull/10197)
- `trusted_ips` configurable option for `opensearch_service_domains_not_publicly_accessible` check to reduce false positives on IP-restricted policies [(#8631)](https://github.com/prowler-cloud/prowler/pull/8631)
- Add `trusted_ips` configurable option to `opensearch_service_domains_not_publicly_accessible` check to reduce false positives on IP-restricted policies [(#8631)](https://github.com/prowler-cloud/prowler/pull/8631)
- `guardduty_delegated_admin_enabled_all_regions` check for AWS provider [(#9867)](https://github.com/prowler-cloud/prowler/pull/9867)
- OpenStack object storage service with 7 checks [(#10258)](https://github.com/prowler-cloud/prowler/pull/10258)
- AWS Organizations OU metadata (OU ID, OU path) in ASFF, OCSF and CSV outputs [(#10283)](https://github.com/prowler-cloud/prowler/pull/10283)
- Add AWS Organizations OU metadata (OU ID, OU path) to ASFF, OCSF and CSV outputs [(#10283)](https://github.com/prowler-cloud/prowler/pull/10283)
### 🔄 Changed
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -752,7 +752,7 @@
"Id": "2.2.8",
"Description": "Ensure Multi-factor Authentication is Required to access Microsoft Admin Portals",
"Checks": [
"entra_conditional_access_policy_require_mfa_for_admin_portals"
"defender_ensure_defender_for_server_is_on"
],
"Attributes": [
{
+1 -1
View File
@@ -1036,7 +1036,7 @@
"Id": "6.2.7",
"Description": "Ensure that multifactor authentication is required to access Microsoft Admin Portals",
"Checks": [
"entra_conditional_access_policy_require_mfa_for_admin_portals"
"defender_ensure_defender_for_server_is_on"
],
"Attributes": [
{
+1 -1
View File
@@ -472,7 +472,7 @@
"Id": "5.2.7",
"Description": "Ensure that multifactor authentication is required to access Microsoft Admin Portals",
"Checks": [
"entra_conditional_access_policy_require_mfa_for_admin_portals"
"defender_ensure_defender_for_server_is_on"
],
"Attributes": [
{
@@ -63,7 +63,7 @@
"Id": "1.1.4",
"Description": "Ensure Multi-factor Authentication is Required to access Microsoft Admin Portals",
"Checks": [
"entra_conditional_access_policy_require_mfa_for_admin_portals"
"defender_ensure_defender_for_server_is_on"
],
"Attributes": [
{
File diff suppressed because it is too large Load Diff
@@ -1,178 +0,0 @@
{
"Framework": "RBI-Cyber-Security-Framework",
"Name": "Reserve Bank of India (RBI) Cyber Security Framework",
"Version": "",
"Provider": "GCP",
"Description": "The Reserve Bank had prescribed a set of baseline cyber security controls for primary (Urban) cooperative banks (UCBs) in October 2018. On further examination, it has been decided to prescribe a comprehensive cyber security framework for the UCBs, as a graded approach, based on their digital depth and interconnectedness with the payment systems landscape, digital products offered by them and assessment of cyber security risk. The framework would mandate implementation of progressively stronger security measures based on the nature, variety and scale of digital product offerings of banks.",
"Requirements": [
{
"Id": "annex_i_1_1",
"Name": "Annex I (1.1)",
"Description": "UCBs should maintain an up-to-date business IT Asset Inventory Register containing the following fields, as a minimum: a) Details of the IT Asset (viz., hardware/software/network devices, key personnel, services, etc.), b. Details of systems where customer data are stored, c. Associated business applications, if any, d. Criticality of the IT asset (For example, High/Medium/Low).",
"Attributes": [
{
"ItemId": "annex_i_1_1",
"Service": "gcp"
}
],
"Checks": [
"iam_cloud_asset_inventory_enabled",
"iam_organization_essential_contacts_configured"
]
},
{
"Id": "annex_i_1_3",
"Name": "Annex I (1.3)",
"Description": "Appropriately manage and provide protection within and outside UCB/network, keeping in mind how the data/information is stored, transmitted, processed, accessed and put to use within/outside the UCB's network, and level of risk they are exposed to depending on the sensitivity of the data/information.",
"Attributes": [
{
"ItemId": "annex_i_1_3",
"Service": "gcp"
}
],
"Checks": [
"cloudstorage_bucket_public_access",
"cloudstorage_bucket_uniform_bucket_level_access",
"cloudstorage_bucket_logging_enabled",
"cloudstorage_bucket_versioning_enabled",
"cloudsql_instance_public_access",
"cloudsql_instance_public_ip",
"cloudsql_instance_ssl_connections",
"compute_instance_public_ip",
"compute_instance_encryption_with_csek_enabled",
"compute_image_not_publicly_shared",
"kms_key_rotation_enabled",
"kms_key_not_publicly_accessible",
"bigquery_dataset_public_access",
"bigquery_dataset_cmk_encryption"
]
},
{
"Id": "annex_i_5_1",
"Name": "Annex I (5.1)",
"Description": "The firewall configurations should be set to the highest security level and evaluation of critical device (such as firewall, network switches, security devices, etc.) configurations should be done periodically.",
"Attributes": [
{
"ItemId": "annex_i_5_1",
"Service": "compute"
}
],
"Checks": [
"compute_firewall_rdp_access_from_the_internet_allowed",
"compute_firewall_ssh_access_from_the_internet_allowed",
"compute_network_not_legacy",
"compute_network_default_in_use",
"compute_subnet_flow_logs_enabled",
"compute_network_dns_logging_enabled",
"dns_dnssec_disabled"
]
},
{
"Id": "annex_i_6",
"Name": "Annex I (6)",
"Description": "Put in place systems and processes to identify, track, manage and monitor the status of patches to servers, operating system and application software running at the systems used by the UCB officials (end-users). Implement and update antivirus protection for all servers and applicable end points preferably through a centralised system.",
"Attributes": [
{
"ItemId": "annex_i_6",
"Service": "gcp"
}
],
"Checks": [
"compute_instance_shielded_vm_enabled",
"compute_project_os_login_enabled",
"artifacts_container_analysis_enabled",
"gcr_container_scanning_enabled"
]
},
{
"Id": "annex_i_7_1",
"Name": "Annex I (7.1)",
"Description": "Disallow administrative rights on end-user workstations/PCs/laptops and provide access rights on a 'need to know' and 'need to do' basis.",
"Attributes": [
{
"ItemId": "annex_i_7_1",
"Service": "iam"
}
],
"Checks": [
"iam_sa_no_administrative_privileges",
"iam_no_service_roles_at_project_level",
"iam_role_sa_enforce_separation_of_duties",
"iam_role_kms_enforce_separation_of_duties",
"iam_sa_no_user_managed_keys",
"compute_instance_default_service_account_in_use",
"compute_instance_default_service_account_in_use_with_full_api_access"
]
},
{
"Id": "annex_i_7_2",
"Name": "Annex I (7.2)",
"Description": "Passwords should be set as complex and lengthy and users should not use same passwords for all the applications/systems/devices.",
"Attributes": [
{
"ItemId": "annex_i_7_2",
"Service": "iam"
}
],
"Checks": [
"compute_project_os_login_2fa_enabled",
"iam_account_access_approval_enabled"
]
},
{
"Id": "annex_i_7_3",
"Name": "Annex I (7.3)",
"Description": "Remote Desktop Protocol (RDP) which allows others to access the computer remotely over a network or over the internet should be always disabled and should be enabled only with the approval of the authorised officer of the UCB. Logs for such remote access shall be enabled and monitored for suspicious activities.",
"Attributes": [
{
"ItemId": "annex_i_7_3",
"Service": "compute"
}
],
"Checks": [
"compute_firewall_rdp_access_from_the_internet_allowed",
"compute_firewall_ssh_access_from_the_internet_allowed",
"compute_project_os_login_enabled"
]
},
{
"Id": "annex_i_7_4",
"Name": "Annex I (7.4)",
"Description": "Implement appropriate (e.g. centralised) systems and controls to allow, manage, log and monitor privileged/super user/administrative access to critical systems (servers/databases, applications, network devices etc.)",
"Attributes": [
{
"ItemId": "annex_i_7_4",
"Service": "logging"
}
],
"Checks": [
"iam_audit_logs_enabled",
"logging_sink_created",
"cloudstorage_audit_logs_enabled",
"compute_loadbalancer_logging_enabled",
"compute_subnet_flow_logs_enabled",
"logging_log_metric_filter_and_alert_for_project_ownership_changes_enabled",
"logging_log_metric_filter_and_alert_for_custom_role_changes_enabled",
"logging_log_metric_filter_and_alert_for_audit_configuration_changes_enabled"
]
},
{
"Id": "annex_i_12",
"Name": "Annex I (12)",
"Description": "Take periodic back up of the important data and store this data 'off line' (i.e., transferring important files to a storage device that can be detached from a computer/system after copying all the files).",
"Attributes": [
{
"ItemId": "annex_i_12",
"Service": "gcp"
}
],
"Checks": [
"cloudsql_instance_automated_backups",
"cloudstorage_bucket_versioning_enabled",
"cloudstorage_bucket_soft_delete_enabled",
"cloudstorage_bucket_lifecycle_management_enabled",
"compute_snapshot_not_outdated"
]
}
]
}
File diff suppressed because it is too large Load Diff
@@ -499,9 +499,7 @@
{
"Id": "1.2.3",
"Description": "Ensure only a limited number of trusted users can delete repositories.",
"Checks": [
"organization_repository_deletion_limited"
],
"Checks": [],
"Attributes": [
{
"Section": "1 Source Code",
+1 -3
View File
@@ -1606,9 +1606,7 @@
{
"Id": "5.2.2.12",
"Description": "The Microsoft identity platform supports the device authorization grant, which allows users to sign in to input-constrained devices such as a smart TV, IoT device, or a printer. Ensure the device code sign-in flow is blocked.",
"Checks": [
"entra_conditional_access_policy_device_code_flow_blocked"
],
"Checks": [],
"Attributes": [
{
"Section": "5 Microsoft Entra admin center",
@@ -243,7 +243,6 @@
"entra_break_glass_account_fido2_security_key_registered",
"entra_default_app_management_policy_enabled",
"entra_all_apps_conditional_access_coverage",
"entra_conditional_access_policy_device_code_flow_blocked",
"entra_legacy_authentication_blocked",
"entra_managed_device_required_for_authentication",
"entra_seamless_sso_disabled",
@@ -465,7 +464,6 @@
"defender_malware_policy_common_attachments_filter_enabled",
"defender_malware_policy_comprehensive_attachments_filter_applied",
"defender_malware_policy_notifications_internal_users_malware_enabled",
"entra_conditional_access_policy_device_code_flow_blocked",
"entra_identity_protection_sign_in_risk_enabled",
"entra_identity_protection_user_risk_enabled",
"entra_legacy_authentication_blocked",
@@ -696,9 +694,8 @@
"entra_admin_users_mfa_enabled",
"entra_admin_users_sign_in_frequency_enabled",
"entra_all_apps_conditional_access_coverage",
"entra_break_glass_account_fido2_security_key_registered",
"entra_conditional_access_policy_approved_client_app_required_for_mobile",
"entra_conditional_access_policy_device_code_flow_blocked",
"entra_break_glass_account_fido2_security_key_registered",
"entra_identity_protection_sign_in_risk_enabled",
"entra_managed_device_required_for_authentication",
"entra_seamless_sso_disabled",
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -38,7 +38,7 @@ class _MutableTimestamp:
timestamp = _MutableTimestamp(datetime.today())
timestamp_utc = _MutableTimestamp(datetime.now(timezone.utc))
prowler_version = "5.21.1"
prowler_version = "5.20.0"
html_logo_url = "https://github.com/prowler-cloud/prowler/"
square_logo_img = "https://raw.githubusercontent.com/prowler-cloud/prowler/dc7d2d5aeb92fdf12e8604f42ef6472cd3e8e889/docs/img/prowler-logo-black.png"
aws_logo = "https://user-images.githubusercontent.com/38561120/235953920-3e3fba08-0795-41dc-b480-9bea57db9f2e.png"
+3 -212
View File
@@ -1,5 +1,4 @@
import functools
import json
import os
import re
import sys
@@ -16,115 +15,6 @@ from prowler.lib.check.compliance_models import Compliance
from prowler.lib.check.utils import recover_checks_from_provider
from prowler.lib.logger import logger
# Valid ResourceGroup values as defined in the RFC
VALID_RESOURCE_GROUPS = frozenset(
{
"compute",
"container",
"serverless",
"database",
"storage",
"network",
"IAM",
"messaging",
"security",
"monitoring",
"api_gateway",
"ai_ml",
"governance",
"collaboration",
"devops",
"analytics",
}
)
# Valid Categories as defined in the RFC
VALID_CATEGORIES = frozenset(
{
"encryption",
"internet-exposed",
"logging",
"secrets",
"resilience",
"threat-detection",
"trust-boundaries",
"vulnerabilities",
"cluster-security",
"container-security",
"node-security",
"gen-ai",
"ci-cd",
"identity-access",
"email-security",
"forensics-ready",
"software-supply-chain",
"e3",
"e5",
"privilege-escalation",
"ec2-imdsv1",
}
)
@functools.lru_cache(maxsize=1)
def _load_aws_check_types_hierarchy() -> dict:
"""
Load and cache the AWS CheckTypes hierarchy from the JSON config file.
Returns:
dict: The CheckTypes hierarchy, or empty dict if file not found.
"""
try:
current_dir = os.path.dirname(os.path.abspath(__file__))
check_types_file = os.path.normpath(
os.path.join(
current_dir,
"..",
"..",
"providers",
"aws",
"config",
"check_types.json",
)
)
if not os.path.exists(check_types_file):
return {}
with open(check_types_file, "r") as f:
return json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
return {}
def _validate_aws_check_type_in_config(check_type: str) -> bool:
"""
Validate if a CheckType exists in the AWS config using direct lookups.
Supports partial paths: namespace, namespace/category, namespace/category/classifier
Args:
check_type: The CheckType string to validate (e.g., "TTPs/Initial Access")
Returns:
bool: True if the CheckType path exists in the config hierarchy
"""
if not check_type:
return False
hierarchy = _load_aws_check_types_hierarchy()
if not hierarchy:
return False
path_parts = check_type.split("/")
current_level = hierarchy
for part in path_parts:
if not isinstance(current_level, dict) or part not in current_level:
return False
current_level = current_level[part]
return True
class Code(BaseModel):
"""
@@ -204,19 +94,11 @@ class CheckMetadata(BaseModel):
Compliance (list, optional): The compliance information for the check. Defaults to None.
Validators:
valid_category(value): Validator function to validate the categories of the check against predefined values.
valid_category(value): Validator function to validate the categories of the check.
severity_to_lower(severity): Validator function to convert the severity to lowercase.
valid_severity(severity): Validator function to validate the severity of the check.
valid_cli_command(remediation): Validator function to validate the CLI command is not an URL.
valid_resource_type(resource_type): Validator function to validate the resource type is not empty.
validate_service_name(service_name, values): Validator function to validate the service name matches CheckID.
valid_check_id(check_id): Validator function to validate the CheckID format.
validate_check_title(check_title): Validator function to validate CheckTitle max length (150 chars) and not starting with 'Ensure'.
validate_related_url(related_url): Validator function to validate RelatedUrl is empty (deprecated field).
validate_recommendation_url(remediation): Validator function to validate Recommendation URL points to Prowler Hub.
validate_check_type(check_type, values): Validator function to validate CheckType - must be empty for non-AWS providers, no empty strings and predefined types validation for AWS.
validate_description(description): Validator function to validate Description max length (400 chars).
validate_risk(risk): Validator function to validate Risk max length (400 chars).
validate_resource_group(resource_group): Validator function to validate ResourceGroup against predefined values.
validate_additional_urls(additional_urls): Validator function to ensure AdditionalURLs contains no duplicates.
"""
@@ -245,7 +127,7 @@ class CheckMetadata(BaseModel):
Compliance: Optional[list[Any]] = Field(default_factory=list)
@validator("Categories", each_item=True, pre=True, always=True)
def valid_category(cls, value, values):
def valid_category(value):
if not isinstance(value, str):
raise ValueError("Categories must be a list of strings")
value_lower = value.lower()
@@ -253,13 +135,6 @@ class CheckMetadata(BaseModel):
raise ValueError(
f"Invalid category: {value}. Categories can only contain lowercase letters, numbers and hyphen '-'"
)
if (
value_lower not in VALID_CATEGORIES
and values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS
):
raise ValueError(
f"Invalid category: '{value_lower}'. Must be one of: {', '.join(sorted(VALID_CATEGORIES))}."
)
return value_lower
@validator("Severity", pre=True, always=True)
@@ -308,90 +183,6 @@ class CheckMetadata(BaseModel):
return check_id
@validator("CheckTitle", pre=True, always=True)
def validate_check_title(cls, check_title, values):
if values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS:
if len(check_title) > 150:
raise ValueError(
f"CheckTitle must not exceed 150 characters, got {len(check_title)} characters"
)
if check_title.startswith("Ensure"):
raise ValueError(
"CheckTitle must not start with 'Ensure'. Use a descriptive title that focuses on the security state."
)
return check_title
@validator("RelatedUrl", pre=True, always=True)
def validate_related_url(cls, related_url, values):
if related_url and values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS:
raise ValueError("RelatedUrl must be empty. This field is deprecated.")
return related_url
@validator("Remediation")
def validate_recommendation_url(cls, remediation, values):
if values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS:
url = remediation.Recommendation.Url
if url and not url.startswith("https://hub.prowler.com/"):
raise ValueError(
f"Remediation Recommendation URL must point to Prowler Hub (https://hub.prowler.com/...), got '{url}'."
)
return remediation
@validator("CheckType", pre=True, always=True)
def validate_check_type(cls, check_type, values):
provider = values.get("Provider", "").lower()
# Non-AWS providers must have an empty CheckType list
if provider != "aws" and provider not in EXTERNAL_TOOL_PROVIDERS:
if check_type:
raise ValueError(
f"CheckType must be empty for non-AWS providers. Got {check_type} for provider '{provider}'."
)
return check_type
# Check for empty strings in the list - applies to AWS
for i, check_type_item in enumerate(check_type):
if not check_type_item or check_type_item.strip() == "":
raise ValueError(
f"CheckType list cannot contain empty strings. Found empty string at index {i}."
)
# For AWS provider, validate against config hierarchy
if provider == "aws":
for check_type_item in check_type:
if not _validate_aws_check_type_in_config(check_type_item):
raise ValueError(
f"Invalid CheckType: '{check_type_item}'. Must be a valid path in the AWS CheckType hierarchy. See prowler/providers/aws/config/check_types.json for valid values."
)
return check_type
@validator("Description", pre=True, always=True)
def validate_description(cls, description, values):
if values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS:
if len(description) > 400:
raise ValueError(
f"Description must not exceed 400 characters, got {len(description)} characters"
)
return description
@validator("Risk", pre=True, always=True)
def validate_risk(cls, risk, values):
if values.get("Provider") not in EXTERNAL_TOOL_PROVIDERS:
if len(risk) > 400:
raise ValueError(
f"Risk must not exceed 400 characters, got {len(risk)} characters"
)
return risk
@validator("ResourceGroup", pre=True, always=True)
def validate_resource_group(cls, resource_group):
if resource_group and resource_group not in VALID_RESOURCE_GROUPS:
raise ValueError(
f"Invalid ResourceGroup: '{resource_group}'. Must be one of: {', '.join(sorted(VALID_RESOURCE_GROUPS))} or empty string."
)
return resource_group
@validator("AdditionalURLs", pre=True, always=True)
def validate_additional_urls(cls, additional_urls):
if not isinstance(additional_urls, list):

Some files were not shown because too many files have changed in this diff Show More