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
461 changed files with 4093 additions and 26341 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 }}'
+7 -13
View File
@@ -57,7 +57,7 @@ jobs:
message-ts: ${{ steps.slack-notification.outputs.ts }}
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
@@ -95,18 +95,12 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
with:
persist-credentials: false
- name: Pin prowler SDK to latest master commit
if: github.event_name == 'push'
run: |
LATEST_SHA=$(git ls-remote https://github.com/prowler-cloud/prowler.git refs/heads/master | cut -f1)
sed -i "s|prowler-cloud/prowler.git@master|prowler-cloud/prowler.git@${LATEST_SHA}|" api/pyproject.toml
- 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 }}
@@ -117,7 +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
@@ -135,7 +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 }}
@@ -167,7 +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()
@@ -186,7 +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 -53
View File
@@ -2,67 +2,20 @@
All notable changes to the **Prowler API** are documented in this file.
## [1.23.0] (Prowler v5.22.0)
### 🚀 Added
- Finding groups support `check_title` substring filtering [(#10377)](https://github.com/prowler-cloud/prowler/pull/10377)
### 🐞 Fixed
- Finding groups latest endpoint now aggregates the latest snapshot per provider before check-level totals, keeping impacted resources aligned across providers [(#10419)](https://github.com/prowler-cloud/prowler/pull/10419)
- Mute rule creation now triggers finding-group summary re-aggregation after historical muting, keeping stats in sync after mute operations [(#10419)](https://github.com/prowler-cloud/prowler/pull/10419)
- Attack Paths: Deduplicate nodes before ProwlerFinding lookup in Attack Paths Cypher queries, reducing execution time [(#10424)](https://github.com/prowler-cloud/prowler/pull/10424)
### 🔐 Security
- Replace stdlib XML parser with `defusedxml` in SAML metadata parsing to prevent XML bomb (billion laughs) DoS attacks [(#10165)](https://github.com/prowler-cloud/prowler/pull/10165)
- Bump `flask` to 3.1.3 (CVE-2026-27205) and `werkzeug` to 3.1.6 (CVE-2026-27199) [(#10430)](https://github.com/prowler-cloud/prowler/pull/10430)
---
## [1.22.1] (Prowler v5.21.1)
### 🐞 Fixed
- Threat score 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)
- Replace stdlib XML parser with `defusedxml` in SAML metadata parsing to prevent XML bomb (billion laughs) DoS attacks [(#10165)](https://github.com/prowler-cloud/prowler/pull/10165)
---
## [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)
---
+38 -388
View File
File diff suppressed because it is too large Load Diff
+2 -3
View File
@@ -22,10 +22,9 @@ dependencies = [
"drf-nested-routers (>=0.94.1,<1.0.0)",
"drf-spectacular==0.27.2",
"drf-spectacular-jsonapi==0.5.1",
"defusedxml==0.7.1",
"gunicorn==23.0.0",
"lxml==5.3.2",
"prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.22",
"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)",
@@ -50,7 +49,7 @@ name = "prowler-api"
package-mode = false
# Needed for the SDK compatibility
requires-python = ">=3.11,<3.13"
version = "1.23.0"
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
File diff suppressed because it is too large Load Diff
@@ -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):
-6
View File
@@ -926,9 +926,6 @@ class FindingGroupSummaryFilter(FilterSet):
check_id = CharFilter(field_name="check_id", lookup_expr="exact")
check_id__in = CharInFilter(field_name="check_id", lookup_expr="in")
check_id__icontains = CharFilter(field_name="check_id", lookup_expr="icontains")
check_title__icontains = CharFilter(
field_name="check_title", lookup_expr="icontains"
)
# Provider filters
provider_id = UUIDFilter(field_name="provider_id", lookup_expr="exact")
@@ -1028,9 +1025,6 @@ class LatestFindingGroupSummaryFilter(FilterSet):
check_id = CharFilter(field_name="check_id", lookup_expr="exact")
check_id__in = CharInFilter(field_name="check_id", lookup_expr="in")
check_id__icontains = CharFilter(field_name="check_id", lookup_expr="icontains")
check_title__icontains = CharFilter(
field_name="check_title", lookup_expr="icontains"
)
# Provider filters
provider_id = UUIDFilter(field_name="provider_id", lookup_expr="exact")
@@ -1,31 +0,0 @@
# Generated by Django 5.1.15 on 2026-03-18
from django.contrib.postgres.indexes import GinIndex, OpClass
from django.contrib.postgres.operations import AddIndexConcurrently
from django.db import migrations
from django.db.models.functions import Upper
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0084_googleworkspace_provider"),
]
operations = [
AddIndexConcurrently(
model_name="findinggroupdailysummary",
index=GinIndex(
OpClass(Upper("check_id"), name="gin_trgm_ops"),
name="fgds_check_id_trgm_idx",
),
),
AddIndexConcurrently(
model_name="findinggroupdailysummary",
index=GinIndex(
OpClass(Upper("check_title"), name="gin_trgm_ops"),
name="fgds_check_title_trgm_idx",
),
),
]
+1 -13
View File
@@ -1,6 +1,7 @@
import json
import logging
import re
import xml.etree.ElementTree as ET
from datetime import datetime, timedelta, timezone
from uuid import UUID, uuid4
@@ -8,8 +9,6 @@ from allauth.socialaccount.models import SocialApp
from config.custom_logging import BackendLogger
from config.settings.social_login import SOCIALACCOUNT_PROVIDERS
from cryptography.fernet import Fernet, InvalidToken
import defusedxml
from defusedxml import ElementTree as ET
from django.conf import settings
from django.contrib.auth.models import AbstractBaseUser
from django.contrib.postgres.fields import ArrayField
@@ -1784,15 +1783,6 @@ class FindingGroupDailySummary(RowLevelSecurityProtectedModel):
fields=["tenant_id", "provider", "inserted_at"],
name="fgds_tenant_prov_ins_idx",
),
# Trigram indexes for case-insensitive search
GinIndex(
OpClass(Upper("check_id"), name="gin_trgm_ops"),
name="fgds_check_id_trgm_idx",
),
GinIndex(
OpClass(Upper("check_title"), name="gin_trgm_ops"),
name="fgds_check_title_trgm_idx",
),
]
class JSONAPIMeta:
@@ -2068,8 +2058,6 @@ class SAMLConfiguration(RowLevelSecurityProtectedModel):
root = ET.fromstring(self.metadata_xml)
except ET.ParseError as e:
raise ValidationError({"metadata_xml": f"Invalid XML: {e}"})
except defusedxml.DefusedXmlException as e:
raise ValidationError({"metadata_xml": f"Unsafe XML content rejected: {e}"})
# Entity ID
entity_id = root.attrib.get("entityID")
+1 -1
View File
@@ -1,7 +1,7 @@
openapi: 3.0.3
info:
title: Prowler API
version: 1.23.0
version: 1.21.0
description: |-
Prowler API specification.
@@ -301,7 +301,7 @@ class TestTokenSwitchTenant:
assert invalid_tenant_response.status_code == 400
assert invalid_tenant_response.json()["errors"][0]["code"] == "invalid"
assert invalid_tenant_response.json()["errors"][0]["detail"] == (
"Tenant does not exist or user is not a member."
"Tenant does not exist or user is not a " "member."
)
@@ -912,9 +912,10 @@ class TestAPIKeyLifecycle:
auth_response = client.get(reverse("provider-list"), headers=api_key_headers)
# Must return 401 Unauthorized, not 500 Internal Server Error
assert (
auth_response.status_code == 401
), f"Expected 401 but got {auth_response.status_code}: {auth_response.json()}"
assert auth_response.status_code == 401, (
f"Expected 401 but got {auth_response.status_code}: "
f"{auth_response.json()}"
)
# Verify error message is present
response_json = auth_response.json()
+13 -17
View File
@@ -10,11 +10,11 @@ from django.conf import settings
import api
import api.apps as api_apps_module
from api.apps import (
ApiConfig,
PRIVATE_KEY_FILE,
PUBLIC_KEY_FILE,
SIGNING_KEY_ENV,
VERIFYING_KEY_ENV,
ApiConfig,
)
@@ -187,10 +187,9 @@ def test_ready_initializes_driver_for_api_process(monkeypatch):
_set_argv(monkeypatch, ["gunicorn"])
_set_testing(monkeypatch, False)
with (
patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None),
patch("api.attack_paths.database.init_driver") as init_driver,
):
with patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None), patch(
"api.attack_paths.database.init_driver"
) as init_driver:
config.ready()
init_driver.assert_called_once()
@@ -201,10 +200,9 @@ def test_ready_skips_driver_for_celery(monkeypatch):
_set_argv(monkeypatch, ["celery", "-A", "api"])
_set_testing(monkeypatch, False)
with (
patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None),
patch("api.attack_paths.database.init_driver") as init_driver,
):
with patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None), patch(
"api.attack_paths.database.init_driver"
) as init_driver:
config.ready()
init_driver.assert_not_called()
@@ -215,10 +213,9 @@ def test_ready_skips_driver_for_manage_py_skip_command(monkeypatch):
_set_argv(monkeypatch, ["manage.py", "migrate"])
_set_testing(monkeypatch, False)
with (
patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None),
patch("api.attack_paths.database.init_driver") as init_driver,
):
with patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None), patch(
"api.attack_paths.database.init_driver"
) as init_driver:
config.ready()
init_driver.assert_not_called()
@@ -229,10 +226,9 @@ def test_ready_skips_driver_when_testing(monkeypatch):
_set_argv(monkeypatch, ["gunicorn"])
_set_testing(monkeypatch, True)
with (
patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None),
patch("api.attack_paths.database.init_driver") as init_driver,
):
with patch.object(ApiConfig, "_ensure_crypto_keys", return_value=None), patch(
"api.attack_paths.database.init_driver"
) as init_driver:
config.ready()
init_driver.assert_not_called()
+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",)
-33
View File
@@ -243,39 +243,6 @@ class TestSAMLConfigurationModel:
assert "Invalid XML" in errors["metadata_xml"][0]
assert "not well-formed" in errors["metadata_xml"][0]
def test_xml_bomb_rejected(self, tenants_fixture):
"""
Regression test: a 'billion laughs' XML bomb in the SAML metadata field
must be rejected and not allowed to exhaust server memory / CPU.
Before the fix, xml.etree.ElementTree was used directly, which does not
protect against entity-expansion attacks. The fix switches to defusedxml
which raises an exception for any XML containing entity definitions.
"""
tenant = tenants_fixture[0]
xml_bomb = (
"<?xml version='1.0'?>"
"<!DOCTYPE bomb ["
" <!ENTITY a 'aaaaaaaaaa'>"
" <!ENTITY b '&a;&a;&a;&a;&a;&a;&a;&a;&a;&a;'>"
" <!ENTITY c '&b;&b;&b;&b;&b;&b;&b;&b;&b;&b;'>"
" <!ENTITY d '&c;&c;&c;&c;&c;&c;&c;&c;&c;&c;'>"
"]>"
"<md:EntityDescriptor entityID='&d;' "
"xmlns:md='urn:oasis:names:tc:SAML:2.0:metadata'/>"
)
config = SAMLConfiguration(
email_domain="xmlbomb.com",
metadata_xml=xml_bomb,
tenant=tenant,
)
with pytest.raises(ValidationError) as exc_info:
config._parse_metadata()
errors = exc_info.value.message_dict
assert "metadata_xml" in errors
def test_metadata_missing_sso_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
xml = """<md:EntityDescriptor entityID="x" xmlns:md="urn:oasis:names:tc:SAML:2.0:metadata">
+15 -422
View File
@@ -45,7 +45,6 @@ from api.models import (
ComplianceRequirementOverview,
DailySeveritySummary,
Finding,
FindingGroupDailySummary,
Integration,
Invitation,
LighthouseProviderConfiguration,
@@ -3811,12 +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 {
@@ -4418,6 +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,
@@ -4475,6 +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,
@@ -4529,6 +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,
@@ -4570,6 +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,
@@ -4596,6 +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,
@@ -4633,343 +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,
@@ -5019,6 +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,
@@ -5053,6 +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,
@@ -7859,12 +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
@@ -14690,16 +14353,10 @@ class TestMuteRuleViewSet:
assert len(data) == 2
assert data[0]["id"] == str(mute_rules_fixture[first_index].id)
@patch("api.v1.views.chain")
@patch("api.v1.views.aggregate_finding_group_summaries_task.si")
@patch("api.v1.views.mute_historical_findings_task.si")
@patch("api.v1.views.transaction.on_commit", side_effect=lambda fn: fn())
@patch("tasks.tasks.mute_historical_findings_task.apply_async")
def test_mute_rules_create_valid(
self,
_mock_on_commit,
mock_mute_signature,
mock_aggregate_signature,
mock_chain,
mock_task,
authenticated_client,
findings_fixture,
create_test_user,
@@ -14737,14 +14394,8 @@ class TestMuteRuleViewSet:
assert finding.muted_at is not None
assert finding.muted_reason == "Security exception approved"
# Verify background task chain was called
mock_mute_signature.assert_called_once()
mock_aggregate_signature.assert_called_once()
mock_chain.assert_called_once_with(
mock_mute_signature.return_value,
mock_aggregate_signature.return_value,
)
mock_chain.return_value.apply_async.assert_called_once()
# Verify background task was called
mock_task.assert_called_once()
@patch("tasks.tasks.mute_historical_findings_task.apply_async")
def test_mute_rules_create_converts_finding_ids_to_uids(
@@ -15539,22 +15190,6 @@ class TestFindingGroupViewSet:
assert len(response.json()["data"]) == 1
assert "bucket" in response.json()["data"][0]["id"].lower()
def test_finding_groups_check_title_icontains(
self, authenticated_client, finding_groups_fixture
):
"""Test searching check titles with icontains."""
response = authenticated_client.get(
reverse("finding-group-list"),
{
"filter[inserted_at]": TODAY,
"filter[check_title.icontains]": "public access",
},
)
assert response.status_code == status.HTTP_200_OK
data = response.json()["data"]
assert len(data) == 1
assert data[0]["id"] == "s3_bucket_public_access"
def test_resources_not_found(self, authenticated_client):
"""Test 404 returned for nonexistent check_id."""
response = authenticated_client.get(
@@ -15853,48 +15488,6 @@ class TestFindingGroupViewSet:
assert len(data) == 1
assert data[0]["id"] == "cloudtrail_enabled"
def test_finding_groups_latest_aggregates_latest_per_provider(
self, authenticated_client, providers_fixture
):
"""Test /latest aggregates latest summary from each provider for the same check."""
provider1 = providers_fixture[0]
provider2 = providers_fixture[1]
check_id = "cross_provider_latest_resources_total"
now = datetime.now(timezone.utc).replace(minute=0, second=0, microsecond=0)
FindingGroupDailySummary.objects.create(
tenant_id=provider1.tenant_id,
provider=provider1,
check_id=check_id,
inserted_at=now - timedelta(days=1),
resources_total=20,
resources_fail=20,
fail_count=20,
)
FindingGroupDailySummary.objects.create(
tenant_id=provider2.tenant_id,
provider=provider2,
check_id=check_id,
inserted_at=now,
resources_total=7,
resources_fail=7,
fail_count=7,
)
response = authenticated_client.get(
reverse("finding-group-latest"),
{"filter[check_id]": check_id},
)
assert response.status_code == status.HTTP_200_OK
data = response.json()["data"]
assert len(data) == 1
attrs = data[0]["attributes"]
assert attrs["resources_total"] == 27
assert attrs["resources_fail"] == 27
assert attrs["fail_count"] == 27
def test_finding_groups_latest_provider_type_filter(
self, authenticated_client, finding_groups_fixture
):
+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)),
+16 -57
View File
@@ -4,6 +4,7 @@ import json
import logging
import os
import time
from collections import defaultdict
from copy import deepcopy
from datetime import datetime, timedelta, timezone
@@ -11,12 +12,12 @@ from decimal import ROUND_HALF_UP, Decimal, InvalidOperation
from urllib.parse import urljoin
import sentry_sdk
from allauth.socialaccount.models import SocialAccount, SocialApp
from allauth.socialaccount.providers.github.views import GitHubOAuth2Adapter
from allauth.socialaccount.providers.google.views import GoogleOAuth2Adapter
from allauth.socialaccount.providers.saml.views import FinishACSView, LoginView
from botocore.exceptions import ClientError, NoCredentialsError, ParamValidationError
from celery import chain
from celery.result import AsyncResult
from config.custom_logging import BackendLogger
from config.env import env
@@ -75,14 +76,12 @@ from rest_framework.exceptions import (
)
from rest_framework.generics import GenericAPIView, get_object_or_404
from rest_framework.permissions import SAFE_METHODS
from rest_framework_json_api import filters as jsonapi_filters
from rest_framework_json_api.views import RelationshipView, Response
from rest_framework_simplejwt.exceptions import InvalidToken, TokenError
from tasks.beat import schedule_provider_scan
from tasks.jobs.attack_paths import db_utils as attack_paths_db_utils
from tasks.jobs.export import get_s3_client
from tasks.tasks import (
aggregate_finding_group_summaries_task,
backfill_compliance_summaries_task,
backfill_scan_resource_summaries_task,
check_integration_connection_task,
@@ -101,6 +100,7 @@ from api.attack_paths import database as graph_database
from api.attack_paths import get_queries_for_provider, get_query_by_id
from api.attack_paths import views_helpers as attack_paths_views_helpers
from api.base_views import BaseRLSViewSet, BaseTenantViewset, BaseUserViewset
from api.renderers import APIJSONRenderer, PlainTextRenderer
from api.compliance import (
PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
get_compliance_frameworks,
@@ -199,7 +199,6 @@ from api.models import (
)
from api.pagination import ComplianceOverviewPagination
from api.rbac.permissions import Permissions, get_providers, get_role
from api.renderers import APIJSONRenderer, PlainTextRenderer
from api.rls import Tenant
from api.utils import (
CustomOAuth2Client,
@@ -409,7 +408,7 @@ class SchemaView(SpectacularAPIView):
def get(self, request, *args, **kwargs):
spectacular_settings.TITLE = "Prowler API"
spectacular_settings.VERSION = "1.23.0"
spectacular_settings.VERSION = "1.21.0"
spectacular_settings.DESCRIPTION = (
"Prowler API specification.\n\nThis file is auto-generated."
)
@@ -2453,11 +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 = []
@@ -6727,25 +6721,10 @@ class MuteRuleViewSet(BaseRLSViewSet):
)
# Launch background task for historical muting
latest_scan_id = (
Scan.objects.filter(tenant_id=tenant_id, state=StateChoices.COMPLETED)
.order_by("-completed_at", "-inserted_at")
.values_list("id", flat=True)
.first()
)
transaction.on_commit(
lambda: chain(
mute_historical_findings_task.si(
tenant_id=tenant_id,
mute_rule_id=str(mute_rule.id),
),
aggregate_finding_group_summaries_task.si(
tenant_id=tenant_id,
scan_id=str(latest_scan_id),
),
).apply_async()
)
with transaction.atomic():
mute_historical_findings_task.apply_async(
kwargs={"tenant_id": tenant_id, "mute_rule_id": str(mute_rule.id)}
)
# Return the created mute rule
serializer = self.get_serializer(mute_rule)
@@ -6793,29 +6772,13 @@ class FindingGroupViewSet(BaseRLSViewSet):
queryset = FindingGroupDailySummary.objects.all()
serializer_class = FindingGroupSerializer
filterset_class = FindingGroupSummaryFilter
filter_backends = [
jsonapi_filters.QueryParameterValidationFilter,
jsonapi_filters.OrderingFilter,
CustomDjangoFilterBackend,
]
http_method_names = ["get"]
required_permissions = []
def get_filterset_class(self):
"""Return the filterset class used for schema generation and the list action.
Note: The resources and latest_resources actions do not use this method
at runtime. They manually instantiate FindingGroupFilter /
LatestFindingGroupFilter against a Finding queryset (see
_get_finding_queryset). The class returned here for those actions only
affects the OpenAPI schema generated by drf-spectacular.
"""
"""Return appropriate filter based on action."""
if self.action == "latest":
return LatestFindingGroupSummaryFilter
if self.action == "resources":
return FindingGroupFilter
if self.action == "latest_resources":
return LatestFindingGroupFilter
return FindingGroupSummaryFilter
def get_queryset(self):
@@ -7227,15 +7190,13 @@ class FindingGroupViewSet(BaseRLSViewSet):
raise ValidationError(filterset.errors)
filtered_queryset = filterset.qs
# Keep only the latest row per (check_id, provider), then aggregate by check_id.
latest_per_check_ids = (
filtered_queryset.order_by("check_id", "provider_id", "-inserted_at")
.distinct("check_id", "provider_id")
.values("id")
)
latest_per_check = filtered_queryset.filter(
id__in=Subquery(latest_per_check_ids)
)
# Keep only rows from the latest inserted_at date per check_id
latest_per_check = filtered_queryset.annotate(
latest_inserted_at=Window(
expression=Max("inserted_at"),
partition_by=[F("check_id")],
)
).filter(inserted_at=F("latest_inserted_at"))
# Re-aggregate daily summaries
aggregated_queryset = self._aggregate_daily_summaries(latest_per_check)
@@ -7271,7 +7232,6 @@ class FindingGroupViewSet(BaseRLSViewSet):
and timing information including how long they have been failing.
""",
tags=["Finding Groups"],
filters=True,
)
@action(detail=True, methods=["get"], url_path="resources")
def resources(self, request, pk=None):
@@ -7346,7 +7306,6 @@ class FindingGroupViewSet(BaseRLSViewSet):
and timing information. No date filters required.
""",
tags=["Finding Groups"],
filters=True,
)
@action(
detail=False,
+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 |
-7
View File
@@ -304,13 +304,6 @@
"pages": [
"user-guide/compliance/tutorials/threatscore"
]
},
{
"group": "Cookbooks",
"pages": [
"user-guide/cookbooks/kubernetes-in-cluster",
"user-guide/cookbooks/cicd-pipeline"
]
}
]
},
@@ -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>
Binary file not shown.

Before

Width:  |  Height:  |  Size: 420 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 486 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 420 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 323 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 419 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 490 KiB

-243
View File
@@ -1,243 +0,0 @@
---
title: 'Run Prowler in CI/CD and Send Findings to Prowler Cloud'
---
This cookbook demonstrates how to integrate Prowler into CI/CD pipelines so that security scans run automatically and findings are sent to Prowler Cloud via [Import Findings](/user-guide/tutorials/prowler-app-import-findings). Examples cover GitHub Actions and GitLab CI.
## Prerequisites
* A **Prowler Cloud** account with an active subscription (see [Prowler Cloud Pricing](https://prowler.com/pricing))
* A Prowler Cloud **API key** with the **Manage Ingestions** permission (see [API Keys](/user-guide/tutorials/prowler-app-api-keys))
* Cloud provider credentials configured in the CI/CD environment (e.g., AWS credentials for scanning AWS accounts)
* Access to configure pipeline workflows and secrets in the CI/CD platform
## Key Concepts
Prowler CLI provides the `--push-to-cloud` flag, which uploads scan results directly to Prowler Cloud after a scan completes. Combined with the `PROWLER_CLOUD_API_KEY` environment variable, this enables fully automated ingestion without manual file uploads.
For full details on the flag and API, refer to the [Import Findings](/user-guide/tutorials/prowler-app-import-findings) documentation.
<Note>
The examples in this guide use AWS as the target provider, but the same approach applies to any provider supported by Prowler (Azure, GCP, Kubernetes, and others). Replace `prowler aws` with the desired provider command (e.g., `prowler gcp`, `prowler azure`) and configure the corresponding credentials in the CI/CD environment.
</Note>
## GitHub Actions
### Store Secrets
Before creating the workflow, add the following secrets to the repository (under "Settings" > "Secrets and variables" > "Actions"):
* `PROWLER_CLOUD_API_KEY` — the Prowler Cloud API key
* Cloud provider credentials (e.g., `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`, or configure OIDC-based role assumption)
### Workflow: Scheduled AWS Scan
This workflow runs Prowler against an AWS account on a daily schedule and on every push to the `main` branch:
```yaml
name: Prowler Security Scan
on:
schedule:
- cron: "0 3 * * *" # Daily at 03:00 UTC
push:
branches: [main]
workflow_dispatch: # Allow manual triggers
permissions:
id-token: write # Required for OIDC
contents: read
jobs:
prowler-scan:
runs-on: ubuntu-latest
steps:
- name: Configure AWS Credentials
uses: aws-actions/configure-aws-credentials@v4
with:
role-to-assume: arn:aws:iam::123456789012:role/ProwlerScanRole
aws-region: us-east-1
- name: Install Prowler
run: pip install prowler
- name: Run Prowler Scan
env:
PROWLER_CLOUD_API_KEY: ${{ secrets.PROWLER_CLOUD_API_KEY }}
run: |
prowler aws --push-to-cloud
```
<Note>
Replace `123456789012` with the actual AWS account ID and `ProwlerScanRole` with the IAM role name. For IAM role setup, refer to the [AWS authentication guide](/user-guide/providers/aws/authentication).
</Note>
### Workflow: Scan Specific Services on Pull Request
To run targeted scans on pull requests without blocking the merge pipeline, use `continue-on-error`:
```yaml
name: Prowler PR Check
on:
pull_request:
branches: [main]
jobs:
prowler-scan:
runs-on: ubuntu-latest
continue-on-error: true
steps:
- name: Configure AWS Credentials
uses: aws-actions/configure-aws-credentials@v4
with:
role-to-assume: arn:aws:iam::123456789012:role/ProwlerScanRole
aws-region: us-east-1
- name: Install Prowler
run: pip install prowler
- name: Run Prowler Scan
env:
PROWLER_CLOUD_API_KEY: ${{ secrets.PROWLER_CLOUD_API_KEY }}
run: |
prowler aws --services s3,iam,ec2 --push-to-cloud
```
<Tip>
Limiting the scan to specific services with `--services` reduces execution time, making it practical for pull request checks.
</Tip>
## GitLab CI
### Store Variables
Add the following CI/CD variables in the GitLab project (under "Settings" > "CI/CD" > "Variables"):
* `PROWLER_CLOUD_API_KEY` — mark as **masked** and **protected**
* Cloud provider credentials as needed
### Pipeline: Scheduled AWS Scan
Add the following to `.gitlab-ci.yml`:
```yaml
prowler-scan:
image: python:3.12-slim
stage: test
script:
- pip install prowler
- prowler aws --push-to-cloud
variables:
PROWLER_CLOUD_API_KEY: $PROWLER_CLOUD_API_KEY
AWS_ACCESS_KEY_ID: $AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY: $AWS_SECRET_ACCESS_KEY
AWS_DEFAULT_REGION: "us-east-1"
rules:
- if: $CI_PIPELINE_SOURCE == "schedule"
- if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
when: manual
```
To run the scan on a schedule, create a **Pipeline Schedule** in GitLab (under "Build" > "Pipeline Schedules") with the desired cron expression.
### Pipeline: Multi-Provider Scan
To scan multiple cloud providers in parallel:
```yaml
stages:
- security
.prowler-base:
image: python:3.12-slim
stage: security
before_script:
- pip install prowler
rules:
- if: $CI_PIPELINE_SOURCE == "schedule"
prowler-aws:
extends: .prowler-base
script:
- prowler aws --push-to-cloud
variables:
PROWLER_CLOUD_API_KEY: $PROWLER_CLOUD_API_KEY
AWS_ACCESS_KEY_ID: $AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY: $AWS_SECRET_ACCESS_KEY
prowler-gcp:
extends: .prowler-base
script:
- prowler gcp --push-to-cloud
variables:
PROWLER_CLOUD_API_KEY: $PROWLER_CLOUD_API_KEY
GOOGLE_APPLICATION_CREDENTIALS: $GCP_SERVICE_ACCOUNT_KEY
```
## Tips and Best Practices
### When to Run Scans
* **Scheduled scans** (daily or weekly) provide continuous monitoring and are ideal for baseline security assessments
* **On-merge scans** catch configuration changes introduced by new code
* **Pull request scans** provide early feedback but should target specific services to keep execution times reasonable
### Handling Scan Failures
By default, Prowler exits with a non-zero code when it finds failing checks. This causes the CI/CD job to fail. To prevent scan results from blocking the pipeline:
* **GitHub Actions**: Add `continue-on-error: true` to the job
* **GitLab CI**: Add `allow_failure: true` to the job
<Note>
Ingestion failures (e.g., network issues reaching Prowler Cloud) do not affect the Prowler exit code. The scan completes normally and only a warning is emitted. See [Import Findings troubleshooting](/user-guide/tutorials/prowler-app-import-findings#troubleshooting) for details.
</Note>
### Caching Prowler Installation
For faster pipeline runs, cache the Prowler installation:
**GitHub Actions:**
```yaml
- name: Cache pip packages
uses: actions/cache@v4
with:
path: ~/.cache/pip
key: ${{ runner.os }}-pip-prowler
restore-keys: ${{ runner.os }}-pip-
- name: Install Prowler
run: pip install prowler
```
**GitLab CI:**
```yaml
prowler-scan:
cache:
paths:
- .cache/pip
variables:
PIP_CACHE_DIR: "$CI_PROJECT_DIR/.cache/pip"
```
### Output Formats
To generate additional report formats alongside the cloud upload:
```bash
prowler aws --push-to-cloud -M csv,html -o /tmp/prowler-reports
```
This produces CSV and HTML files locally while also pushing OCSF findings to Prowler Cloud. The local files can be stored as CI/CD artifacts for archival purposes.
### Scanning Multiple AWS Accounts
To scan multiple accounts sequentially in a single job, use [role assumption](/user-guide/providers/aws/role-assumption):
```bash
prowler aws -R arn:aws:iam::111111111111:role/ProwlerScanRole --push-to-cloud
prowler aws -R arn:aws:iam::222222222222:role/ProwlerScanRole --push-to-cloud
```
Each scan run creates a separate ingestion job in Prowler Cloud.
@@ -1,207 +0,0 @@
---
title: 'Run Kubernetes In-Cluster and Send Findings to Prowler Cloud'
---
This cookbook walks through deploying Prowler inside a Kubernetes cluster on a recurring schedule and automatically sending findings to Prowler Cloud via [Import Findings](/user-guide/tutorials/prowler-app-import-findings). By the end, security scan results from the cluster appear in Prowler Cloud without any manual file uploads.
## Prerequisites
* A **Prowler Cloud** account with an active subscription (see [Prowler Cloud Pricing](https://prowler.com/pricing))
* A Prowler Cloud **API key** with the **Manage Ingestions** permission (see [API Keys](/user-guide/tutorials/prowler-app-api-keys))
* Access to a Kubernetes cluster with `kubectl` configured
* Permissions to create ServiceAccounts, Roles, RoleBindings, Secrets, and CronJobs in the cluster
## Step 1: Create the ServiceAccount and RBAC Resources
Prowler needs a ServiceAccount with read access to cluster resources. Apply the manifests from the [`kubernetes` directory](https://github.com/prowler-cloud/prowler/tree/master/kubernetes) of the Prowler repository:
```console
kubectl apply -f kubernetes/prowler-sa.yaml
kubectl apply -f kubernetes/prowler-role.yaml
kubectl apply -f kubernetes/prowler-rolebinding.yaml
```
This creates:
* A `prowler-sa` ServiceAccount in the `prowler-ns` namespace
* A ClusterRole with the read permissions Prowler requires
* A ClusterRoleBinding linking the ServiceAccount to the role
For more details on these resources, refer to [Getting Started with Kubernetes](/user-guide/providers/kubernetes/getting-started-k8s).
## Step 2: Store the Prowler Cloud API Key as a Secret
Create a Kubernetes Secret to hold the API key securely:
```console
kubectl create secret generic prowler-cloud-api-key \
--from-literal=api-key=pk_your_api_key_here \
--namespace prowler-ns
```
Replace `pk_your_api_key_here` with the actual API key from Prowler Cloud.
<Warning>
Avoid embedding the API key directly in the CronJob manifest. Using a Kubernetes Secret keeps credentials out of version control and pod specs.
</Warning>
## Step 3: Create the CronJob Manifest
The CronJob runs Prowler on a schedule, scanning the cluster and pushing findings to Prowler Cloud with the `--push-to-cloud` flag.
Create a file named `prowler-cronjob.yaml`:
```yaml
apiVersion: batch/v1
kind: CronJob
metadata:
name: prowler-k8s-scan
namespace: prowler-ns
spec:
schedule: "0 2 * * *" # Runs daily at 02:00 UTC
concurrencyPolicy: Forbid
jobTemplate:
spec:
backoffLimit: 1
template:
metadata:
labels:
app: prowler
spec:
serviceAccountName: prowler-sa
containers:
- name: prowler
image: prowlercloud/prowler:stable
args:
- "kubernetes"
- "--push-to-cloud"
env:
- name: PROWLER_CLOUD_API_KEY
valueFrom:
secretKeyRef:
name: prowler-cloud-api-key
key: api-key
- name: CLUSTER_NAME
value: "my-cluster"
imagePullPolicy: Always
volumeMounts:
- name: var-lib-cni
mountPath: /var/lib/cni
readOnly: true
- name: var-lib-etcd
mountPath: /var/lib/etcd
readOnly: true
- name: var-lib-kubelet
mountPath: /var/lib/kubelet
readOnly: true
- name: etc-kubernetes
mountPath: /etc/kubernetes
readOnly: true
hostPID: true
restartPolicy: Never
volumes:
- name: var-lib-cni
hostPath:
path: /var/lib/cni
- name: var-lib-etcd
hostPath:
path: /var/lib/etcd
- name: var-lib-kubelet
hostPath:
path: /var/lib/kubelet
- name: etc-kubernetes
hostPath:
path: /etc/kubernetes
```
<Note>
Replace `my-cluster` with a meaningful name for the cluster. This value appears in Prowler Cloud reports and helps identify the source of findings. See the `--cluster-name` flag documentation in [Getting Started with Kubernetes](/user-guide/providers/kubernetes/getting-started-k8s) for more details.
</Note>
### Customizing the Schedule
The `schedule` field uses standard cron syntax. Common examples:
* `"0 2 * * *"` — daily at 02:00 UTC
* `"0 */6 * * *"` — every 6 hours
* `"0 2 * * 1"` — weekly on Mondays at 02:00 UTC
### Scanning Specific Namespaces
To limit the scan to specific namespaces, add the `--namespace` flag to the `args` array:
```yaml
args:
- "kubernetes"
- "--push-to-cloud"
- "--namespace"
- "production,staging"
```
## Step 4: Deploy and Verify
Apply the CronJob to the cluster:
```console
kubectl apply -f prowler-cronjob.yaml
```
To trigger an immediate test run without waiting for the schedule:
```console
kubectl create job prowler-test-run --from=cronjob/prowler-k8s-scan -n prowler-ns
```
Monitor the job execution:
```console
kubectl get pods -n prowler-ns -l app=prowler --watch
```
Check the logs to confirm findings were pushed successfully:
```console
kubectl logs -n prowler-ns -l app=prowler --tail=50
```
A successful upload produces output similar to:
```
Pushing findings to Prowler Cloud, please wait...
Findings successfully pushed to Prowler Cloud. Ingestion job: fa8bc8c5-4925-46a0-9fe0-f6575905e094
See more details here: https://cloud.prowler.com/scans
```
## Step 5: View Findings in Prowler Cloud
Once the job completes and findings are pushed:
1. Navigate to [Prowler Cloud](https://cloud.prowler.com/)
2. Open the "Scans" section to verify the ingestion job status
3. Browse findings under the Kubernetes provider
For details on the ingestion workflow and status tracking, refer to the [Import Findings](/user-guide/tutorials/prowler-app-import-findings) documentation.
## Tips and Troubleshooting
* **Resource limits**: For large clusters, consider setting `resources.requests` and `resources.limits` on the container to prevent the scan from consuming excessive cluster resources.
* **Network policies**: Ensure the Prowler pod can reach `api.prowler.com` over HTTPS (port 443). Adjust NetworkPolicies or egress rules if needed.
* **Job history**: Kubernetes retains completed and failed jobs by default. Set `successfulJobsHistoryLimit` and `failedJobsHistoryLimit` in the CronJob spec to control cleanup:
```yaml
spec:
successfulJobsHistoryLimit: 3
failedJobsHistoryLimit: 1
```
* **API key rotation**: When rotating the API key, update the Secret and restart any running jobs:
```console
kubectl delete secret prowler-cloud-api-key -n prowler-ns
kubectl create secret generic prowler-cloud-api-key \
--from-literal=api-key=pk_new_api_key_here \
--namespace prowler-ns
```
* **Failed uploads**: If the push to Prowler Cloud fails, the scan still completes and findings are saved locally in the container. Check the [Import Findings troubleshooting section](/user-guide/tutorials/prowler-app-import-findings#troubleshooting) for common error messages.
@@ -2,13 +2,9 @@
title: 'Google Workspace Authentication in Prowler'
---
import { VersionBadge } from "/snippets/version-badge.mdx"
<VersionBadge version="5.19.0" />
Prowler for Google Workspace uses a **Service Account with Domain-Wide Delegation** to authenticate to the Google Workspace Admin SDK. This allows Prowler to read directory data on behalf of a super administrator without requiring an interactive login.
## Required Open Authorization (OAuth) Scopes
## Required OAuth Scopes
Prowler requests the following read-only OAuth 2.0 scopes from the Google Workspace Admin SDK:
@@ -24,16 +20,16 @@ The delegated user must be a **super administrator** in your Google Workspace or
## Setup Steps
### Step 1: Create a Google Cloud Platform (GCP) Project (if Needed)
### Step 1: Create a GCP Project (if needed)
If no GCP project exists, create one at [https://console.cloud.google.com](https://console.cloud.google.com).
If you don't have a GCP project, create one at [https://console.cloud.google.com](https://console.cloud.google.com).
The project is only used to host the Service Account — it does not need to have any Google Workspace data in it.
### Step 2: Enable the Admin SDK API
1. Navigate to the [Google Cloud Console](https://console.cloud.google.com)
2. Select the target project
1. Go to the [Google Cloud Console](https://console.cloud.google.com)
2. Select your project
3. Navigate to **APIs & Services → Library**
4. Search for **Admin SDK API**
5. Click **Enable**
@@ -52,8 +48,8 @@ The Service Account does not need any GCP IAM roles. Its access to Google Worksp
### Step 4: Generate a JSON Key
1. Click the newly created Service Account
2. Navigate to the **Keys** tab
1. Click on the Service Account you just created
2. Go to the **Keys** tab
3. Click **Add Key → Create new key**
4. Select **JSON** format
5. Click **Create** — the key file will download automatically
@@ -65,7 +61,7 @@ This JSON key grants access to your Google Workspace organization. Never commit
### Step 5: Configure Domain-Wide Delegation in Google Workspace
1. Navigate to the [Google Workspace Admin Console](https://admin.google.com)
1. Go to the [Google Workspace Admin Console](https://admin.google.com)
2. Navigate to **Security → Access and data control → API controls**
3. Click **Manage Domain Wide Delegation**
4. Click **Add new**
@@ -82,26 +78,23 @@ https://www.googleapis.com/auth/admin.directory.user.readonly,https://www.google
Domain-Wide Delegation must be configured by a Google Workspace **super administrator**. It may take a few minutes to propagate after saving.
</Note>
### Step 6: Provide Credentials to Prowler
### Step 6: Store Credentials Securely
- **Prowler Cloud:** Paste the Service Account JSON content and enter the delegated user email in the credentials form when configuring the Google Workspace provider.
- **Prowler CLI:** Export the credentials as environment variables:
Set your credentials as environment variables:
```console
```bash
export GOOGLEWORKSPACE_CREDENTIALS_FILE="/path/to/googleworkspace-sa.json"
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
prowler googleworkspace
```
Alternatively, to pass credentials as a string (e.g., in CI/CD pipelines):
Alternatively, if you need to pass credentials as a string (e.g., in CI/CD pipelines):
```console
```bash
export GOOGLEWORKSPACE_CREDENTIALS_CONTENT=$(cat /path/to/googleworkspace-sa.json)
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
prowler googleworkspace
```
## How Prowler Resolves Credentials
## Credential Lookup Order
Prowler resolves credentials in the following order:
@@ -154,7 +147,7 @@ The Service Account cannot impersonate the delegated user. This usually means Do
- All three required OAuth scopes are included
- The delegated user is a super administrator
### Permission Denied on Admin SDK Calls
### Permission Denied on Admin SDK calls
If Prowler connects but returns empty results or permission errors for specific API calls:
@@ -1,131 +1,100 @@
---
title: 'Getting Started With Google Workspace on Prowler'
title: 'Getting Started with Google Workspace'
---
import { VersionBadge } from "/snippets/version-badge.mdx"
Prowler for Google Workspace audits the organization's Google Workspace environment for security misconfigurations, including super administrator account hygiene, domain settings, and more.
## Prerequisites
Set up authentication for Google Workspace with the [Google Workspace Authentication](/user-guide/providers/googleworkspace/authentication) guide before starting either path:
- **Service Account:** Create a Service Account in a GCP project with Domain-Wide Delegation enabled.
- **OAuth Scopes:** Authorize the required read-only OAuth scopes in the Google Workspace Admin Console.
- **Customer ID:** Identify the Google Workspace Customer ID to use as the provider identifier.
- **Delegated User:** Have the email of a super administrator to use as the delegated user.
<CardGroup cols={2}>
<Card title="Prowler Cloud" icon="cloud" href="#prowler-cloud">
Onboard Google Workspace using Prowler Cloud
</Card>
<Card title="Prowler CLI" icon="terminal" href="#prowler-cli">
Onboard Google Workspace using Prowler CLI
</Card>
</CardGroup>
## Prowler Cloud
<VersionBadge version="5.21.0" />
### Step 1: Locate the Customer ID
1. Log into the [Google Workspace Admin Console](https://admin.google.com).
2. Navigate to "Account" > "Account Settings".
3. Find the **Customer ID** on the Account Settings page.
![Google Workspace Customer ID](/images/providers/googleworkspace-customer-id.png)
<Note>
The Customer ID starts with the letter "C" followed by alphanumeric characters (e.g., `C0xxxxxxx`). This value acts as the unique identifier for the Google Workspace account in Prowler Cloud.
</Note>
### Step 2: Open Prowler Cloud
1. Go to [Prowler Cloud](https://cloud.prowler.com/) or launch [Prowler App](/user-guide/tutorials/prowler-app).
2. Navigate to "Configuration" > "Cloud Providers".
![Cloud Providers Page](/images/prowler-app/cloud-providers-page.png)
3. Click "Add Cloud Provider".
![Add a Cloud Provider](/images/prowler-app/add-cloud-provider.png)
4. Select "Google Workspace".
![Select Google Workspace](/images/providers/select-googleworkspace-prowler-cloud.png)
### Step 3: Provide Credentials
1. Enter the **Customer ID** and an optional alias, then click "Next".
![Google Workspace Customer ID Form](/images/providers/googleworkspace-customer-id-form.png)
2. Paste the **Service Account JSON** credentials content.
3. Enter the "Delegated User Email" (a super administrator in the Google Workspace organization).
![Google Workspace Credentials Form](/images/providers/googleworkspace-credentials-form.png)
<Note>
The Service Account JSON is the full content of the key file downloaded when creating the Service Account. Paste the entire JSON object, not just the file path. For setup instructions, see the [Authentication guide](/user-guide/providers/googleworkspace/authentication).
</Note>
### Step 4: Check Connection
1. Click "Check Connection" to verify that the credentials and Domain-Wide Delegation are configured correctly.
2. Prowler will test the Service Account impersonation and Admin SDK access.
![Check Connection](/images/providers/googleworkspace-check-connection.png)
<Note>
If the connection test fails, verify that Domain-Wide Delegation is properly configured and that all three OAuth scopes are authorized. It may take a few minutes for delegation changes to propagate. See the [Troubleshooting](/user-guide/providers/googleworkspace/authentication#troubleshooting) section for common errors.
</Note>
### Step 5: Launch the Scan
1. Review the summary.
2. Click "Launch Scan" to start auditing Google Workspace.
![Launch Scan](/images/providers/googleworkspace-launch-scan.png)
---
## Prowler CLI
import { VersionBadge } from "/snippets/version-badge.mdx";
<VersionBadge version="5.19.0" />
Prowler for Google Workspace allows you to audit your organization's Google Workspace environment for security misconfigurations, including super administrator account hygiene, domain settings, and more.
## Prerequisites
Before running Prowler with the Google Workspace provider, ensure you have:
1. A Google Workspace account with super administrator privileges
2. A Google Cloud Platform (GCP) project to host the Service Account
3. Authentication configured (see [Authentication](/user-guide/providers/googleworkspace/authentication)):
- A **Service Account JSON key** from a GCP project with Domain-Wide Delegation enabled
## Quick Start
### Step 1: Set Up Authentication
Set your Service Account credentials and delegated user email following the [Google Workspace Authentication](/user-guide/providers/googleworkspace/authentication) guide:
Set your Service Account credentials file path and delegated user email as environment variables:
```console
```bash
export GOOGLEWORKSPACE_CREDENTIALS_FILE="/path/to/service-account-key.json"
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
```
Alternatively, pass the credentials content directly as a JSON string:
### Step 2: Run Prowler
```console
export GOOGLEWORKSPACE_CREDENTIALS_CONTENT='{"type": "service_account", ...}'
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
```
### Step 2: Run the First Scan
Run a baseline scan after credentials are configured:
```console
```bash
prowler googleworkspace
```
Prowler authenticates as the delegated user and runs all available security checks against the Google Workspace organization.
Prowler will authenticate as the delegated user and run all available security checks against your Google Workspace organization.
### Step 3: Use a Custom Configuration (Optional)
## Authentication
Prowler uses a **Service Account with Domain-Wide Delegation** to authenticate to Google Workspace. This requires:
- A Service Account created in a GCP project
- The Admin SDK API enabled in that project
- Domain-Wide Delegation configured in the Google Workspace Admin Console
- A super admin user email to impersonate
### Using Environment Variables (Recommended)
```bash
export GOOGLEWORKSPACE_CREDENTIALS_FILE="/path/to/service-account-key.json"
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
prowler googleworkspace
```
Alternatively, pass the credentials content directly as a JSON string:
```bash
export GOOGLEWORKSPACE_CREDENTIALS_CONTENT='{"type": "service_account", ...}'
export GOOGLEWORKSPACE_DELEGATED_USER="admin@yourdomain.com"
prowler googleworkspace
```
<Note>
The delegated user must be a super admin email in your Google Workspace organization. The service account credentials must be provided via environment variables (`GOOGLEWORKSPACE_CREDENTIALS_FILE` or `GOOGLEWORKSPACE_CREDENTIALS_CONTENT`).
</Note>
## Understanding the Output
When Prowler runs successfully, it will display the credentials being used:
```
Using the Google Workspace credentials below:
┌─────────────────────────────────────────────────────────┐
│ Google Workspace Domain: yourdomain.com │
│ Customer ID: C0xxxxxxx │
│ Delegated User: admin@yourdomain.com │
│ Authentication Method: Service Account with Domain-Wide │
│ Delegation │
└─────────────────────────────────────────────────────────┘
```
Findings are reported per check. For example, the `directory_super_admin_count` check verifies the number of super administrators is within a recommended range (24):
- **PASS** — 2 to 4 super administrators found
- **FAIL** — 0 or 1 (single point of failure) or 5+ (excessive privilege exposure)
Output files are saved in the configured output directory (default: `output/`) in CSV, JSON-OCSF, and HTML formats.
## Configuration
Prowler uses a configuration file to customize provider behavior. To use a custom configuration:
```console
```bash
prowler googleworkspace --config-file /path/to/config.yaml
```
---
## Next Steps
- [Authentication](/user-guide/providers/googleworkspace/authentication) — Detailed guide on setting up a Service Account and Domain-Wide Delegation
@@ -164,7 +164,3 @@ env:
```
</Tip>
<Tip>
To set up a production-ready CronJob that runs Prowler on a schedule and sends findings to Prowler Cloud, see the [Run Kubernetes In-Cluster and Send Findings to Prowler Cloud](/user-guide/cookbooks/kubernetes-in-cluster) cookbook.
</Tip>
@@ -202,135 +202,15 @@ To expand the graph for detailed exploration, click the fullscreen icon in the g
width="700"
/>
## Using Attack Paths with the MCP Server and Lighthouse AI
## Using Attack Paths with the MCP Server
Attack Paths capabilities are also available through the [Prowler MCP Server](/getting-started/products/prowler-mcp), enabling interaction with Attack Paths data via AI assistants like Claude Desktop, Cursor, and other MCP clients.
[Prowler Lighthouse AI](/getting-started/products/prowler-lighthouse-ai) also supports Attack Paths queries, allowing you to analyze privilege escalation chains and security misconfigurations directly from the chat interface.
The following MCP tools are available for Attack Paths:
- **`prowler_app_list_attack_paths_scans`** - List and filter Attack Paths scans
- **`prowler_app_list_attack_paths_queries`** - Discover available queries for a completed scan
- **`prowler_app_run_attack_paths_query`** - Execute a query and retrieve graph results with nodes and relationships
- **`prowler_app_get_attack_paths_cartography_schema`** - Retrieve the Cartography graph schema for custom openCypher queries
### Example Questions
Ask through the MCP Server or Lighthouse AI:
- "Find EC2 instances exposed to the internet with access to sensitive S3 buckets"
- "Are there any IAM roles that can escalate their own privileges?"
- "Show me all internet-facing resources with open security groups"
- "Which principals can create Lambda functions with privileged roles?"
- "List all RDS instances with storage encryption disabled"
- "Find S3 buckets that allow anonymous access"
- "Are there any CloudFormation stacks that could be hijacked for privilege escalation?"
- "Show me all roles that can be assumed for lateral movement"
### Supported Queries
Attack Paths currently supports the following built-in queries for AWS:
#### Custom Attack Path Queries
| Query | Description |
|---|---|
| **Internet-Exposed EC2 with Sensitive S3 Access** | Find SSH-exposed EC2 instances that can assume roles to read tagged sensitive S3 buckets |
#### Basic Resource Queries
| Query | Description |
|---|---|
| **RDS Instances Inventory** | List all provisioned RDS database instances in the account |
| **Unencrypted RDS Instances** | Find RDS instances with storage encryption disabled |
| **S3 Buckets with Anonymous Access** | Find S3 buckets that allow anonymous access |
| **IAM Statements Allowing All Actions** | Find IAM policy statements that allow all actions via wildcard (\*) |
| **IAM Statements Allowing Policy Deletion** | Find IAM policy statements that allow iam:DeletePolicy |
| **IAM Statements Allowing Create Actions** | Find IAM policy statements that allow any create action |
#### Network Exposure Queries
| Query | Description |
|---|---|
| **Internet-Exposed EC2 Instances** | Find EC2 instances flagged as exposed to the internet |
| **Open Security Groups on Internet-Facing Resources** | Find internet-facing resources with security groups allowing inbound from 0.0.0.0/0 |
| **Internet-Exposed Classic Load Balancers** | Find Classic Load Balancers exposed to the internet with their listeners |
| **Internet-Exposed ALB/NLB Load Balancers** | Find ELBv2 (ALB/NLB) load balancers exposed to the internet with their listeners |
| **Resource Lookup by Public IP** | Find the AWS resource associated with a given public IP address |
#### Privilege Escalation Queries
These queries are based on research from [pathfinding.cloud](https://pathfinding.cloud) by Datadog.
| Query | Description |
|---|---|
| **App Runner Service Creation with Privileged Role (APPRUNNER-001)** | Create an App Runner service with a privileged IAM role to gain its permissions |
| **App Runner Service Update for Role Access (APPRUNNER-002)** | Update an existing App Runner service to leverage its already-attached privileged role |
| **Bedrock Code Interpreter with Privileged Role (BEDROCK-001)** | Create a Bedrock AgentCore Code Interpreter with a privileged role attached |
| **Bedrock Code Interpreter Session Hijacking (BEDROCK-002)** | Start a session on an existing Bedrock code interpreter to exfiltrate its privileged role credentials |
| **CloudFormation Stack Creation with Privileged Role (CLOUDFORMATION-001)** | Create a CloudFormation stack with a privileged role to provision arbitrary AWS resources |
| **CloudFormation Stack Update for Role Access (CLOUDFORMATION-002)** | Update an existing CloudFormation stack to leverage its already-attached privileged service role |
| **CloudFormation StackSet Creation with Privileged Role (CLOUDFORMATION-003)** | Create a CloudFormation StackSet with a privileged execution role to provision arbitrary resources across accounts |
| **CloudFormation StackSet Update with Privileged Role (CLOUDFORMATION-004)** | Update an existing CloudFormation StackSet to inject malicious resources using a privileged execution role |
| **CloudFormation Change Set Privilege Escalation (CLOUDFORMATION-005)** | Create and execute a change set on an existing stack to leverage its privileged service role |
| **CodeBuild Project Creation with Privileged Role (CODEBUILD-001)** | Create a CodeBuild project with a privileged role to execute arbitrary code via a malicious buildspec |
| **CodeBuild Buildspec Override for Role Access (CODEBUILD-002)** | Start a build on an existing CodeBuild project with a buildspec override to execute code with its privileged role |
| **CodeBuild Batch Buildspec Override for Role Access (CODEBUILD-003)** | Start a batch build on an existing CodeBuild project with a buildspec override to execute code with its privileged role |
| **CodeBuild Batch Project Creation with Privileged Role (CODEBUILD-004)** | Create a CodeBuild project configured for batch builds with a privileged role to execute arbitrary code via a malicious buildspec |
| **Data Pipeline Creation with Privileged Role (DATAPIPELINE-001)** | Create a Data Pipeline with a privileged role to execute arbitrary commands on provisioned infrastructure |
| **EC2 Instance Launch with Privileged Role (EC2-001)** | Launch EC2 instances with privileged IAM roles to gain their permissions via IMDS |
| **EC2 Role Hijacking via UserData Injection (EC2-002)** | Inject malicious scripts into EC2 instance userData to gain the attached role's permissions |
| **Spot Instance Launch with Privileged Role (EC2-003)** | Launch EC2 Spot Instances with privileged IAM roles to gain their permissions via IMDS |
| **Launch Template Poisoning for Role Access (EC2-004)** | Inject malicious userData into launch templates that reference privileged roles, no PassRole needed |
| **EC2 Instance Connect SSH Access for Role Credentials (EC2INSTANCECONNECT-003)** | Push a temporary SSH key to an EC2 instance via Instance Connect to access its attached role credentials through IMDS |
| **ECS Service Creation with Privileged Role (ECS-001 - New Cluster)** | Create an ECS cluster and service with a privileged Fargate task role to execute arbitrary code |
| **ECS Task Execution with Privileged Role (ECS-002 - New Cluster)** | Create an ECS cluster and run a one-off Fargate task with a privileged role to execute arbitrary code |
| **ECS Service Creation with Privileged Role (ECS-003 - Existing Cluster)** | Deploy a Fargate service with a privileged role on an existing ECS cluster |
| **ECS Task Execution with Privileged Role (ECS-004 - Existing Cluster)** | Run a one-off Fargate task with a privileged role on an existing ECS cluster |
| **ECS Task Start with Privileged Role on EC2 (ECS-005 - Existing Cluster)** | Register a task definition with a privileged role and start it on an EC2 container instance to execute arbitrary code |
| **ECS Exec Container Hijacking for Role Credentials (ECS-006)** | Shell into a running ECS container via ECS Exec to steal the attached task role's credentials |
| **Glue Dev Endpoint with Privileged Role (GLUE-001)** | Create a Glue development endpoint with a privileged role attached to gain its permissions |
| **Glue Dev Endpoint SSH Hijacking via Update (GLUE-002)** | Update an existing Glue development endpoint to inject an SSH public key and access its attached role credentials |
| **Glue Job Creation with Privileged Role (GLUE-003)** | Create a Glue job with a privileged role and start it to execute arbitrary code with that role's permissions |
| **Glue Job Creation with Scheduled Trigger and Privileged Role (GLUE-004)** | Create a Glue job with a privileged role and a scheduled trigger to persistently execute arbitrary code |
| **Glue Job Hijacking via Update with Privileged Role (GLUE-005)** | Update an existing Glue job to attach a privileged role and inject malicious code, then start it to gain that role's permissions |
| **Glue Job Hijacking with Scheduled Trigger and Privileged Role (GLUE-006)** | Update an existing Glue job to attach a privileged role and inject malicious code, then create a scheduled trigger for persistent automated execution |
| **Policy Version Override for Self-Escalation (IAM-001)** | Create a new version of an attached policy with administrative permissions, instantly escalating the principal's own privileges |
| **Access Key Creation for Lateral Movement (IAM-002)** | Create access keys for other IAM users to gain their permissions and move laterally across the account |
| **Access Key Rotation Attack for Lateral Movement (IAM-003)** | Delete and recreate access keys for other IAM users to bypass the two-key limit and gain their permissions |
| **Console Login Profile Creation for Lateral Movement (IAM-004)** | Create console login profiles for other IAM users to access the AWS Console with their permissions |
| **Inline Policy Injection for Self-Escalation (IAM-005)** | Attach an inline policy with administrative permissions to your own role, instantly escalating privileges |
| **Console Password Override for Lateral Movement (IAM-006)** | Change the console password of other IAM users to log in as them and gain their permissions |
| **Inline Policy Injection on User for Self-Escalation (IAM-007)** | Attach an inline policy with administrative permissions to your own IAM user, instantly escalating privileges |
| **Managed Policy Attachment on User for Self-Escalation (IAM-008)** | Attach existing managed policies with administrative permissions to your own IAM user, instantly escalating privileges |
| **Managed Policy Attachment on Role for Self-Escalation (IAM-009)** | Attach existing managed policies with administrative permissions to your own IAM role, instantly escalating privileges |
| **Managed Policy Attachment on Group for Self-Escalation (IAM-010)** | Attach existing managed policies with administrative permissions to a group you belong to, escalating privileges for all group members |
| **Inline Policy Injection on Group for Self-Escalation (IAM-011)** | Attach an inline policy with administrative permissions to a group you belong to, escalating privileges for all group members |
| **Trust Policy Hijacking for Role Assumption (IAM-012)** | Modify a role's trust policy to allow yourself to assume it, gaining the role's permissions |
| **Group Membership Hijacking for Privilege Escalation (IAM-013)** | Add yourself to a privileged IAM group to inherit its permissions, gaining access to all policies attached to the group |
| **Managed Policy Attachment with Role Assumption for Lateral Movement (IAM-014)** | Attach administrative managed policies to another role you can assume, then assume it to gain elevated privileges |
| **Managed Policy Attachment with Access Key Creation for Lateral Movement (IAM-015)** | Attach administrative managed policies to another IAM user and create access keys for them to gain programmatic access with elevated privileges |
| **Policy Version Override with Role Assumption for Lateral Movement (IAM-016)** | Create a new version of a customer-managed policy attached to another role with administrative permissions, then assume that role to gain elevated access |
| **Inline Policy Injection with Role Assumption for Lateral Movement (IAM-017)** | Attach an inline policy with administrative permissions to another role you can assume, then assume it to gain elevated privileges |
| **Inline Policy Injection with Access Key Creation for Lateral Movement (IAM-018)** | Attach an inline policy with administrative permissions to another IAM user and create access keys for them to gain programmatic access with elevated privileges |
| **Managed Policy Attachment with Trust Policy Hijacking for Privilege Escalation (IAM-019)** | Attach administrative managed policies to a role and modify its trust policy to allow yourself to assume it, gaining elevated privileges without prior assume-role access |
| **Policy Version Override with Trust Policy Hijacking for Privilege Escalation (IAM-020)** | Create a new version of a customer-managed policy attached to a role with administrative permissions and modify its trust policy to assume it, without prior assume-role access |
| **Inline Policy Injection with Trust Policy Hijacking for Privilege Escalation (IAM-021)** | Add an inline policy with administrative permissions to a role and modify its trust policy to allow yourself to assume it, gaining elevated privileges without prior assume-role access |
| **Lambda Function Creation with Privileged Role (LAMBDA-001)** | Create a Lambda function with a privileged IAM role and invoke it to execute code with that role's permissions |
| **Lambda Function Creation with Event Source Trigger (LAMBDA-002)** | Create a Lambda function with a privileged IAM role and an event source mapping to trigger it automatically, executing code with the role's permissions |
| **Lambda Function Code Injection (LAMBDA-003)** | Modify the code of an existing Lambda function to execute arbitrary commands with the function's execution role permissions |
| **Lambda Function Code Injection with Direct Invocation (LAMBDA-004)** | Modify the code of an existing Lambda function and invoke it directly to execute arbitrary commands with the function's execution role permissions |
| **Lambda Function Code Injection with Resource Policy Grant (LAMBDA-005)** | Modify the code of an existing Lambda function and grant yourself invocation permission via its resource-based policy to execute code with the function's execution role |
| **Lambda Function Creation with Resource Policy Invocation (LAMBDA-006)** | Create a Lambda function with a privileged IAM role and grant yourself invocation permission via its resource-based policy to execute code with the role's permissions |
| **SageMaker Notebook Creation with Privileged Role (SAGEMAKER-001)** | Create a SageMaker notebook instance with a privileged IAM role to execute arbitrary code with the role's permissions via the Jupyter environment |
| **SageMaker Training Job Creation with Privileged Role (SAGEMAKER-002)** | Create a SageMaker training job with a privileged IAM role to execute arbitrary container code with the role's permissions |
| **SageMaker Processing Job Creation with Privileged Role (SAGEMAKER-003)** | Create a SageMaker processing job with a privileged IAM role to execute arbitrary container code with the role's permissions |
| **SageMaker Presigned Notebook URL for Privilege Escalation (SAGEMAKER-004)** | Generate a presigned URL to access an existing SageMaker notebook instance and execute code with its execution role's permissions |
| **SageMaker Notebook Lifecycle Config Injection (SAGEMAKER-005)** | Inject a malicious lifecycle configuration into an existing SageMaker notebook to execute code with the notebook's execution role during startup |
| **SSM Session Access for EC2 Role Credentials (SSM-001)** | Start an SSM session on an EC2 instance to access its attached role credentials through IMDS |
| **SSM Send Command for EC2 Role Credentials (SSM-002)** | Execute commands on an EC2 instance via SSM Run Command to access its attached role credentials through IMDS |
| **Role Assumption for Privilege Escalation (STS-001)** | Assume IAM roles with elevated permissions by exploiting bidirectional trust between the starting principal and the target role |
These tools enable workflows such as:
- Asking an AI assistant to identify privilege escalation paths in a specific AWS account
-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)}"}

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