Compare commits

..

1 Commits

Author SHA1 Message Date
Rubén De la Torre Vico
06a91aa9ff docs: update the changelog 2025-06-02 12:10:09 +02:00
888 changed files with 15296 additions and 61965 deletions

15
.env
View File

@@ -6,15 +6,11 @@
PROWLER_UI_VERSION="stable"
AUTH_URL=http://localhost:3000
API_BASE_URL=http://prowler-api:8080/api/v1
NEXT_PUBLIC_API_BASE_URL=${API_BASE_URL}
NEXT_PUBLIC_API_DOCS_URL=http://prowler-api:8080/api/v1/docs
AUTH_TRUST_HOST=true
UI_PORT=3000
# openssl rand -base64 32
AUTH_SECRET="N/c6mnaS5+SWq81+819OrzQZlmx1Vxtp/orjttJSmw8="
# Google Tag Manager ID
NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID=""
#### Prowler API Configuration ####
PROWLER_API_VERSION="stable"
@@ -131,7 +127,7 @@ SENTRY_ENVIRONMENT=local
SENTRY_RELEASE=local
#### Prowler release version ####
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.7.5
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.6.0
# Social login credentials
SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
@@ -141,12 +137,3 @@ SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET=""
SOCIAL_GITHUB_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/github"
SOCIAL_GITHUB_OAUTH_CLIENT_ID=""
SOCIAL_GITHUB_OAUTH_CLIENT_SECRET=""
# Single Sign-On (SSO)
SAML_SSO_CALLBACK_URL="${AUTH_URL}/api/auth/callback/saml"
# Lighthouse tracing
LANGSMITH_TRACING=false
LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
LANGSMITH_API_KEY=""
LANGCHAIN_PROJECT=""

5
.github/labeler.yml vendored
View File

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

View File

@@ -6,7 +6,6 @@ on:
- "master"
paths:
- "api/**"
- "prowler/**"
- ".github/workflows/api-build-lint-push-containers.yml"
# Uncomment the code below to test this action on PRs
@@ -77,12 +76,12 @@ jobs:
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.WORKING_DIRECTORY }}
# Set push: false for testing
@@ -95,7 +94,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.WORKING_DIRECTORY }}
push: true

View File

@@ -48,12 +48,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/api-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
category: "/language:${{matrix.language}}"

View File

@@ -28,10 +28,6 @@ env:
VALKEY_DB: 0
API_WORKING_DIR: ./api
IMAGE_NAME: prowler-api
IGNORE_FILES: |
api/docs/**
api/README.md
api/CHANGELOG.md
jobs:
test:
@@ -82,7 +78,12 @@ jobs:
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: api/**
files_ignore: ${{ env.IGNORE_FILES }}
files_ignore: |
api/.github/**
api/docs/**
api/permissions/**
api/README.md
api/mkdocs.yml
- name: Replace @master with current branch in pyproject.toml
working-directory: ./api
@@ -112,12 +113,6 @@ jobs:
python-version: ${{ matrix.python-version }}
cache: "poetry"
- name: Install system dependencies for xmlsec
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
sudo apt-get update
sudo apt-get install -y libxml2-dev libxmlsec1-dev libxmlsec1-openssl pkg-config
- name: Install dependencies
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -163,9 +158,8 @@ jobs:
- name: Safety
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
# 76352, 76353, 77323 come from SDK, but they cannot upgrade it yet. It does not affect API
run: |
poetry run safety check --ignore 70612,66963,74429,76352,76353,77323
poetry run safety check --ignore 70612,66963,74429
- name: Vulture
working-directory: ./api
@@ -187,7 +181,7 @@ jobs:
- name: Upload coverage reports to Codecov
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
with:
@@ -196,19 +190,10 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Test if changes are in not ignored paths
id: are-non-ignored-files-changed
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: api/**
files_ignore: ${{ env.IGNORE_FILES }}
- name: Set up Docker Buildx
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.API_WORKING_DIR }}
push: false

View File

@@ -11,7 +11,7 @@ jobs:
with:
fetch-depth: 0
- name: TruffleHog OSS
uses: trufflesecurity/trufflehog@6641d4ba5b684fffe195b9820345de1bf19f3181 # v3.89.2
uses: trufflesecurity/trufflehog@b06f6d72a3791308bb7ba59c2b8cb7a083bd17e4 # v3.88.26
with:
path: ./
base: ${{ github.event.repository.default_branch }}

View File

@@ -1,215 +0,0 @@
name: Prowler Release Preparation
run-name: Prowler Release Preparation for ${{ inputs.prowler_version }}
on:
workflow_dispatch:
inputs:
prowler_version:
description: 'Prowler version to release (e.g., 5.9.0)'
required: true
type: string
env:
PROWLER_VERSION: ${{ github.event.inputs.prowler_version }}
jobs:
prepare-release:
if: github.repository == 'prowler-cloud/prowler'
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Parse version and determine branch
run: |
# Validate version format (reusing pattern from sdk-bump-version.yml)
if [[ $PROWLER_VERSION =~ ^([0-9]+)\.([0-9]+)\.([0-9]+)$ ]]; then
MAJOR_VERSION=${BASH_REMATCH[1]}
MINOR_VERSION=${BASH_REMATCH[2]}
PATCH_VERSION=${BASH_REMATCH[3]}
# Export version components to environment
echo "MAJOR_VERSION=${MAJOR_VERSION}" >> "${GITHUB_ENV}"
echo "MINOR_VERSION=${MINOR_VERSION}" >> "${GITHUB_ENV}"
echo "PATCH_VERSION=${PATCH_VERSION}" >> "${GITHUB_ENV}"
# Determine branch name (format: v5.9)
BRANCH_NAME="v${MAJOR_VERSION}.${MINOR_VERSION}"
echo "BRANCH_NAME=${BRANCH_NAME}" >> "${GITHUB_ENV}"
# Calculate UI version (1.X.X format - matches Prowler minor version)
UI_VERSION="1.${MINOR_VERSION}.${PATCH_VERSION}"
echo "UI_VERSION=${UI_VERSION}" >> "${GITHUB_ENV}"
# Calculate API version (1.X.X format - one minor version ahead)
API_MINOR_VERSION=$((MINOR_VERSION + 1))
API_VERSION="1.${API_MINOR_VERSION}.${PATCH_VERSION}"
echo "API_VERSION=${API_VERSION}" >> "${GITHUB_ENV}"
echo "Prowler version: $PROWLER_VERSION"
echo "Branch name: $BRANCH_NAME"
echo "UI version: $UI_VERSION"
echo "API version: $API_VERSION"
echo "Is minor release: $([ $PATCH_VERSION -eq 0 ] && echo 'true' || echo 'false')"
else
echo "Invalid version syntax: '$PROWLER_VERSION' (must be N.N.N)" >&2
exit 1
fi
- name: Checkout existing branch for patch release
if: ${{ env.PATCH_VERSION != '0' }}
run: |
echo "Patch release detected, checking out existing branch $BRANCH_NAME..."
if git show-ref --verify --quiet "refs/heads/$BRANCH_NAME"; then
echo "Branch $BRANCH_NAME exists locally, checking out..."
git checkout "$BRANCH_NAME"
elif git show-ref --verify --quiet "refs/remotes/origin/$BRANCH_NAME"; then
echo "Branch $BRANCH_NAME exists remotely, checking out..."
git checkout -b "$BRANCH_NAME" "origin/$BRANCH_NAME"
else
echo "ERROR: Branch $BRANCH_NAME should exist for patch release $PROWLER_VERSION"
exit 1
fi
- name: Verify version in pyproject.toml
run: |
CURRENT_VERSION=$(grep '^version = ' pyproject.toml | sed -E 's/version = "([^"]+)"/\1/' | tr -d '[:space:]')
PROWLER_VERSION_TRIMMED=$(echo "$PROWLER_VERSION" | tr -d '[:space:]')
if [ "$CURRENT_VERSION" != "$PROWLER_VERSION_TRIMMED" ]; then
echo "ERROR: Version mismatch in pyproject.toml (expected: '$PROWLER_VERSION_TRIMMED', found: '$CURRENT_VERSION')"
exit 1
fi
echo "✓ pyproject.toml version: $CURRENT_VERSION"
- name: Verify version in prowler/config/config.py
run: |
CURRENT_VERSION=$(grep '^prowler_version = ' prowler/config/config.py | sed -E 's/prowler_version = "([^"]+)"/\1/' | tr -d '[:space:]')
PROWLER_VERSION_TRIMMED=$(echo "$PROWLER_VERSION" | tr -d '[:space:]')
if [ "$CURRENT_VERSION" != "$PROWLER_VERSION_TRIMMED" ]; then
echo "ERROR: Version mismatch in prowler/config/config.py (expected: '$PROWLER_VERSION_TRIMMED', found: '$CURRENT_VERSION')"
exit 1
fi
echo "✓ prowler/config/config.py version: $CURRENT_VERSION"
- name: Verify version in api/pyproject.toml
run: |
CURRENT_API_VERSION=$(grep '^version = ' api/pyproject.toml | sed -E 's/version = "([^"]+)"/\1/' | tr -d '[:space:]')
API_VERSION_TRIMMED=$(echo "$API_VERSION" | tr -d '[:space:]')
if [ "$CURRENT_API_VERSION" != "$API_VERSION_TRIMMED" ]; then
echo "ERROR: API version mismatch in api/pyproject.toml (expected: '$API_VERSION_TRIMMED', found: '$CURRENT_API_VERSION')"
exit 1
fi
echo "✓ api/pyproject.toml version: $CURRENT_API_VERSION"
- name: Verify prowler dependency in api/pyproject.toml
run: |
CURRENT_PROWLER_REF=$(grep 'prowler @ git+https://github.com/prowler-cloud/prowler.git@' api/pyproject.toml | sed -E 's/.*@([^"]+)".*/\1/' | tr -d '[:space:]')
PROWLER_VERSION_TRIMMED=$(echo "$PROWLER_VERSION" | tr -d '[:space:]')
if [ "$CURRENT_PROWLER_REF" != "$PROWLER_VERSION_TRIMMED" ]; then
echo "ERROR: Prowler dependency mismatch in api/pyproject.toml (expected: '$PROWLER_VERSION_TRIMMED', found: '$CURRENT_PROWLER_REF')"
exit 1
fi
echo "✓ api/pyproject.toml prowler dependency: $CURRENT_PROWLER_REF"
- name: Verify version in api/src/backend/api/v1/views.py
run: |
CURRENT_API_VERSION=$(grep 'spectacular_settings.VERSION = ' api/src/backend/api/v1/views.py | sed -E 's/.*spectacular_settings.VERSION = "([^"]+)".*/\1/' | tr -d '[:space:]')
API_VERSION_TRIMMED=$(echo "$API_VERSION" | tr -d '[:space:]')
if [ "$CURRENT_API_VERSION" != "$API_VERSION_TRIMMED" ]; then
echo "ERROR: API version mismatch in views.py (expected: '$API_VERSION_TRIMMED', found: '$CURRENT_API_VERSION')"
exit 1
fi
echo "✓ api/src/backend/api/v1/views.py version: $CURRENT_API_VERSION"
- name: Create release branch for minor release
if: ${{ env.PATCH_VERSION == '0' }}
run: |
echo "Minor release detected (patch = 0), creating new branch $BRANCH_NAME..."
if git show-ref --verify --quiet "refs/heads/$BRANCH_NAME" || git show-ref --verify --quiet "refs/remotes/origin/$BRANCH_NAME"; then
echo "ERROR: Branch $BRANCH_NAME already exists for minor release $PROWLER_VERSION"
exit 1
fi
git checkout -b "$BRANCH_NAME"
- name: Extract changelog entries
run: |
set -e
# Function to extract changelog for a specific version
extract_changelog() {
local file="$1"
local version="$2"
local output_file="$3"
if [ ! -f "$file" ]; then
echo "Warning: $file not found, skipping..."
touch "$output_file"
return
fi
# Extract changelog section for this version
awk -v version="$version" '
/^## \[v?'"$version"'\]/ { found=1; next }
found && /^## \[v?[0-9]+\.[0-9]+\.[0-9]+\]/ { found=0 }
found && !/^## \[v?'"$version"'\]/ { print }
' "$file" > "$output_file"
# Remove --- separators
sed -i '/^---$/d' "$output_file"
# Remove trailing empty lines
sed -i '/^$/d' "$output_file"
}
# Extract changelogs
echo "Extracting changelog entries..."
extract_changelog "prowler/CHANGELOG.md" "$PROWLER_VERSION" "prowler_changelog.md"
extract_changelog "api/CHANGELOG.md" "$API_VERSION" "api_changelog.md"
extract_changelog "ui/CHANGELOG.md" "$UI_VERSION" "ui_changelog.md"
# Combine changelogs in order: UI, API, SDK
> combined_changelog.md
if [ -s "ui_changelog.md" ]; then
echo "## UI" >> combined_changelog.md
echo "" >> combined_changelog.md
cat ui_changelog.md >> combined_changelog.md
echo "" >> combined_changelog.md
fi
if [ -s "api_changelog.md" ]; then
echo "## API" >> combined_changelog.md
echo "" >> combined_changelog.md
cat api_changelog.md >> combined_changelog.md
echo "" >> combined_changelog.md
fi
if [ -s "prowler_changelog.md" ]; then
echo "## SDK" >> combined_changelog.md
echo "" >> combined_changelog.md
cat prowler_changelog.md >> combined_changelog.md
echo "" >> combined_changelog.md
fi
echo "Combined changelog preview:"
cat combined_changelog.md
- name: Create draft release
uses: softprops/action-gh-release@72f2c25fcb47643c292f7107632f7a47c1df5cd8 # v2.3.2
with:
tag_name: ${{ env.PROWLER_VERSION }}
name: Prowler ${{ env.PROWLER_VERSION }}
body_path: combined_changelog.md
draft: true
target_commitish: ${{ env.PATCH_VERSION == '0' && 'master' || env.BRANCH_NAME }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Clean up temporary files
run: |
rm -f prowler_changelog.md api_changelog.md ui_changelog.md combined_changelog.md

View File

@@ -1,86 +0,0 @@
name: Check Changelog
on:
pull_request:
types: [opened, synchronize, reopened, labeled, unlabeled]
jobs:
check-changelog:
if: contains(github.event.pull_request.labels.*.name, 'no-changelog') == false
runs-on: ubuntu-latest
permissions:
id-token: write
contents: read
pull-requests: write
env:
MONITORED_FOLDERS: "api ui prowler"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Get list of changed files
id: changed_files
run: |
git fetch origin ${{ github.base_ref }}
git diff --name-only origin/${{ github.base_ref }}...HEAD > changed_files.txt
cat changed_files.txt
- name: Check for folder changes and changelog presence
id: check_folders
run: |
missing_changelogs=""
for folder in $MONITORED_FOLDERS; do
if grep -q "^${folder}/" changed_files.txt; then
echo "Detected changes in ${folder}/"
if ! grep -q "^${folder}/CHANGELOG.md$" changed_files.txt; then
echo "No changelog update found for ${folder}/"
missing_changelogs="${missing_changelogs}- \`${folder}\`\n"
fi
fi
done
echo "missing_changelogs<<EOF" >> $GITHUB_OUTPUT
echo -e "${missing_changelogs}" >> $GITHUB_OUTPUT
echo "EOF" >> $GITHUB_OUTPUT
- name: Find existing changelog comment
if: github.event.pull_request.head.repo.full_name == github.repository
id: find_comment
uses: peter-evans/find-comment@3eae4d37986fb5a8592848f6a574fdf654e61f9e #v3.1.0
with:
issue-number: ${{ github.event.pull_request.number }}
comment-author: 'github-actions[bot]'
body-includes: '<!-- changelog-check -->'
- name: Comment on PR if changelog is missing
if: github.event.pull_request.head.repo.full_name == github.repository && steps.check_folders.outputs.missing_changelogs != ''
uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
with:
issue-number: ${{ github.event.pull_request.number }}
comment-id: ${{ steps.find_comment.outputs.comment-id }}
body: |
<!-- changelog-check -->
⚠️ **Changes detected in the following folders without a corresponding update to the `CHANGELOG.md`:**
${{ steps.check_folders.outputs.missing_changelogs }}
Please add an entry to the corresponding `CHANGELOG.md` file to maintain a clear history of changes.
- name: Comment on PR if all changelogs are present
if: github.event.pull_request.head.repo.full_name == github.repository && steps.check_folders.outputs.missing_changelogs == ''
uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
with:
issue-number: ${{ github.event.pull_request.number }}
comment-id: ${{ steps.find_comment.outputs.comment-id }}
body: |
<!-- changelog-check -->
✅ All necessary `CHANGELOG.md` files have been updated. Great job! 🎉
- name: Fail if changelog is missing
if: steps.check_folders.outputs.missing_changelogs != ''
run: |
echo "ERROR: Missing changelog updates in some folders."
exit 1

View File

@@ -123,11 +123,11 @@ jobs:
AWS_REGION: ${{ env.AWS_REGION }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build and push container image (latest)
if: github.event_name == 'push'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
push: true
tags: |
@@ -140,7 +140,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
# Use local context to get changes
# https://github.com/docker/build-push-action#path-context

View File

@@ -97,7 +97,6 @@ jobs:
commit-message: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
branch: "version-bump-to-v${{ env.BUMP_VERSION_TO }}"
title: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
labels: no-changelog
body: |
### Description
@@ -136,7 +135,6 @@ jobs:
commit-message: "chore(release): Bump version to v${{ env.PATCH_VERSION_TO }}"
branch: "version-bump-to-v${{ env.PATCH_VERSION_TO }}"
title: "chore(release): Bump version to v${{ env.PATCH_VERSION_TO }}"
labels: no-changelog
body: |
### Description

View File

@@ -56,12 +56,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/sdk-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
category: "/language:${{matrix.language}}"

View File

@@ -102,15 +102,8 @@ jobs:
run: |
poetry run vulture --exclude "contrib,api,ui" --min-confidence 100 .
- name: Dockerfile - Check if Dockerfile has changed
id: dockerfile-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
Dockerfile
- name: Hadolint
if: steps.dockerfile-changed-files.outputs.any_changed == 'true'
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
/tmp/hadolint Dockerfile --ignore=DL3013
@@ -219,21 +212,6 @@ jobs:
run: |
poetry run pytest -n auto --cov=./prowler/providers/m365 --cov-report=xml:m365_coverage.xml tests/providers/m365
# Test IaC
- name: IaC - Check if any file has changed
id: iac-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/iac/**
./tests/providers/iac/**
.poetry.lock
- name: IaC - Test
if: steps.iac-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/iac --cov-report=xml:iac_coverage.xml tests/providers/iac
# Common Tests
- name: Lib - Test
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -248,7 +226,7 @@ jobs:
# Codecov
- name: Upload coverage reports to Codecov
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
with:

View File

@@ -38,7 +38,7 @@ jobs:
pip install boto3
- name: Configure AWS Credentials -- DEV
uses: aws-actions/configure-aws-credentials@b47578312673ae6fa5b5096b330d9fbac3d116df # v4.2.1
uses: aws-actions/configure-aws-credentials@ececac1a45f3b08a01d2dd070d28d111c5fe6722 # v4.1.0
with:
aws-region: ${{ env.AWS_REGION_DEV }}
role-to-assume: ${{ secrets.DEV_IAM_ROLE_ARN }}

View File

@@ -30,7 +30,6 @@ env:
# Container Registries
PROWLERCLOUD_DOCKERHUB_REPOSITORY: prowlercloud
PROWLERCLOUD_DOCKERHUB_IMAGE: prowler-ui
NEXT_PUBLIC_API_BASE_URL: http://prowler-api:8080/api/v1
jobs:
repository-check:
@@ -77,17 +76,16 @@ jobs:
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=${{ env.SHORT_SHA }}
NEXT_PUBLIC_API_BASE_URL=${{ env.NEXT_PUBLIC_API_BASE_URL }}
# Set push: false for testing
push: true
tags: |
@@ -98,12 +96,11 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${{ env.RELEASE_TAG }}
NEXT_PUBLIC_API_BASE_URL=${{ env.NEXT_PUBLIC_API_BASE_URL }}
push: true
tags: |
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.RELEASE_TAG }}

View File

@@ -48,12 +48,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/ui-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
with:
category: "/language:${{matrix.language}}"

View File

@@ -34,72 +34,23 @@ jobs:
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
with:
node-version: ${{ matrix.node-version }}
cache: 'npm'
cache-dependency-path: './ui/package-lock.json'
- name: Install dependencies
working-directory: ./ui
run: npm ci
run: npm install
- name: Run Healthcheck
working-directory: ./ui
run: npm run healthcheck
- name: Build the application
working-directory: ./ui
run: npm run build
e2e-tests:
runs-on: ubuntu-latest
env:
AUTH_SECRET: 'fallback-ci-secret-for-testing'
AUTH_TRUST_HOST: true
NEXTAUTH_URL: http://localhost:3000
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Setup Node.js
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
with:
node-version: '20.x'
cache: 'npm'
cache-dependency-path: './ui/package-lock.json'
- name: Install dependencies
working-directory: ./ui
run: npm ci
- name: Cache Playwright browsers
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
id: playwright-cache
with:
path: ~/.cache/ms-playwright
key: ${{ runner.os }}-playwright-${{ hashFiles('ui/package-lock.json') }}
restore-keys: |
${{ runner.os }}-playwright-
- name: Install Playwright browsers
working-directory: ./ui
if: steps.playwright-cache.outputs.cache-hit != 'true'
run: npm run test:e2e:install
- name: Build the application
working-directory: ./ui
run: npm run build
- name: Run Playwright tests
working-directory: ./ui
run: npm run test:e2e
- name: Upload Playwright report
uses: actions/upload-artifact@6f51ac03b9356f520e9adb1b1b7802705f340c2b # v4.5.0
if: failure()
with:
name: playwright-report
path: ui/playwright-report/
retention-days: 30
test-container-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
with:
context: ${{ env.UI_WORKING_DIR }}
# Always build using `prod` target

10
.gitignore vendored
View File

@@ -44,16 +44,6 @@ junit-reports/
# Cursor files
.cursorignore
.cursor/
# RooCode files
.roo/
.rooignore
.roomodes
# Cline files
.cline/
.clineignore
# Terraform
.terraform*

View File

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

View File

@@ -1,4 +1,4 @@
FROM python:3.12.11-slim-bookworm AS build
FROM python:3.12.10-slim-bookworm AS build
LABEL maintainer="https://github.com/prowler-cloud/prowler"
LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
@@ -6,8 +6,7 @@ LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
ARG POWERSHELL_VERSION=7.5.0
# hadolint ignore=DL3008
RUN apt-get update && apt-get install -y --no-install-recommends \
wget libicu72 libunwind8 libssl3 libcurl4 ca-certificates apt-transport-https gnupg \
RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
&& rm -rf /var/lib/apt/lists/*
# Install PowerShell
@@ -47,6 +46,10 @@ ENV PATH="${HOME}/.local/bin:${PATH}"
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir poetry
# By default poetry does not compile Python source files to bytecode during installation.
# This speeds up the installation process, but the first execution may take a little more
# time because Python then compiles source files to bytecode automatically. If you want to
# compile source files to bytecode during installation, you can use the --compile option
RUN poetry install --compile && \
rm -rf ~/.cache/pip

View File

@@ -87,11 +87,11 @@ prowler dashboard
| Provider | Checks | Services | [Compliance Frameworks](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/compliance/) | [Categories](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/misc/#categories) |
|---|---|---|---|---|
| AWS | 567 | 82 | 36 | 10 |
| GCP | 79 | 13 | 10 | 3 |
| GCP | 79 | 13 | 9 | 3 |
| Azure | 142 | 18 | 10 | 3 |
| Kubernetes | 83 | 7 | 5 | 7 |
| GitHub | 16 | 2 | 1 | 0 |
| M365 | 69 | 7 | 3 | 2 |
| M365 | 69 | 7 | 2 | 2 |
| NHN (Unofficial) | 6 | 2 | 1 | 0 |
> [!Note]
@@ -136,14 +136,6 @@ If your workstation's architecture is incompatible, you can resolve this by:
> Once configured, access the Prowler App at http://localhost:3000. Sign up using your email and password to get started.
### Common Issues with Docker Pull Installation
> [!Note]
If you want to use AWS role assumption (e.g., with the "Connect assuming IAM Role" option), you may need to mount your local `.aws` directory into the container as a volume (e.g., `- "${HOME}/.aws:/home/prowler/.aws:ro"`). There are several ways to configure credentials for Docker containers. See the [Troubleshooting](./docs/troubleshooting.md) section for more details and examples.
You can find more information in the [Troubleshooting](./docs/troubleshooting.md) section.
### From GitHub
**Requirements**

168
api/.gitignore vendored Normal file
View File

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

View File

@@ -0,0 +1,91 @@
repos:
## GENERAL
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.6.0
hooks:
- id: check-merge-conflict
- id: check-yaml
args: ["--unsafe"]
- id: check-json
- id: end-of-file-fixer
- id: trailing-whitespace
- id: no-commit-to-branch
- id: pretty-format-json
args: ["--autofix", "--no-sort-keys", "--no-ensure-ascii"]
exclude: 'src/backend/api/fixtures/dev/.*\.json$'
## TOML
- repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
rev: v2.13.0
hooks:
- id: pretty-format-toml
args: [--autofix]
files: pyproject.toml
## BASH
- repo: https://github.com/koalaman/shellcheck-precommit
rev: v0.10.0
hooks:
- id: shellcheck
exclude: contrib
## PYTHON
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.5.0
hooks:
# Run the linter.
- id: ruff
args: [ --fix ]
# Run the formatter.
- id: ruff-format
- repo: https://github.com/python-poetry/poetry
rev: 1.8.0
hooks:
- id: poetry-check
args: ["--directory=src"]
- id: poetry-lock
args: ["--no-update", "--directory=src"]
- repo: https://github.com/hadolint/hadolint
rev: v2.13.0-beta
hooks:
- id: hadolint
args: ["--ignore=DL3013", "Dockerfile"]
- repo: local
hooks:
- id: pylint
name: pylint
entry: bash -c 'poetry run pylint --disable=W,C,R,E -j 0 -rn -sn src/'
language: system
files: '.*\.py'
- id: trufflehog
name: TruffleHog
description: Detect secrets in your data.
entry: bash -c 'trufflehog --no-update git file://. --only-verified --fail'
# For running trufflehog in docker, use the following entry instead:
# entry: bash -c 'docker run -v "$(pwd):/workdir" -i --rm trufflesecurity/trufflehog:latest git file:///workdir --only-verified --fail'
language: system
stages: ["commit", "push"]
- id: bandit
name: bandit
description: "Bandit is a tool for finding common security issues in Python code"
entry: bash -c 'poetry run bandit -q -lll -x '*_test.py,./contrib/,./.venv/' -r .'
language: system
files: '.*\.py'
- id: safety
name: safety
description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
entry: bash -c 'poetry run safety check --ignore 70612,66963,74429'
language: system
- id: vulture
name: vulture
description: "Vulture finds unused code in Python programs."
entry: bash -c 'poetry run vulture --exclude "contrib,.venv,tests,conftest.py" --min-confidence 100 .'
language: system
files: '.*\.py'

View File

@@ -2,132 +2,44 @@
All notable changes to the **Prowler API** are documented in this file.
## [1.10.2] (Prowler v5.9.2)
### Changed
- Optimized queries for resources views [(#8336)](https://github.com/prowler-cloud/prowler/pull/8336)
---
## [v1.10.1] (Prowler v5.9.1)
### Fixed
- Calculate failed findings during scans to prevent heavy database queries [(#8322)](https://github.com/prowler-cloud/prowler/pull/8322)
---
## [v1.10.0] (Prowler v5.9.0)
## [v1.9.0] (Prowler UNRELEASED)
### Added
- SSO with SAML support [(#8175)](https://github.com/prowler-cloud/prowler/pull/8175)
- `GET /resources/metadata`, `GET /resources/metadata/latest` and `GET /resources/latest` to expose resource metadata and latest scan results [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
### Changed
- `/processors` endpoints to post-process findings. Currently, only the Mutelist processor is supported to allow to mute findings.
- Optimized the underlying queries for resources endpoints [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
- Optimized include parameters for resources view [(#8229)](https://github.com/prowler-cloud/prowler/pull/8229)
- Optimized overview background tasks [(#8300)](https://github.com/prowler-cloud/prowler/pull/8300)
### Fixed
- Search filter for findings and resources [(#8112)](https://github.com/prowler-cloud/prowler/pull/8112)
- RBAC is now applied to `GET /overviews/providers` [(#8277)](https://github.com/prowler-cloud/prowler/pull/8277)
### Changed
- `POST /schedules/daily` returns a `409 CONFLICT` if already created [(#8258)](https://github.com/prowler-cloud/prowler/pull/8258)
### Security
- Enhanced password validation to enforce 12+ character passwords with special characters, uppercase, lowercase, and numbers [(#8225)](https://github.com/prowler-cloud/prowler/pull/8225)
---
## [v1.9.1] (Prowler v5.8.1)
### Added
- Custom exception for provider connection errors during scans [(#8234)](https://github.com/prowler-cloud/prowler/pull/8234)
### Changed
- Summary and overview tasks now use a dedicated queue and no longer propagate errors to compliance tasks [(#8214)](https://github.com/prowler-cloud/prowler/pull/8214)
### Fixed
- Scan with no resources will not trigger legacy code for findings metadata [(#8183)](https://github.com/prowler-cloud/prowler/pull/8183)
- Invitation email comparison case-insensitive [(#8206)](https://github.com/prowler-cloud/prowler/pull/8206)
### Removed
- Validation of the provider's secret type during updates [(#8197)](https://github.com/prowler-cloud/prowler/pull/8197)
---
## [v1.9.0] (Prowler v5.8.0)
### Added
- Support GCP Service Account key [(#7824)](https://github.com/prowler-cloud/prowler/pull/7824)
- `GET /compliance-overviews` endpoints to retrieve compliance metadata and specific requirements statuses [(#7877)](https://github.com/prowler-cloud/prowler/pull/7877)
- Lighthouse configuration support [(#7848)](https://github.com/prowler-cloud/prowler/pull/7848)
### Changed
- Reworked `GET /compliance-overviews` to return proper requirement metrics [(#7877)](https://github.com/prowler-cloud/prowler/pull/7877)
- Optional `user` and `password` for M365 provider [(#7992)](https://github.com/prowler-cloud/prowler/pull/7992)
### Fixed
- Scheduled scans are no longer deleted when their daily schedule run is disabled [(#8082)](https://github.com/prowler-cloud/prowler/pull/8082)
---
## [v1.8.5] (Prowler v5.7.5)
### Fixed
- Normalize provider UID to ensure safe and unique export directory paths [(#8007)](https://github.com/prowler-cloud/prowler/pull/8007).
- Blank resource types in `/metadata` endpoints [(#8027)](https://github.com/prowler-cloud/prowler/pull/8027)
---
## [v1.8.4] (Prowler v5.7.4)
### Removed
- Reverted RLS transaction handling and DB custom backend [(#7994)](https://github.com/prowler-cloud/prowler/pull/7994)
---
## [v1.8.3] (Prowler v5.7.3)
### Added
- Database backend to handle already closed connections [(#7935)](https://github.com/prowler-cloud/prowler/pull/7935)
- Support GCP Service Account key. [(#7824)](https://github.com/prowler-cloud/prowler/pull/7824)
### Changed
- Renamed field encrypted_password to password for M365 provider [(#7784)](https://github.com/prowler-cloud/prowler/pull/7784)
### Fixed
- Transaction persistence with RLS operations [(#7916)](https://github.com/prowler-cloud/prowler/pull/7916)
- Reverted the change `get_with_retry` to use the original `get` method for retrieving tasks [(#7932)](https://github.com/prowler-cloud/prowler/pull/7932)
- Fixed the connection status verification before launching a scan [(#7831)](https://github.com/prowler-cloud/prowler/pull/7831)
---
## [v1.8.2] (Prowler v5.7.2)
### Fixed
- Task lookup to use task_kwargs instead of task_args for scan report resolution [(#7830)](https://github.com/prowler-cloud/prowler/pull/7830)
- Kubernetes UID validation to allow valid context names [(#7871)](https://github.com/prowler-cloud/prowler/pull/7871)
- Connection status verification before launching a scan [(#7831)](https://github.com/prowler-cloud/prowler/pull/7831)
- Race condition when creating background tasks [(#7876)](https://github.com/prowler-cloud/prowler/pull/7876)
- Error when modifying or retrieving tenants due to missing user UUID in transaction context [(#7890)](https://github.com/prowler-cloud/prowler/pull/7890)
- Fixed task lookup to use task_kwargs instead of task_args for scan report resolution. [(#7830)](https://github.com/prowler-cloud/prowler/pull/7830)
- Fixed Kubernetes UID validation to allow valid context names [(#7871)](https://github.com/prowler-cloud/prowler/pull/7871)
- Fixed a race condition when creating background tasks [(#7876)](https://github.com/prowler-cloud/prowler/pull/7876).
- Fixed an error when modifying or retrieving tenants due to missing user UUID in transaction context [(#7890)](https://github.com/prowler-cloud/prowler/pull/7890).
---
## [v1.8.1] (Prowler v5.7.1)
### Fixed
- Added database index to improve performance on finding lookup [(#7800)](https://github.com/prowler-cloud/prowler/pull/7800)
- Added database index to improve performance on finding lookup. [(#7800)](https://github.com/prowler-cloud/prowler/pull/7800)
---
## [v1.8.0] (Prowler v5.7.0)
### Added
- Huge improvements to `/findings/metadata` and resource related filters for findings [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
- Improvements to `/overviews` endpoints [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
- Queue to perform backfill background tasks [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690)
- New endpoints to retrieve latest findings and metadata [(#7743)](https://github.com/prowler-cloud/prowler/pull/7743)
- Export support for Prowler ThreatScore in M365 [(7783)](https://github.com/prowler-cloud/prowler/pull/7783)
- Added huge improvements to `/findings/metadata` and resource related filters for findings [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
- Added improvements to `/overviews` endpoints [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
- Added new queue to perform backfill background tasks [(#7690)](https://github.com/prowler-cloud/prowler/pull/7690).
- Added new endpoints to retrieve latest findings and metadata [(#7743)](https://github.com/prowler-cloud/prowler/pull/7743).
- Added export support for Prowler ThreatScore in M365 [(7783)](https://github.com/prowler-cloud/prowler/pull/7783)
---
@@ -135,9 +47,9 @@ All notable changes to the **Prowler API** are documented in this file.
### Added
- M365 as a new provider [(#7563)](https://github.com/prowler-cloud/prowler/pull/7563)
- `compliance/` folder and ZIPexport functionality for all compliance reports [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653)
- API endpoint to fetch and download any specific compliance file by name [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653)
- Added M365 as a new provider [(#7563)](https://github.com/prowler-cloud/prowler/pull/7563).
- Added a `compliance/` folder and ZIPexport functionality for all compliance reports.[(#7653)](https://github.com/prowler-cloud/prowler/pull/7653).
- Added a new API endpoint to fetch and download any specific compliance file by name [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653).
---
@@ -145,42 +57,43 @@ All notable changes to the **Prowler API** are documented in this file.
### Added
- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167)
- HTTP Security Headers [(#7289)](https://github.com/prowler-cloud/prowler/pull/7289)
- New endpoint to get the compliance overviews metadata [(#7333)](https://github.com/prowler-cloud/prowler/pull/7333)
- Support for muted findings [(#7378)](https://github.com/prowler-cloud/prowler/pull/7378)
- Missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318)
- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167).
- HTTP Security Headers [(#7289)](https://github.com/prowler-cloud/prowler/pull/7289).
- New endpoint to get the compliance overviews metadata [(#7333)](https://github.com/prowler-cloud/prowler/pull/7333).
- Support for muted findings [(#7378)](https://github.com/prowler-cloud/prowler/pull/7378).
- Added missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318).
---
## [v1.5.4] (Prowler v5.4.4)
### Fixed
- Bug with periodic tasks when trying to delete a provider [(#7466)](https://github.com/prowler-cloud/prowler/pull/7466)
- Fixed a bug with periodic tasks when trying to delete a provider ([#7466])(https://github.com/prowler-cloud/prowler/pull/7466).
---
## [v1.5.3] (Prowler v5.4.3)
### Fixed
- Duplicated scheduled scans handling [(#7401)](https://github.com/prowler-cloud/prowler/pull/7401)
- Environment variable to configure the deletion task batch size [(#7423)](https://github.com/prowler-cloud/prowler/pull/7423)
- Added duplicated scheduled scans handling ([#7401])(https://github.com/prowler-cloud/prowler/pull/7401).
- Added environment variable to configure the deletion task batch size ([#7423])(https://github.com/prowler-cloud/prowler/pull/7423).
---
## [v1.5.2] (Prowler v5.4.2)
### Changed
- Refactored deletion logic and implemented retry mechanism for deletion tasks [(#7349)](https://github.com/prowler-cloud/prowler/pull/7349)
- Refactored deletion logic and implemented retry mechanism for deletion tasks [(#7349)](https://github.com/prowler-cloud/prowler/pull/7349).
---
## [v1.5.1] (Prowler v5.4.1)
### Fixed
- Handle response in case local files are missing [(#7183)](https://github.com/prowler-cloud/prowler/pull/7183)
- Race condition when deleting export files after the S3 upload [(#7172)](https://github.com/prowler-cloud/prowler/pull/7172)
- Handle exception when a provider has no secret in test connection [(#7283)](https://github.com/prowler-cloud/prowler/pull/7283)
- Added a handled response in case local files are missing [(#7183)](https://github.com/prowler-cloud/prowler/pull/7183).
- Fixed a race condition when deleting export files after the S3 upload [(#7172)](https://github.com/prowler-cloud/prowler/pull/7172).
- Handled exception when a provider has no secret in test connection [(#7283)](https://github.com/prowler-cloud/prowler/pull/7283).
---
@@ -188,20 +101,20 @@ All notable changes to the **Prowler API** are documented in this file.
### Added
- Social login integration with Google and GitHub [(#6906)](https://github.com/prowler-cloud/prowler/pull/6906)
- API scan report system, now all scans launched from the API will generate a compressed file with the report in OCSF, CSV and HTML formats [(#6878)](https://github.com/prowler-cloud/prowler/pull/6878)
- Add API scan report system, now all scans launched from the API will generate a compressed file with the report in OCSF, CSV and HTML formats [(#6878)](https://github.com/prowler-cloud/prowler/pull/6878).
- Configurable Sentry integration [(#6874)](https://github.com/prowler-cloud/prowler/pull/6874)
### Changed
- Optimized `GET /findings` endpoint to improve response time and size [(#7019)](https://github.com/prowler-cloud/prowler/pull/7019)
- Optimized `GET /findings` endpoint to improve response time and size [(#7019)](https://github.com/prowler-cloud/prowler/pull/7019).
---
## [v1.4.0] (Prowler v5.3.0)
### Changed
- Daily scheduled scan instances are now created beforehand with `SCHEDULED` state [(#6700)](https://github.com/prowler-cloud/prowler/pull/6700)
- Findings endpoints now require at least one date filter [(#6800)](https://github.com/prowler-cloud/prowler/pull/6800)
- Findings metadata endpoint received a performance improvement [(#6863)](https://github.com/prowler-cloud/prowler/pull/6863)
- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869)
- Daily scheduled scan instances are now created beforehand with `SCHEDULED` state [(#6700)](https://github.com/prowler-cloud/prowler/pull/6700).
- Findings endpoints now require at least one date filter [(#6800)](https://github.com/prowler-cloud/prowler/pull/6800).
- Findings metadata endpoint received a performance improvement [(#6863)](https://github.com/prowler-cloud/prowler/pull/6863).
- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869).
---

View File

@@ -6,19 +6,7 @@ ARG POWERSHELL_VERSION=7.5.0
ENV POWERSHELL_VERSION=${POWERSHELL_VERSION}
# hadolint ignore=DL3008
RUN apt-get update && apt-get install -y --no-install-recommends \
wget \
libicu72 \
gcc \
g++ \
make \
libxml2-dev \
libxmlsec1-dev \
libxmlsec1-openssl \
pkg-config \
libtool \
libxslt1-dev \
python3-dev \
RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
&& rm -rf /var/lib/apt/lists/*
# Install PowerShell
@@ -49,17 +37,18 @@ COPY pyproject.toml ./
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir poetry
COPY src/backend/ ./backend/
ENV PATH="/home/prowler/.local/bin:$PATH"
# Add `--no-root` to avoid installing the current project as a package
RUN poetry install --no-root && \
rm -rf ~/.cache/pip
RUN poetry run python "$(poetry env info --path)/src/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py"
COPY src/backend/ ./backend/
COPY docker-entrypoint.sh ./docker-entrypoint.sh
RUN poetry run python "$(poetry env info --path)/src/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py"
WORKDIR /home/prowler/backend
# Development image

View File

@@ -257,7 +257,7 @@ cd src/backend
python manage.py loaddata api/fixtures/0_dev_users.json --database admin
```
> The default credentials are `dev@prowler.com:Thisisapassword123@` or `dev2@prowler.com:Thisisapassword123@`
> The default credentials are `dev@prowler.com:thisisapassword123` or `dev2@prowler.com:thisisapassword123`
## Run tests

125
api/docker-compose.yml Normal file
View File

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

View File

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

3991
api/poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -7,8 +7,8 @@ authors = [{name = "Prowler Engineering", email = "engineering@prowler.com"}]
dependencies = [
"celery[pytest] (>=5.4.0,<6.0.0)",
"dj-rest-auth[with_social,jwt] (==7.0.1)",
"django==5.1.10",
"django-allauth[saml] (>=65.8.0,<66.0.0)",
"django==5.1.8",
"django-allauth==65.4.1",
"django-celery-beat (>=2.7.0,<3.0.0)",
"django-celery-results (>=2.5.1,<3.0.0)",
"django-cors-headers==4.4.0",
@@ -23,14 +23,11 @@ dependencies = [
"drf-spectacular==0.27.2",
"drf-spectacular-jsonapi==0.5.1",
"gunicorn==23.0.0",
"lxml==5.3.2",
"prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.9",
"prowler @ git+https://github.com/prowler-cloud/prowler.git@master",
"psycopg2-binary==2.9.9",
"pytest-celery[redis] (>=1.0.1,<2.0.0)",
"sentry-sdk[django] (>=2.20.0,<3.0.0)",
"uuid6==2024.7.10",
"openai (>=1.82.0,<2.0.0)",
"xmlsec==1.3.14"
"uuid6==2024.7.10"
]
description = "Prowler's API (Django/DRF)"
license = "Apache-2.0"
@@ -38,7 +35,7 @@ name = "prowler-api"
package-mode = false
# Needed for the SDK compatibility
requires-python = ">=3.11,<3.13"
version = "1.10.2"
version = "1.9.0"
[project.scripts]
celery = "src.backend.config.settings.celery"

View File

@@ -17,8 +17,6 @@ class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
def pre_social_login(self, request, sociallogin):
# Link existing accounts with the same email address
email = sociallogin.account.extra_data.get("email")
if sociallogin.provider.id == "saml":
email = sociallogin.user.email
if email:
existing_user = self.get_user_by_email(email)
if existing_user:
@@ -31,41 +29,33 @@ class ProwlerSocialAccountAdapter(DefaultSocialAccountAdapter):
"""
with transaction.atomic(using=MainRouter.admin_db):
user = super().save_user(request, sociallogin, form)
provider = sociallogin.provider.id
extra = sociallogin.account.extra_data
if provider != "saml":
# Handle other providers (e.g., GitHub, Google)
user.save(using=MainRouter.admin_db)
social_account_name = sociallogin.account.extra_data.get("name")
if social_account_name:
user.name = social_account_name
user.save(using=MainRouter.admin_db)
social_account_name = extra.get("name")
if social_account_name:
user.name = social_account_name
user.save(using=MainRouter.admin_db)
tenant = Tenant.objects.using(MainRouter.admin_db).create(
name=f"{user.email.split('@')[0]} default tenant"
tenant = Tenant.objects.using(MainRouter.admin_db).create(
name=f"{user.email.split('@')[0]} default tenant"
)
with rls_transaction(str(tenant.id)):
Membership.objects.using(MainRouter.admin_db).create(
user=user, tenant=tenant, role=Membership.RoleChoices.OWNER
)
role = Role.objects.using(MainRouter.admin_db).create(
name="admin",
tenant_id=tenant.id,
manage_users=True,
manage_account=True,
manage_billing=True,
manage_providers=True,
manage_integrations=True,
manage_scans=True,
unlimited_visibility=True,
)
UserRoleRelationship.objects.using(MainRouter.admin_db).create(
user=user,
role=role,
tenant_id=tenant.id,
)
with rls_transaction(str(tenant.id)):
Membership.objects.using(MainRouter.admin_db).create(
user=user, tenant=tenant, role=Membership.RoleChoices.OWNER
)
role = Role.objects.using(MainRouter.admin_db).create(
name="admin",
tenant_id=tenant.id,
manage_users=True,
manage_account=True,
manage_billing=True,
manage_providers=True,
manage_integrations=True,
manage_scans=True,
unlimited_visibility=True,
)
UserRoleRelationship.objects.using(MainRouter.admin_db).create(
user=user,
role=role,
tenant_id=tenant.id,
)
else:
request.session["saml_user_created"] = str(user.id)
return user

View File

@@ -190,16 +190,10 @@ def generate_compliance_overview_template(prowler_compliance: dict):
total_checks = len(requirement.Checks)
checks_dict = {check: None for check in requirement.Checks}
req_status_val = "MANUAL" if total_checks == 0 else "PASS"
# Build requirement dictionary
requirement_dict = {
"name": requirement.Name or requirement.Id,
"description": requirement.Description,
"tactics": getattr(requirement, "Tactics", []),
"subtechniques": getattr(requirement, "SubTechniques", []),
"platforms": getattr(requirement, "Platforms", []),
"technique_url": getattr(requirement, "TechniqueURL", ""),
"attributes": [
dict(attribute) for attribute in requirement.Attributes
],
@@ -210,18 +204,20 @@ def generate_compliance_overview_template(prowler_compliance: dict):
"manual": 0,
"total": total_checks,
},
"status": req_status_val,
"status": "PASS",
}
# Update requirements status counts for the framework
if req_status_val == "MANUAL":
# Update requirements status
if total_checks == 0:
requirements_status["manual"] += 1
elif req_status_val == "PASS":
requirements_status["passed"] += 1
# Add requirement to compliance requirements
compliance_requirements[requirement.Id] = requirement_dict
# Calculate pending requirements
pending_requirements = total_requirements - requirements_status["manual"]
requirements_status["passed"] = pending_requirements
# Build compliance dictionary
compliance_dict = {
"framework": compliance_data.Framework,

View File

@@ -1,4 +1,3 @@
import re
import secrets
import uuid
from contextlib import contextmanager
@@ -153,51 +152,6 @@ def delete_related_daily_task(provider_id: str):
PeriodicTask.objects.filter(name=task_name).delete()
def create_objects_in_batches(
tenant_id: str, model, objects: list, batch_size: int = 500
):
"""
Bulk-create model instances in repeated, per-tenant RLS transactions.
All chunks execute in their own transaction, so no single transaction
grows too large.
Args:
tenant_id (str): UUID string of the tenant under which to set RLS.
model: Django model class whose `.objects.bulk_create()` will be called.
objects (list): List of model instances (unsaved) to bulk-create.
batch_size (int): Maximum number of objects per bulk_create call.
"""
total = len(objects)
for i in range(0, total, batch_size):
chunk = objects[i : i + batch_size]
with rls_transaction(value=tenant_id, parameter=POSTGRES_TENANT_VAR):
model.objects.bulk_create(chunk, batch_size)
def update_objects_in_batches(
tenant_id: str, model, objects: list, fields: list, batch_size: int = 500
):
"""
Bulk-update model instances in repeated, per-tenant RLS transactions.
All chunks execute in their own transaction, so no single transaction
grows too large.
Args:
tenant_id (str): UUID string of the tenant under which to set RLS.
model: Django model class whose `.objects.bulk_update()` will be called.
objects (list): List of model instances (saved) to bulk-update.
fields (list): List of field names to update.
batch_size (int): Maximum number of objects per bulk_update call.
"""
total = len(objects)
for start in range(0, total, batch_size):
chunk = objects[start : start + batch_size]
with rls_transaction(value=tenant_id, parameter=POSTGRES_TENANT_VAR):
model.objects.bulk_update(chunk, fields, batch_size)
# Postgres Enums
@@ -273,72 +227,6 @@ def register_enum(apps, schema_editor, enum_class): # noqa: F841
register_adapter(enum_class, enum_adapter)
def _should_create_index_on_partition(
partition_name: str, all_partitions: bool = False
) -> bool:
"""
Determine if we should create an index on this partition.
Args:
partition_name: The name of the partition (e.g., "findings_2025_aug", "findings_default")
all_partitions: If True, create on all partitions. If False, only current/future partitions.
Returns:
bool: True if index should be created on this partition, False otherwise.
"""
if all_partitions:
return True
# Extract date from partition name if it follows the pattern
# Partition names look like: findings_2025_aug, findings_2025_jul, etc.
date_pattern = r"(\d{4})_([a-z]{3})$"
match = re.search(date_pattern, partition_name)
if not match:
# If we can't parse the date, include it to be safe (e.g., default partition)
return True
try:
year_str, month_abbr = match.groups()
year = int(year_str)
# Map month abbreviations to numbers
month_map = {
"jan": 1,
"feb": 2,
"mar": 3,
"apr": 4,
"may": 5,
"jun": 6,
"jul": 7,
"aug": 8,
"sep": 9,
"oct": 10,
"nov": 11,
"dec": 12,
}
month = month_map.get(month_abbr.lower())
if month is None:
# Unknown month abbreviation, include it to be safe
return True
partition_date = datetime(year, month, 1, tzinfo=timezone.utc)
# Get current month start
now = datetime.now(timezone.utc)
current_month_start = now.replace(
day=1, hour=0, minute=0, second=0, microsecond=0
)
# Include current month and future partitions
return partition_date >= current_month_start
except (ValueError, TypeError):
# If date parsing fails, include it to be safe
return True
def create_index_on_partitions(
apps, # noqa: F841
schema_editor,
@@ -347,39 +235,16 @@ def create_index_on_partitions(
columns: str,
method: str = "BTREE",
where: str = "",
all_partitions: bool = True,
):
"""
Create an index on existing partitions of `parent_table`.
Create an index on every existing partition of `parent_table`.
Args:
parent_table: The name of the root table (e.g. "findings").
index_name: A short name for the index (will be prefixed per-partition).
columns: The parenthesized column list, e.g. "tenant_id, scan_id, status".
method: The index method—BTREE, GIN, etc. Defaults to BTREE.
where: Optional WHERE clause (without the leading "WHERE"), e.g. "status = 'FAIL'".
all_partitions: Whether to create indexes on all partitions or just current/future ones.
Defaults to False (current/future only) to avoid maintenance overhead
on old partitions where the index may not be needed.
Examples:
# Create index only on current and future partitions (recommended for new indexes)
create_index_on_partitions(
apps, schema_editor,
parent_table="findings",
index_name="new_performance_idx",
columns="tenant_id, status, severity",
all_partitions=False # Default behavior
)
# Create index on all partitions (use when migrating existing critical indexes)
create_index_on_partitions(
apps, schema_editor,
parent_table="findings",
index_name="critical_existing_idx",
columns="tenant_id, scan_id",
all_partitions=True
)
method: The index method—BTREE, GIN, etc. Defaults to BTREE.
where: Optional WHERE clause (without the leading "WHERE"), e.g. "status = 'FAIL'".
"""
with connection.cursor() as cursor:
cursor.execute(
@@ -394,14 +259,13 @@ def create_index_on_partitions(
where_sql = f" WHERE {where}" if where else ""
for partition in partitions:
if _should_create_index_on_partition(partition, all_partitions):
idx_name = f"{partition.replace('.', '_')}_{index_name}"
sql = (
f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {idx_name} "
f"ON {partition} USING {method} ({columns})"
f"{where_sql};"
)
schema_editor.execute(sql)
idx_name = f"{partition.replace('.', '_')}_{index_name}"
sql = (
f"CREATE INDEX CONCURRENTLY IF NOT EXISTS {idx_name} "
f"ON {partition} USING {method} ({columns})"
f"{where_sql};"
)
schema_editor.execute(sql)
def drop_index_on_partitions(
@@ -415,7 +279,7 @@ def drop_index_on_partitions(
Args:
parent_table: The name of the root table (e.g. "findings").
index_name: The same short name used when creating them.
index_name: The same short name used when creating them.
"""
with connection.cursor() as cursor:
cursor.execute(
@@ -552,15 +416,3 @@ class IntegrationTypeEnum(EnumType):
class IntegrationTypeEnumField(PostgresEnumField):
def __init__(self, *args, **kwargs):
super().__init__("integration_type", *args, **kwargs)
# Postgres enum definition for Processor type
class ProcessorTypeEnum(EnumType):
enum_type_name = "processor_type"
class ProcessorTypeEnumField(PostgresEnumField):
def __init__(self, *args, **kwargs):
super().__init__("processor_type", *args, **kwargs)

View File

@@ -3,7 +3,7 @@ from rest_framework import status
from rest_framework.exceptions import APIException
from rest_framework_json_api.exceptions import exception_handler
from rest_framework_json_api.serializers import ValidationError
from rest_framework_simplejwt.exceptions import InvalidToken, TokenError
from rest_framework_simplejwt.exceptions import TokenError, InvalidToken
class ModelValidationError(ValidationError):
@@ -32,36 +32,6 @@ class InvitationTokenExpiredException(APIException):
default_code = "token_expired"
# Task Management Exceptions (non-HTTP)
class TaskManagementError(Exception):
"""Base exception for task management errors."""
def __init__(self, task=None):
self.task = task
super().__init__()
class TaskFailedException(TaskManagementError):
"""Raised when a task has failed."""
class TaskNotFoundException(TaskManagementError):
"""Raised when a task is not found."""
class TaskInProgressException(TaskManagementError):
"""Raised when a task is running but there's no related Task object to return."""
def __init__(self, task_result=None):
self.task_result = task_result
super().__init__()
# Provider connection errors
class ProviderConnectionError(Exception):
"""Base exception for provider connection errors."""
def custom_exception_handler(exc, context):
if isinstance(exc, django_validation_error):
if hasattr(exc, "error_dict"):
@@ -69,30 +39,7 @@ def custom_exception_handler(exc, context):
else:
exc = ValidationError(detail=exc.messages[0], code=exc.code)
elif isinstance(exc, (TokenError, InvalidToken)):
if (
hasattr(exc, "detail")
and isinstance(exc.detail, dict)
and "messages" in exc.detail
):
exc.detail["messages"] = [
message_item["message"] for message_item in exc.detail["messages"]
]
exc.detail["messages"] = [
message_item["message"] for message_item in exc.detail["messages"]
]
return exception_handler(exc, context)
class ConflictException(APIException):
status_code = status.HTTP_409_CONFLICT
default_detail = "A conflict occurred. The resource already exists."
default_code = "conflict"
def __init__(self, detail=None, code=None, pointer=None):
error_detail = {
"detail": detail or self.default_detail,
"status": self.status_code,
"code": self.default_code,
}
if pointer:
error_detail["source"] = {"pointer": pointer}
super().__init__(detail=[error_detail])

View File

@@ -1,6 +1,5 @@
from datetime import date, datetime, timedelta, timezone
from dateutil.parser import parse
from django.conf import settings
from django.db.models import Q
from django_filters.rest_framework import (
@@ -23,13 +22,12 @@ from api.db_utils import (
StatusEnumField,
)
from api.models import (
ComplianceRequirementOverview,
ComplianceOverview,
Finding,
Integration,
Invitation,
Membership,
PermissionChoices,
Processor,
Provider,
ProviderGroup,
ProviderSecret,
@@ -340,8 +338,6 @@ class ResourceFilter(ProviderRelationshipFilterSet):
tags = CharFilter(method="filter_tag")
inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
scan = UUIDFilter(field_name="provider__scan", lookup_expr="exact")
scan__in = UUIDInFilter(field_name="provider__scan", lookup_expr="in")
class Meta:
model = Resource
@@ -356,82 +352,6 @@ class ResourceFilter(ProviderRelationshipFilterSet):
"updated_at": ["gte", "lte"],
}
def filter_queryset(self, queryset):
if not (self.data.get("scan") or self.data.get("scan__in")) and not (
self.data.get("updated_at")
or self.data.get("updated_at__date")
or self.data.get("updated_at__gte")
or self.data.get("updated_at__lte")
):
raise ValidationError(
[
{
"detail": "At least one date filter is required: filter[updated_at], filter[updated_at.gte], "
"or filter[updated_at.lte].",
"status": 400,
"source": {"pointer": "/data/attributes/updated_at"},
"code": "required",
}
]
)
gte_date = (
parse(self.data.get("updated_at__gte")).date()
if self.data.get("updated_at__gte")
else datetime.now(timezone.utc).date()
)
lte_date = (
parse(self.data.get("updated_at__lte")).date()
if self.data.get("updated_at__lte")
else datetime.now(timezone.utc).date()
)
if abs(lte_date - gte_date) > timedelta(
days=settings.FINDINGS_MAX_DAYS_IN_RANGE
):
raise ValidationError(
[
{
"detail": f"The date range cannot exceed {settings.FINDINGS_MAX_DAYS_IN_RANGE} days.",
"status": 400,
"source": {"pointer": "/data/attributes/updated_at"},
"code": "invalid",
}
]
)
return super().filter_queryset(queryset)
def filter_tag_key(self, queryset, name, value):
return queryset.filter(Q(tags__key=value) | Q(tags__key__icontains=value))
def filter_tag_value(self, queryset, name, value):
return queryset.filter(Q(tags__value=value) | Q(tags__value__icontains=value))
def filter_tag(self, queryset, name, value):
# We won't know what the user wants to filter on just based on the value,
# and we don't want to build special filtering logic for every possible
# provider tag spec, so we'll just do a full text search
return queryset.filter(tags__text_search=value)
class LatestResourceFilter(ProviderRelationshipFilterSet):
tag_key = CharFilter(method="filter_tag_key")
tag_value = CharFilter(method="filter_tag_value")
tag = CharFilter(method="filter_tag")
tags = CharFilter(method="filter_tag")
class Meta:
model = Resource
fields = {
"provider": ["exact", "in"],
"uid": ["exact", "icontains"],
"name": ["exact", "icontains"],
"region": ["exact", "icontains", "in"],
"service": ["exact", "icontains", "in"],
"type": ["exact", "icontains", "in"],
}
def filter_tag_key(self, queryset, name, value):
return queryset.filter(Q(tags__key=value) | Q(tags__key__icontains=value))
@@ -717,11 +637,12 @@ class RoleFilter(FilterSet):
class ComplianceOverviewFilter(FilterSet):
inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
scan_id = UUIDFilter(field_name="scan_id")
region = CharFilter(field_name="region")
provider_type = ChoiceFilter(choices=Provider.ProviderChoices.choices)
provider_type__in = ChoiceInFilter(choices=Provider.ProviderChoices.choices)
scan_id = UUIDFilter(field_name="scan__id")
class Meta:
model = ComplianceRequirementOverview
model = ComplianceOverview
fields = {
"inserted_at": ["date", "gte", "lte"],
"compliance_id": ["exact", "icontains"],
@@ -784,12 +705,3 @@ class IntegrationFilter(FilterSet):
fields = {
"inserted_at": ["date", "gte", "lte"],
}
class ProcessorFilter(FilterSet):
processor_type = ChoiceFilter(choices=Processor.ProcessorChoices.choices)
processor_type__in = ChoiceInFilter(
choices=Processor.ProcessorChoices.choices,
field_name="processor_type",
lookup_expr="in",
)

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,107 +0,0 @@
# Generated by Django 5.1.10 on 2025-06-12 12:45
import uuid
import django.core.validators
import django.db.models.deletion
from django.db import migrations, models
import api.rls
class Migration(migrations.Migration):
dependencies = [
("api", "0029_findings_check_index_parent"),
]
operations = [
migrations.CreateModel(
name="LighthouseConfiguration",
fields=[
(
"id",
models.UUIDField(
default=uuid.uuid4,
editable=False,
primary_key=True,
serialize=False,
),
),
("inserted_at", models.DateTimeField(auto_now_add=True)),
("updated_at", models.DateTimeField(auto_now=True)),
(
"name",
models.CharField(
help_text="Name of the configuration",
max_length=100,
validators=[django.core.validators.MinLengthValidator(3)],
),
),
(
"api_key",
models.BinaryField(
help_text="Encrypted API key for the LLM service"
),
),
(
"model",
models.CharField(
choices=[
("gpt-4o-2024-11-20", "GPT-4o v2024-11-20"),
("gpt-4o-2024-08-06", "GPT-4o v2024-08-06"),
("gpt-4o-2024-05-13", "GPT-4o v2024-05-13"),
("gpt-4o", "GPT-4o Default"),
("gpt-4o-mini-2024-07-18", "GPT-4o Mini v2024-07-18"),
("gpt-4o-mini", "GPT-4o Mini Default"),
],
default="gpt-4o-2024-08-06",
help_text="Must be one of the supported model names",
max_length=50,
),
),
(
"temperature",
models.FloatField(default=0, help_text="Must be between 0 and 1"),
),
(
"max_tokens",
models.IntegerField(
default=4000, help_text="Must be between 500 and 5000"
),
),
(
"business_context",
models.TextField(
blank=True,
default="",
help_text="Additional business context for this AI model configuration",
),
),
("is_active", models.BooleanField(default=True)),
(
"tenant",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
),
),
],
options={
"db_table": "lighthouse_configurations",
"abstract": False,
"constraints": [
models.UniqueConstraint(
fields=("tenant_id",),
name="unique_lighthouse_config_per_tenant",
),
],
},
),
migrations.AddConstraint(
model_name="lighthouseconfiguration",
constraint=api.rls.RowLevelSecurityConstraint(
"tenant_id",
name="rls_on_lighthouseconfiguration",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
),
]

View File

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

View File

@@ -1,150 +0,0 @@
# Generated by Django 5.1.10 on 2025-07-02 15:47
import uuid
import django.db.models.deletion
from django.conf import settings
from django.db import migrations, models
import api.db_utils
import api.rls
class Migration(migrations.Migration):
dependencies = [
("api", "0031_scan_disable_on_cascade_periodic_tasks"),
]
operations = [
migrations.AlterField(
model_name="integration",
name="integration_type",
field=api.db_utils.IntegrationTypeEnumField(
choices=[
("amazon_s3", "Amazon S3"),
("aws_security_hub", "AWS Security Hub"),
("jira", "JIRA"),
("slack", "Slack"),
]
),
),
migrations.CreateModel(
name="SAMLToken",
fields=[
(
"id",
models.UUIDField(
default=uuid.uuid4,
editable=False,
primary_key=True,
serialize=False,
),
),
("inserted_at", models.DateTimeField(auto_now_add=True)),
("updated_at", models.DateTimeField(auto_now=True)),
("expires_at", models.DateTimeField(editable=False)),
("token", models.JSONField(unique=True)),
(
"user",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE,
to=settings.AUTH_USER_MODEL,
),
),
],
options={
"db_table": "saml_tokens",
},
),
migrations.CreateModel(
name="SAMLConfiguration",
fields=[
(
"id",
models.UUIDField(
default=uuid.uuid4,
editable=False,
primary_key=True,
serialize=False,
),
),
(
"email_domain",
models.CharField(
help_text="Email domain used to identify the tenant, e.g. prowlerdemo.com",
max_length=254,
unique=True,
),
),
(
"metadata_xml",
models.TextField(
help_text="Raw IdP metadata XML to configure SingleSignOnService, certificates, etc."
),
),
("created_at", models.DateTimeField(auto_now_add=True)),
("updated_at", models.DateTimeField(auto_now=True)),
(
"tenant",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
),
),
],
options={
"db_table": "saml_configurations",
},
),
migrations.AddConstraint(
model_name="samlconfiguration",
constraint=api.rls.RowLevelSecurityConstraint(
"tenant_id",
name="rls_on_samlconfiguration",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
),
migrations.AddConstraint(
model_name="samlconfiguration",
constraint=models.UniqueConstraint(
fields=("tenant",), name="unique_samlconfig_per_tenant"
),
),
migrations.CreateModel(
name="SAMLDomainIndex",
fields=[
(
"id",
models.BigAutoField(
auto_created=True,
primary_key=True,
serialize=False,
verbose_name="ID",
),
),
("email_domain", models.CharField(max_length=254, unique=True)),
(
"tenant",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
),
),
],
options={
"db_table": "saml_domain_index",
},
),
migrations.AddConstraint(
model_name="samldomainindex",
constraint=models.UniqueConstraint(
fields=("email_domain", "tenant"),
name="unique_resources_by_email_domain",
),
),
migrations.AddConstraint(
model_name="samldomainindex",
constraint=api.rls.BaseSecurityConstraint(
name="statements_on_samldomainindex",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
),
]

View File

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

View File

@@ -1,88 +0,0 @@
# Generated by Django 5.1.5 on 2025-03-26 13:04
import uuid
import django.db.models.deletion
from django.db import migrations, models
import api.db_utils
import api.rls
from api.rls import RowLevelSecurityConstraint
class Migration(migrations.Migration):
dependencies = [
("api", "0033_processors_enum"),
]
operations = [
migrations.CreateModel(
name="Processor",
fields=[
(
"id",
models.UUIDField(
default=uuid.uuid4,
editable=False,
primary_key=True,
serialize=False,
),
),
("inserted_at", models.DateTimeField(auto_now_add=True)),
("updated_at", models.DateTimeField(auto_now=True)),
(
"processor_type",
api.db_utils.ProcessorTypeEnumField(
choices=[("mutelist", "Mutelist")]
),
),
("configuration", models.JSONField(default=dict)),
(
"tenant",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
),
),
],
options={
"db_table": "processors",
"abstract": False,
"indexes": [
models.Index(
fields=["tenant_id", "id"], name="processor_tenant_id_idx"
),
models.Index(
fields=["tenant_id", "processor_type"],
name="processor_tenant_type_idx",
),
],
},
),
migrations.AddConstraint(
model_name="processor",
constraint=models.UniqueConstraint(
fields=("tenant_id", "processor_type"),
name="unique_processor_types_tenant",
),
),
migrations.AddConstraint(
model_name="processor",
constraint=RowLevelSecurityConstraint(
"tenant_id",
name="rls_on_processor",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
),
migrations.AddField(
model_name="scan",
name="processor",
field=models.ForeignKey(
blank=True,
null=True,
on_delete=django.db.models.deletion.SET_NULL,
related_name="scans",
related_query_name="scan",
to="api.processor",
),
),
]

View File

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

View File

@@ -1,30 +0,0 @@
from functools import partial
from django.db import migrations
from api.db_utils import create_index_on_partitions, drop_index_on_partitions
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0035_finding_muted_reason"),
]
operations = [
migrations.RunPython(
partial(
create_index_on_partitions,
parent_table="resource_finding_mappings",
index_name="rfm_tenant_finding_idx",
columns="tenant_id, finding_id",
method="BTREE",
),
reverse_code=partial(
drop_index_on_partitions,
parent_table="resource_finding_mappings",
index_name="rfm_tenant_finding_idx",
),
),
]

View File

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

View File

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

View File

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

View File

@@ -1,30 +0,0 @@
from functools import partial
from django.db import migrations
from api.db_utils import create_index_on_partitions, drop_index_on_partitions
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0039_resource_resources_failed_findings_idx"),
]
operations = [
migrations.RunPython(
partial(
create_index_on_partitions,
parent_table="resource_finding_mappings",
index_name="rfm_tenant_resource_idx",
columns="tenant_id, resource_id",
method="BTREE",
),
reverse_code=partial(
drop_index_on_partitions,
parent_table="resource_finding_mappings",
index_name="rfm_tenant_resource_idx",
),
),
]

View File

@@ -1,17 +0,0 @@
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("api", "0040_rfm_tenant_resource_index_partitions"),
]
operations = [
migrations.AddIndex(
model_name="resourcefindingmapping",
index=models.Index(
fields=["tenant_id", "resource_id"],
name="rfm_tenant_resource_idx",
),
),
]

View File

@@ -1,23 +0,0 @@
from django.contrib.postgres.operations import AddIndexConcurrently
from django.db import migrations, models
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0041_rfm_tenant_resource_parent_partitions"),
("django_celery_beat", "0019_alter_periodictasks_options"),
]
operations = [
AddIndexConcurrently(
model_name="scan",
index=models.Index(
condition=models.Q(("state", "completed")),
fields=["tenant_id", "provider_id", "-inserted_at"],
include=("id",),
name="scans_prov_ins_desc_idx",
),
),
]

View File

@@ -1,21 +1,15 @@
import json
import logging
import re
import xml.etree.ElementTree as ET
from datetime import datetime, timedelta, timezone
import time
from uuid import UUID, uuid4
from allauth.socialaccount.models import SocialApp
from config.custom_logging import BackendLogger
from config.settings.social_login import SOCIALACCOUNT_PROVIDERS
from cryptography.fernet import Fernet, InvalidToken
from config.env import env
from cryptography.fernet import Fernet
from django.conf import settings
from django.contrib.auth.models import AbstractBaseUser
from django.contrib.postgres.fields import ArrayField
from django.contrib.postgres.indexes import GinIndex
from django.contrib.postgres.search import SearchVector, SearchVectorField
from django.contrib.sites.models import Site
from django.core.exceptions import ValidationError
from django.core.validators import MinLengthValidator
from django.db import models
from django.db.models import Q
@@ -27,14 +21,12 @@ from psqlextra.models import PostgresPartitionedModel
from psqlextra.types import PostgresPartitioningMethod
from uuid6 import uuid7
from api.db_router import MainRouter
from api.db_utils import (
CustomUserManager,
FindingDeltaEnumField,
IntegrationTypeEnumField,
InvitationStateEnumField,
MemberRoleEnumField,
ProcessorTypeEnumField,
ProviderEnumField,
ProviderSecretTypeEnumField,
ScanTriggerEnumField,
@@ -59,8 +51,6 @@ fernet = Fernet(settings.SECRETS_ENCRYPTION_KEY.encode())
# Convert Prowler Severity enum to Django TextChoices
SeverityChoices = enum_to_choices(Severity)
logger = logging.getLogger(BackendLogger.API)
class StatusChoices(models.TextChoices):
"""
@@ -364,6 +354,42 @@ class ProviderGroupMembership(RowLevelSecurityProtectedModel):
resource_name = "provider_groups-provider"
class TaskManager(models.Manager):
def get_with_retry(
self,
id: str,
max_retries: int = None,
delay_seconds: float = None,
):
"""
Retry fetching a Task by ID in case it hasn't been created yet.
Args:
id (str): The Celery task ID (expected to match Task model PK).
max_retries (int, optional): Number of retry attempts. Defaults to env TASK_RETRY_ATTEMPTS or 5.
delay_seconds (float, optional): Delay between retries in seconds. Defaults to env TASK_RETRY_DELAY_SECONDS or 0.1.
Returns:
Task: The retrieved Task instance.
Raises:
Task.DoesNotExist: If the task is not found after all retries.
"""
max_retries = max_retries or env.int("TASK_RETRY_ATTEMPTS", default=5)
delay_seconds = delay_seconds or env.float(
"TASK_RETRY_DELAY_SECONDS", default=0.1
)
for _attempt in range(max_retries):
try:
return self.get(id=id)
except self.model.DoesNotExist:
time.sleep(delay_seconds)
raise self.model.DoesNotExist(
f"Task with ID {id} not found after {max_retries} retries."
)
class Task(RowLevelSecurityProtectedModel):
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
@@ -376,6 +402,8 @@ class Task(RowLevelSecurityProtectedModel):
blank=True,
)
objects = TaskManager()
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "tasks"
@@ -410,6 +438,20 @@ class Scan(RowLevelSecurityProtectedModel):
name = models.CharField(
blank=True, null=True, max_length=100, validators=[MinLengthValidator(3)]
)
provider = models.ForeignKey(
Provider,
on_delete=models.CASCADE,
related_name="scans",
related_query_name="scan",
)
task = models.ForeignKey(
Task,
on_delete=models.CASCADE,
related_name="scans",
related_query_name="scan",
null=True,
blank=True,
)
trigger = ScanTriggerEnumField(
choices=TriggerChoices.choices,
)
@@ -425,31 +467,11 @@ class Scan(RowLevelSecurityProtectedModel):
completed_at = models.DateTimeField(null=True, blank=True)
next_scan_at = models.DateTimeField(null=True, blank=True)
scheduler_task = models.ForeignKey(
PeriodicTask, on_delete=models.SET_NULL, null=True, blank=True
PeriodicTask, on_delete=models.CASCADE, null=True, blank=True
)
output_location = models.CharField(blank=True, null=True, max_length=200)
provider = models.ForeignKey(
Provider,
on_delete=models.CASCADE,
related_name="scans",
related_query_name="scan",
)
task = models.ForeignKey(
Task,
on_delete=models.CASCADE,
related_name="scans",
related_query_name="scan",
null=True,
blank=True,
)
processor = models.ForeignKey(
"Processor",
on_delete=models.SET_NULL,
related_name="scans",
related_query_name="scan",
null=True,
blank=True,
)
# TODO: mutelist foreign key
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "scans"
@@ -476,13 +498,6 @@ class Scan(RowLevelSecurityProtectedModel):
condition=Q(state=StateChoices.COMPLETED),
name="scans_prov_state_ins_desc_idx",
),
# TODO This might replace `scans_prov_state_ins_desc_idx` completely. Review usage
models.Index(
fields=["tenant_id", "provider_id", "-inserted_at"],
condition=Q(state=StateChoices.COMPLETED),
include=["id"],
name="scans_prov_ins_desc_idx",
),
]
class JSONAPIMeta:
@@ -568,8 +583,6 @@ class Resource(RowLevelSecurityProtectedModel):
details = models.TextField(blank=True, null=True)
partition = models.TextField(blank=True, null=True)
failed_findings_count = models.IntegerField(default=0)
# Relationships
tags = models.ManyToManyField(
ResourceTag,
@@ -616,10 +629,6 @@ class Resource(RowLevelSecurityProtectedModel):
fields=["tenant_id", "provider_id"],
name="resources_tenant_provider_idx",
),
models.Index(
fields=["tenant_id", "-failed_findings_count", "id"],
name="resources_failed_findings_idx",
),
]
constraints = [
@@ -718,9 +727,6 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
check_id = models.CharField(max_length=100, blank=False, null=False)
check_metadata = models.JSONField(default=dict, null=False)
muted = models.BooleanField(default=False, null=False)
muted_reason = models.TextField(
blank=True, null=True, validators=[MinLengthValidator(3)], max_length=500
)
compliance = models.JSONField(default=dict, null=True, blank=True)
# Denormalize resource data for performance
@@ -796,10 +802,6 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
GinIndex(fields=["resource_services"], name="gin_find_service_idx"),
GinIndex(fields=["resource_regions"], name="gin_find_region_idx"),
GinIndex(fields=["resource_types"], name="gin_find_rtype_idx"),
models.Index(
fields=["tenant_id", "scan_id", "check_id"],
name="find_tenant_scan_check_idx",
),
]
class JSONAPIMeta:
@@ -862,16 +864,6 @@ class ResourceFindingMapping(PostgresPartitionedModel, RowLevelSecurityProtected
# - tenant_id
# - id
indexes = [
models.Index(
fields=["tenant_id", "finding_id"],
name="rfm_tenant_finding_idx",
),
models.Index(
fields=["tenant_id", "resource_id"],
name="rfm_tenant_resource_idx",
),
]
constraints = [
models.UniqueConstraint(
fields=("tenant_id", "resource_id", "finding_id"),
@@ -976,11 +968,6 @@ class Invitation(RowLevelSecurityProtectedModel):
null=True,
)
def save(self, *args, **kwargs):
if self.email:
self.email = self.email.strip().lower()
super().save(*args, **kwargs)
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "invitations"
@@ -1196,78 +1183,6 @@ class ComplianceOverview(RowLevelSecurityProtectedModel):
resource_name = "compliance-overviews"
class ComplianceRequirementOverview(RowLevelSecurityProtectedModel):
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
compliance_id = models.TextField(blank=False)
framework = models.TextField(blank=False)
version = models.TextField(blank=True)
description = models.TextField(blank=True)
region = models.TextField(blank=False)
requirement_id = models.TextField(blank=False)
requirement_status = StatusEnumField(choices=StatusChoices)
passed_checks = models.IntegerField(default=0)
failed_checks = models.IntegerField(default=0)
total_checks = models.IntegerField(default=0)
scan = models.ForeignKey(
Scan,
on_delete=models.CASCADE,
related_name="compliance_requirements_overviews",
related_query_name="compliance_requirements_overview",
)
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "compliance_requirements_overviews"
constraints = [
models.UniqueConstraint(
fields=(
"tenant_id",
"scan_id",
"compliance_id",
"requirement_id",
"region",
),
name="unique_tenant_compliance_requirement_overview",
),
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "DELETE"],
),
]
indexes = [
models.Index(fields=["tenant_id", "scan_id"], name="cro_tenant_scan_idx"),
models.Index(
fields=["tenant_id", "scan_id", "compliance_id"],
name="cro_scan_comp_idx",
),
models.Index(
fields=["tenant_id", "scan_id", "compliance_id", "region"],
name="cro_scan_comp_reg_idx",
),
models.Index(
fields=["tenant_id", "scan_id", "compliance_id", "requirement_id"],
name="cro_scan_comp_req_idx",
),
models.Index(
fields=[
"tenant_id",
"scan_id",
"compliance_id",
"requirement_id",
"region",
],
name="cro_scan_comp_req_reg_idx",
),
]
class JSONAPIMeta:
resource_name = "compliance-requirements-overviews"
class ScanSummary(RowLevelSecurityProtectedModel):
objects = ActiveProviderManager()
all_objects = models.Manager()
@@ -1336,6 +1251,7 @@ class ScanSummary(RowLevelSecurityProtectedModel):
class Integration(RowLevelSecurityProtectedModel):
class IntegrationChoices(models.TextChoices):
S3 = "amazon_s3", _("Amazon S3")
SAML = "saml", _("SAML")
AWS_SECURITY_HUB = "aws_security_hub", _("AWS Security Hub")
JIRA = "jira", _("JIRA")
SLACK = "slack", _("Slack")
@@ -1409,273 +1325,6 @@ class IntegrationProviderRelationship(RowLevelSecurityProtectedModel):
]
class SAMLToken(models.Model):
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
updated_at = models.DateTimeField(auto_now=True, editable=False)
expires_at = models.DateTimeField(editable=False)
token = models.JSONField(unique=True)
user = models.ForeignKey(User, on_delete=models.CASCADE)
class Meta:
db_table = "saml_tokens"
def save(self, *args, **kwargs):
if not self.expires_at:
self.expires_at = datetime.now(timezone.utc) + timedelta(seconds=15)
super().save(*args, **kwargs)
def is_expired(self) -> bool:
return datetime.now(timezone.utc) >= self.expires_at
class SAMLDomainIndex(models.Model):
"""
Public index of SAML domains. No RLS. Used for fast lookup in SAML login flow.
"""
email_domain = models.CharField(max_length=254, unique=True)
tenant = models.ForeignKey("Tenant", on_delete=models.CASCADE)
class Meta:
db_table = "saml_domain_index"
constraints = [
models.UniqueConstraint(
fields=("email_domain", "tenant"),
name="unique_resources_by_email_domain",
),
BaseSecurityConstraint(
name="statements_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]
class SAMLConfiguration(RowLevelSecurityProtectedModel):
"""
Stores per-tenant SAML settings, including email domain and IdP metadata.
Automatically syncs to a SocialApp instance on save.
Note:
This model exists to provide a tenant-aware abstraction over SAML configuration.
It supports row-level security, custom validation, and metadata parsing, enabling
Prowler to expose a clean API and admin interface for managing SAML integrations.
Although Django Allauth uses the SocialApp model to store provider configuration,
it is not designed for multi-tenant use. SocialApp lacks support for tenant scoping,
email domain mapping, and structured metadata handling.
By managing SAMLConfiguration separately, we ensure:
- Strong isolation between tenants via RLS.
- Ownership of raw IdP metadata and its validation.
- An explicit link between SAML config and business-level identifiers (e.g. email domain).
- Programmatic transformation into the SocialApp format used by Allauth.
In short, this model acts as a secure and user-friendly layer over Allauth's lower-level primitives.
"""
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
email_domain = models.CharField(
max_length=254,
unique=True,
help_text="Email domain used to identify the tenant, e.g. prowlerdemo.com",
)
metadata_xml = models.TextField(
help_text="Raw IdP metadata XML to configure SingleSignOnService, certificates, etc."
)
created_at = models.DateTimeField(auto_now_add=True)
updated_at = models.DateTimeField(auto_now=True)
class JSONAPIMeta:
resource_name = "saml-configurations"
class Meta:
db_table = "saml_configurations"
constraints = [
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
# 1 config per tenant
models.UniqueConstraint(
fields=["tenant"],
name="unique_samlconfig_per_tenant",
),
]
def clean(self, old_email_domain=None, is_create=False):
# Domain must not contain @
if "@" in self.email_domain:
raise ValidationError({"email_domain": "Domain must not contain @"})
# Enforce at most one config per tenant
qs = SAMLConfiguration.objects.filter(tenant=self.tenant)
# Exclude ourselves in case of update
if self.pk:
qs = qs.exclude(pk=self.pk)
if qs.exists():
raise ValidationError(
{"tenant": "A SAML configuration already exists for this tenant."}
)
# The email domain must be unique in the entire system
qs = SAMLConfiguration.objects.using(MainRouter.admin_db).filter(
email_domain__iexact=self.email_domain
)
if qs.exists() and old_email_domain != self.email_domain:
raise ValidationError(
{"tenant": "There is a problem with your email domain."}
)
# The entityID must be unique in the system
idp_settings = self._parsed_metadata
entity_id = idp_settings.get("entity_id")
if entity_id:
# Find any SocialApp with this entityID
q = SocialApp.objects.filter(provider="saml", provider_id=entity_id)
# If updating, exclude our own SocialApp from the check
if not is_create:
q = q.exclude(client_id=old_email_domain)
else:
q = q.exclude(client_id=self.email_domain)
if q.exists():
raise ValidationError(
{"metadata_xml": "There is a problem with your metadata."}
)
def save(self, *args, **kwargs):
self.email_domain = self.email_domain.strip().lower()
is_create = not SAMLConfiguration.objects.filter(pk=self.pk).exists()
if not is_create:
old = SAMLConfiguration.objects.get(pk=self.pk)
old_email_domain = old.email_domain
old_metadata_xml = old.metadata_xml
else:
old_email_domain = None
old_metadata_xml = None
self._parsed_metadata = self._parse_metadata()
self.clean(old_email_domain, is_create)
super().save(*args, **kwargs)
if is_create or (
old_email_domain != self.email_domain
or old_metadata_xml != self.metadata_xml
):
self._sync_social_app(old_email_domain)
# Sync the public index
if not is_create and old_email_domain and old_email_domain != self.email_domain:
SAMLDomainIndex.objects.filter(email_domain=old_email_domain).delete()
# Create/update the new domain index
SAMLDomainIndex.objects.update_or_create(
email_domain=self.email_domain, defaults={"tenant": self.tenant}
)
def delete(self, *args, **kwargs):
super().delete(*args, **kwargs)
SocialApp.objects.filter(provider="saml", client_id=self.email_domain).delete()
SAMLDomainIndex.objects.filter(email_domain=self.email_domain).delete()
def _parse_metadata(self):
"""
Parse the raw IdP metadata XML and extract:
- entity_id
- sso_url
- slo_url (may be None)
- x509cert (required)
"""
ns = {
"md": "urn:oasis:names:tc:SAML:2.0:metadata",
"ds": "http://www.w3.org/2000/09/xmldsig#",
}
try:
root = ET.fromstring(self.metadata_xml)
except ET.ParseError as e:
raise ValidationError({"metadata_xml": f"Invalid XML: {e}"})
# Entity ID
entity_id = root.attrib.get("entityID")
if not entity_id:
raise ValidationError({"metadata_xml": "Missing entityID in metadata."})
# SSO endpoint (must exist)
sso = root.find(".//md:IDPSSODescriptor/md:SingleSignOnService", ns)
if sso is None or "Location" not in sso.attrib:
raise ValidationError(
{"metadata_xml": "Missing SingleSignOnService in metadata."}
)
sso_url = sso.attrib["Location"]
# SLO endpoint (optional)
slo = root.find(".//md:IDPSSODescriptor/md:SingleLogoutService", ns)
slo_url = slo.attrib.get("Location") if slo is not None else None
# X.509 certificate (required)
cert = root.find(
'.//md:KeyDescriptor[@use="signing"]/ds:KeyInfo/ds:X509Data/ds:X509Certificate',
ns,
)
if cert is None or not cert.text or not cert.text.strip():
raise ValidationError(
{
"metadata_xml": 'Metadata must include a <ds:X509Certificate> under <KeyDescriptor use="signing">.'
}
)
x509cert = cert.text.strip()
return {
"entity_id": entity_id,
"sso_url": sso_url,
"slo_url": slo_url,
"x509cert": x509cert,
}
def _sync_social_app(self, previous_email_domain=None):
"""
Create or update the corresponding SocialApp based on email_domain.
If the domain changed, update the matching SocialApp.
"""
settings_dict = SOCIALACCOUNT_PROVIDERS["saml"].copy()
settings_dict["idp"] = self._parsed_metadata
current_site = Site.objects.get(id=settings.SITE_ID)
social_app_qs = SocialApp.objects.filter(
provider="saml", client_id=previous_email_domain or self.email_domain
)
client_id = self.email_domain[:191]
name = f"SAML-{self.email_domain}"[:40]
if social_app_qs.exists():
social_app = social_app_qs.first()
social_app.client_id = client_id
social_app.name = name
social_app.settings = settings_dict
social_app.provider_id = self._parsed_metadata["entity_id"]
social_app.save()
social_app.sites.set([current_site])
else:
social_app = SocialApp.objects.create(
provider="saml",
client_id=client_id,
name=name,
settings=settings_dict,
provider_id=self._parsed_metadata["entity_id"],
)
social_app.sites.set([current_site])
class ResourceScanSummary(RowLevelSecurityProtectedModel):
scan_id = models.UUIDField(default=uuid7, db_index=True)
resource_id = models.UUIDField(default=uuid4, db_index=True)
@@ -1723,169 +1372,3 @@ class ResourceScanSummary(RowLevelSecurityProtectedModel):
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]
class LighthouseConfiguration(RowLevelSecurityProtectedModel):
"""
Stores configuration and API keys for LLM services.
"""
class ModelChoices(models.TextChoices):
GPT_4O_2024_11_20 = "gpt-4o-2024-11-20", _("GPT-4o v2024-11-20")
GPT_4O_2024_08_06 = "gpt-4o-2024-08-06", _("GPT-4o v2024-08-06")
GPT_4O_2024_05_13 = "gpt-4o-2024-05-13", _("GPT-4o v2024-05-13")
GPT_4O = "gpt-4o", _("GPT-4o Default")
GPT_4O_MINI_2024_07_18 = "gpt-4o-mini-2024-07-18", _("GPT-4o Mini v2024-07-18")
GPT_4O_MINI = "gpt-4o-mini", _("GPT-4o Mini Default")
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
updated_at = models.DateTimeField(auto_now=True, editable=False)
name = models.CharField(
max_length=100,
validators=[MinLengthValidator(3)],
blank=False,
null=False,
help_text="Name of the configuration",
)
api_key = models.BinaryField(
blank=False, null=False, help_text="Encrypted API key for the LLM service"
)
model = models.CharField(
max_length=50,
choices=ModelChoices.choices,
blank=False,
null=False,
default=ModelChoices.GPT_4O_2024_08_06,
help_text="Must be one of the supported model names",
)
temperature = models.FloatField(default=0, help_text="Must be between 0 and 1")
max_tokens = models.IntegerField(
default=4000, help_text="Must be between 500 and 5000"
)
business_context = models.TextField(
blank=True,
null=False,
default="",
help_text="Additional business context for this AI model configuration",
)
is_active = models.BooleanField(default=True)
def __str__(self):
return self.name
def clean(self):
super().clean()
# Validate temperature
if not 0 <= self.temperature <= 1:
raise ModelValidationError(
detail="Temperature must be between 0 and 1",
code="invalid_temperature",
pointer="/data/attributes/temperature",
)
# Validate max_tokens
if not 500 <= self.max_tokens <= 5000:
raise ModelValidationError(
detail="Max tokens must be between 500 and 5000",
code="invalid_max_tokens",
pointer="/data/attributes/max_tokens",
)
@property
def api_key_decoded(self):
"""Return the decrypted API key, or None if unavailable or invalid."""
if not self.api_key:
return None
try:
decrypted_key = fernet.decrypt(bytes(self.api_key))
return decrypted_key.decode()
except InvalidToken:
logger.warning("Invalid token while decrypting API key.")
except Exception as e:
logger.exception("Unexpected error while decrypting API key: %s", e)
@api_key_decoded.setter
def api_key_decoded(self, value):
"""Store the encrypted API key."""
if not value:
raise ModelValidationError(
detail="API key is required",
code="invalid_api_key",
pointer="/data/attributes/api_key",
)
# Validate OpenAI API key format
openai_key_pattern = r"^sk-[\w-]+T3BlbkFJ[\w-]+$"
if not re.match(openai_key_pattern, value):
raise ModelValidationError(
detail="Invalid OpenAI API key format.",
code="invalid_api_key",
pointer="/data/attributes/api_key",
)
self.api_key = fernet.encrypt(value.encode())
def save(self, *args, **kwargs):
self.full_clean()
super().save(*args, **kwargs)
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "lighthouse_configurations"
constraints = [
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
# Add unique constraint for name within a tenant
models.UniqueConstraint(
fields=["tenant_id"], name="unique_lighthouse_config_per_tenant"
),
]
class JSONAPIMeta:
resource_name = "lighthouse-configurations"
class Processor(RowLevelSecurityProtectedModel):
class ProcessorChoices(models.TextChoices):
MUTELIST = "mutelist", _("Mutelist")
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
updated_at = models.DateTimeField(auto_now=True, editable=False)
processor_type = ProcessorTypeEnumField(choices=ProcessorChoices.choices)
configuration = models.JSONField(default=dict)
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "processors"
constraints = [
models.UniqueConstraint(
fields=("tenant_id", "processor_type"),
name="unique_processor_types_tenant",
),
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]
indexes = [
models.Index(
fields=["tenant_id", "id"],
name="processor_tenant_id_idx",
),
models.Index(
fields=["tenant_id", "processor_type"],
name="processor_tenant_type_idx",
),
]
class JSONAPIMeta:
resource_name = "processors"

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

@@ -1,77 +0,0 @@
from unittest.mock import MagicMock, patch
import pytest
from allauth.socialaccount.models import SocialLogin
from django.contrib.auth import get_user_model
from api.adapters import ProwlerSocialAccountAdapter
User = get_user_model()
@pytest.mark.django_db
class TestProwlerSocialAccountAdapter:
def test_get_user_by_email_returns_user(self, create_test_user):
adapter = ProwlerSocialAccountAdapter()
user = adapter.get_user_by_email(create_test_user.email)
assert user == create_test_user
def test_get_user_by_email_returns_none_for_unknown_email(self):
adapter = ProwlerSocialAccountAdapter()
assert adapter.get_user_by_email("notfound@example.com") is None
def test_pre_social_login_links_existing_user(self, create_test_user, rf):
adapter = ProwlerSocialAccountAdapter()
sociallogin = MagicMock(spec=SocialLogin)
sociallogin.account = MagicMock()
sociallogin.provider = MagicMock()
sociallogin.provider.id = "saml"
sociallogin.account.extra_data = {}
sociallogin.user = create_test_user
sociallogin.connect = MagicMock()
adapter.pre_social_login(rf.get("/"), sociallogin)
call_args = sociallogin.connect.call_args
assert call_args is not None
called_request, called_user = call_args[0]
assert called_request.path == "/"
assert called_user.email == create_test_user.email
def test_pre_social_login_no_link_if_email_missing(self, rf):
adapter = ProwlerSocialAccountAdapter()
sociallogin = MagicMock(spec=SocialLogin)
sociallogin.account = MagicMock()
sociallogin.provider = MagicMock()
sociallogin.user = MagicMock()
sociallogin.provider.id = "saml"
sociallogin.account.extra_data = {}
sociallogin.connect = MagicMock()
adapter.pre_social_login(rf.get("/"), sociallogin)
sociallogin.connect.assert_not_called()
def test_save_user_saml_sets_session_flag(self, rf):
adapter = ProwlerSocialAccountAdapter()
request = rf.get("/")
request.session = {}
sociallogin = MagicMock(spec=SocialLogin)
sociallogin.provider = MagicMock()
sociallogin.provider.id = "saml"
sociallogin.account = MagicMock()
sociallogin.account.extra_data = {}
mock_user = MagicMock()
mock_user.id = 123
with patch("api.adapters.super") as mock_super:
with patch("api.adapters.transaction"):
with patch("api.adapters.MainRouter"):
mock_super.return_value.save_user.return_value = mock_user
adapter.save_user(request, sociallogin)
assert request.session["saml_user_created"] == "123"

View File

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

View File

@@ -3,17 +3,12 @@ from enum import Enum
from unittest.mock import patch
import pytest
from django.conf import settings
from freezegun import freeze_time
from api.db_utils import (
_should_create_index_on_partition,
batch_delete,
create_objects_in_batches,
enum_to_choices,
generate_random_token,
one_week_from_now,
update_objects_in_batches,
)
from api.models import Provider
@@ -143,173 +138,3 @@ class TestBatchDelete:
)
assert Provider.objects.all().count() == 0
assert summary == {"api.Provider": create_test_providers}
class TestShouldCreateIndexOnPartition:
@freeze_time("2025-05-15 00:00:00Z")
@pytest.mark.parametrize(
"partition_name, all_partitions, expected",
[
("any_name", True, True),
("findings_default", True, True),
("findings_2022_jan", True, True),
("foo_bar", False, True),
("findings_2025_MAY", False, True),
("findings_2025_may", False, True),
("findings_2025_jun", False, True),
("findings_2025_apr", False, False),
("findings_2025_xyz", False, True),
],
)
def test_partition_inclusion_logic(self, partition_name, all_partitions, expected):
assert (
_should_create_index_on_partition(partition_name, all_partitions)
is expected
)
@freeze_time("2025-05-15 00:00:00Z")
def test_invalid_date_components(self):
# even if regex matches but int conversion fails, we fallback True
# (e.g. year too big, month number parse error)
bad_name = "findings_99999_jan"
assert _should_create_index_on_partition(bad_name, False) is True
bad_name2 = "findings_2025_abc"
# abc not in month_map → fallback True
assert _should_create_index_on_partition(bad_name2, False) is True
@pytest.mark.django_db
class TestCreateObjectsInBatches:
@pytest.fixture
def tenant(self, tenants_fixture):
return tenants_fixture[0]
def make_provider_instances(self, tenant, count):
"""
Return a list of `count` unsaved Provider instances for the given tenant.
"""
base_uid = 1000
return [
Provider(
tenant=tenant,
uid=str(base_uid + i),
provider=Provider.ProviderChoices.AWS,
)
for i in range(count)
]
def test_exact_multiple_of_batch(self, tenant):
total = 6
batch_size = 3
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
qs = Provider.objects.filter(tenant=tenant)
assert qs.count() == total
def test_non_multiple_of_batch(self, tenant):
total = 7
batch_size = 3
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
qs = Provider.objects.filter(tenant=tenant)
assert qs.count() == total
def test_batch_size_default(self, tenant):
default_size = settings.DJANGO_DELETION_BATCH_SIZE
total = default_size + 2
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs)
qs = Provider.objects.filter(tenant=tenant)
assert qs.count() == total
@pytest.mark.django_db
class TestUpdateObjectsInBatches:
@pytest.fixture
def tenant(self, tenants_fixture):
return tenants_fixture[0]
def make_provider_instances(self, tenant, count):
"""
Return a list of `count` unsaved Provider instances for the given tenant.
"""
base_uid = 2000
return [
Provider(
tenant=tenant,
uid=str(base_uid + i),
provider=Provider.ProviderChoices.AWS,
)
for i in range(count)
]
def test_exact_multiple_of_batch(self, tenant):
total = 6
batch_size = 3
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
# Fetch them back, mutate the `uid` field, then update in batches
providers = list(Provider.objects.filter(tenant=tenant))
for p in providers:
p.uid = f"{p.uid}_upd"
update_objects_in_batches(
tenant_id=str(tenant.id),
model=Provider,
objects=providers,
fields=["uid"],
batch_size=batch_size,
)
qs = Provider.objects.filter(tenant=tenant, uid__endswith="_upd")
assert qs.count() == total
def test_non_multiple_of_batch(self, tenant):
total = 7
batch_size = 3
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs, batch_size=batch_size)
providers = list(Provider.objects.filter(tenant=tenant))
for p in providers:
p.uid = f"{p.uid}_upd"
update_objects_in_batches(
tenant_id=str(tenant.id),
model=Provider,
objects=providers,
fields=["uid"],
batch_size=batch_size,
)
qs = Provider.objects.filter(tenant=tenant, uid__endswith="_upd")
assert qs.count() == total
def test_batch_size_default(self, tenant):
default_size = settings.DJANGO_DELETION_BATCH_SIZE
total = default_size + 2
objs = self.make_provider_instances(tenant, total)
create_objects_in_batches(str(tenant.id), Provider, objs)
providers = list(Provider.objects.filter(tenant=tenant))
for p in providers:
p.uid = f"{p.uid}_upd"
# Update without specifying batch_size (uses default)
update_objects_in_batches(
tenant_id=str(tenant.id),
model=Provider,
objects=providers,
fields=["uid"],
)
qs = Provider.objects.filter(tenant=tenant, uid__endswith="_upd")
assert qs.count() == total

View File

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

View File

@@ -1,9 +1,9 @@
import pytest
from allauth.socialaccount.models import SocialApp
from django.core.exceptions import ValidationError
import uuid
from unittest import mock
from api.db_router import MainRouter
from api.models import Resource, ResourceTag, SAMLConfiguration, SAMLDomainIndex
import pytest
from api.models import Resource, ResourceTag, Task
@pytest.mark.django_db
@@ -126,201 +126,32 @@ class TestResourceModel:
@pytest.mark.django_db
class TestSAMLConfigurationModel:
VALID_METADATA = """<?xml version='1.0' encoding='UTF-8'?>
<md:EntityDescriptor entityID='TEST' xmlns:md='urn:oasis:names:tc:SAML:2.0:metadata'>
<md:IDPSSODescriptor WantAuthnRequestsSigned='false' protocolSupportEnumeration='urn:oasis:names:tc:SAML:2.0:protocol'>
<md:KeyDescriptor use='signing'>
<ds:KeyInfo xmlns:ds='http://www.w3.org/2000/09/xmldsig#'>
<ds:X509Data>
<ds:X509Certificate>FAKECERTDATA</ds:X509Certificate>
</ds:X509Data>
</ds:KeyInfo>
</md:KeyDescriptor>
<md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-POST' Location='https://idp.test/sso'/>
</md:IDPSSODescriptor>
</md:EntityDescriptor>
"""
class TestTaskManager:
def test_get_with_retry_success(self):
task_id = uuid.uuid4()
call_counter = {"count": 0}
def test_creates_valid_configuration(self, tenants_fixture):
tenant = tenants_fixture[0]
config = SAMLConfiguration.objects.using(MainRouter.admin_db).create(
email_domain="ssoexample.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant,
)
def side_effect(*args, **kwargs):
if call_counter["count"] < 2:
call_counter["count"] += 1
raise Task.DoesNotExist()
return Task(id=task_id)
assert config.email_domain == "ssoexample.com"
assert SocialApp.objects.filter(client_id="ssoexample.com").exists()
with mock.patch.object(Task.objects, "get", side_effect=side_effect):
task = Task.objects.get_with_retry(
task_id, max_retries=5, delay_seconds=0.01
)
def test_email_domain_with_at_symbol_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
config = SAMLConfiguration(
email_domain="invalid@domain.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant,
)
assert task.id == task_id
assert call_counter["count"] == 2
with pytest.raises(ValidationError) as exc_info:
config.clean()
def test_get_with_retry_fail(self):
non_existent_id = uuid.uuid4()
errors = exc_info.value.message_dict
assert "email_domain" in errors
assert "Domain must not contain @" in errors["email_domain"][0]
with mock.patch.object(Task.objects, "get", side_effect=Task.DoesNotExist):
with pytest.raises(Task.DoesNotExist) as excinfo:
Task.objects.get_with_retry(
non_existent_id, max_retries=3, delay_seconds=0.01
)
def test_duplicate_email_domain_fails(self, tenants_fixture):
tenant1, tenant2, *_ = tenants_fixture
SAMLConfiguration.objects.using(MainRouter.admin_db).create(
email_domain="duplicate.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant1,
)
config = SAMLConfiguration(
email_domain="duplicate.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant2,
)
with pytest.raises(ValidationError) as exc_info:
config.clean()
errors = exc_info.value.message_dict
assert "tenant" in errors
assert "There is a problem with your email domain." in errors["tenant"][0]
def test_duplicate_tenant_config_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
SAMLConfiguration.objects.using(MainRouter.admin_db).create(
email_domain="unique1.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant,
)
config = SAMLConfiguration(
email_domain="unique2.com",
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant,
)
with pytest.raises(ValidationError) as exc_info:
config.clean()
errors = exc_info.value.message_dict
assert "tenant" in errors
assert (
"A SAML configuration already exists for this tenant."
in errors["tenant"][0]
)
def test_invalid_metadata_xml_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
config = SAMLConfiguration(
email_domain="brokenxml.com",
metadata_xml="<bad<xml>",
tenant=tenant,
)
with pytest.raises(ValidationError) as exc_info:
config._parse_metadata()
errors = exc_info.value.message_dict
assert "metadata_xml" in errors
assert "Invalid XML" in errors["metadata_xml"][0]
assert "not well-formed" in errors["metadata_xml"][0]
def test_metadata_missing_sso_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
xml = """<md:EntityDescriptor entityID="x" xmlns:md="urn:oasis:names:tc:SAML:2.0:metadata">
<md:IDPSSODescriptor></md:IDPSSODescriptor>
</md:EntityDescriptor>"""
config = SAMLConfiguration(
email_domain="nosso.com",
metadata_xml=xml,
tenant=tenant,
)
with pytest.raises(ValidationError) as exc_info:
config._parse_metadata()
errors = exc_info.value.message_dict
assert "metadata_xml" in errors
assert "Missing SingleSignOnService" in errors["metadata_xml"][0]
def test_metadata_missing_certificate_fails(self, tenants_fixture):
tenant = tenants_fixture[0]
xml = """<md:EntityDescriptor entityID="x" xmlns:md="urn:oasis:names:tc:SAML:2.0:metadata">
<md:IDPSSODescriptor>
<md:SingleSignOnService Binding="urn:oasis:names:tc:SAML:2.0:bindings:HTTP-Redirect" Location="https://example.com/sso"/>
</md:IDPSSODescriptor>
</md:EntityDescriptor>"""
config = SAMLConfiguration(
email_domain="nocert.com",
metadata_xml=xml,
tenant=tenant,
)
with pytest.raises(ValidationError) as exc_info:
config._parse_metadata()
errors = exc_info.value.message_dict
assert "metadata_xml" in errors
assert "X509Certificate" in errors["metadata_xml"][0]
def test_deletes_saml_configuration_and_related_objects(self, tenants_fixture):
tenant = tenants_fixture[0]
email_domain = "deleteme.com"
# Create the configuration
config = SAMLConfiguration.objects.using(MainRouter.admin_db).create(
email_domain=email_domain,
metadata_xml=TestSAMLConfigurationModel.VALID_METADATA,
tenant=tenant,
)
# Verify that the SocialApp and SAMLDomainIndex exist
assert SocialApp.objects.filter(client_id=email_domain).exists()
assert (
SAMLDomainIndex.objects.using(MainRouter.admin_db)
.filter(email_domain=email_domain)
.exists()
)
# Delete the configuration
config.delete()
# Verify that the configuration and its related objects are deleted
assert (
not SAMLConfiguration.objects.using(MainRouter.admin_db)
.filter(pk=config.pk)
.exists()
)
assert not SocialApp.objects.filter(client_id=email_domain).exists()
assert (
not SAMLDomainIndex.objects.using(MainRouter.admin_db)
.filter(email_domain=email_domain)
.exists()
)
def test_duplicate_entity_id_fails_on_creation(self, tenants_fixture):
tenant1, tenant2, *_ = tenants_fixture
SAMLConfiguration.objects.using(MainRouter.admin_db).create(
email_domain="first.com",
metadata_xml=self.VALID_METADATA,
tenant=tenant1,
)
config = SAMLConfiguration(
email_domain="second.com",
metadata_xml=self.VALID_METADATA,
tenant=tenant2,
)
with pytest.raises(ValidationError) as exc_info:
config.save()
errors = exc_info.value.message_dict
assert "metadata_xml" in errors
assert "There is a problem with your metadata." in errors["metadata_xml"][0]
assert str(non_existent_id) in str(excinfo.value)

View File

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

View File

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

View File

@@ -131,21 +131,6 @@ class TestInitializeProwlerProvider:
initialize_prowler_provider(provider)
mock_return_prowler_provider.return_value.assert_called_once_with(key="value")
@patch("api.utils.return_prowler_provider")
def test_initialize_prowler_provider_with_mutelist(
self, mock_return_prowler_provider
):
provider = MagicMock()
provider.secret.secret = {"key": "value"}
mutelist_processor = MagicMock()
mutelist_processor.configuration = {"Mutelist": {"key": "value"}}
mock_return_prowler_provider.return_value = MagicMock()
initialize_prowler_provider(provider, mutelist_processor)
mock_return_prowler_provider.return_value.assert_called_once_with(
key="value", mutelist_content={"key": "value"}
)
class TestProwlerProviderConnectionTest:
@patch("api.utils.return_prowler_provider")
@@ -215,25 +200,6 @@ class TestGetProwlerProviderKwargs:
expected_result = {**secret_dict, **expected_extra_kwargs}
assert result == expected_result
def test_get_prowler_provider_kwargs_with_mutelist(self):
provider_uid = "provider_uid"
secret_dict = {"key": "value"}
secret_mock = MagicMock()
secret_mock.secret = secret_dict
mutelist_processor = MagicMock()
mutelist_processor.configuration = {"Mutelist": {"key": "value"}}
provider = MagicMock()
provider.provider = Provider.ProviderChoices.AWS.value
provider.secret = secret_mock
provider.uid = provider_uid
result = get_prowler_provider_kwargs(provider, mutelist_processor)
expected_result = {**secret_dict, "mutelist_content": {"key": "value"}}
assert result == expected_result
def test_get_prowler_provider_kwargs_unsupported_provider(self):
# Setup
provider_uid = "provider_uid"
@@ -288,7 +254,7 @@ class TestValidateInvitation:
assert result == invitation
mock_db.get.assert_called_once_with(
token="VALID_TOKEN", email__iexact="user@example.com"
token="VALID_TOKEN", email="user@example.com"
)
def test_invitation_not_found_raises_validation_error(self):
@@ -303,7 +269,7 @@ class TestValidateInvitation:
"invitation_token": "Invalid invitation code."
}
mock_db.get.assert_called_once_with(
token="INVALID_TOKEN", email__iexact="user@example.com"
token="INVALID_TOKEN", email="user@example.com"
)
def test_invitation_not_found_raises_not_found(self):
@@ -318,7 +284,7 @@ class TestValidateInvitation:
assert exc_info.value.detail == "Invitation is not valid."
mock_db.get.assert_called_once_with(
token="INVALID_TOKEN", email__iexact="user@example.com"
token="INVALID_TOKEN", email="user@example.com"
)
def test_invitation_expired(self, invitation):
@@ -366,27 +332,5 @@ class TestValidateInvitation:
"invitation_token": "Invalid invitation code."
}
mock_db.get.assert_called_once_with(
token="VALID_TOKEN", email__iexact="different@example.com"
)
def test_valid_invitation_uppercase_email(self):
"""Test that validate_invitation works with case-insensitive email lookup."""
uppercase_email = "USER@example.com"
invitation = MagicMock(spec=Invitation)
invitation.token = "VALID_TOKEN"
invitation.email = uppercase_email
invitation.expires_at = datetime.now(timezone.utc) + timedelta(days=1)
invitation.state = Invitation.State.PENDING
invitation.tenant = MagicMock()
with patch("api.utils.Invitation.objects.using") as mock_using:
mock_db = mock_using.return_value
mock_db.get.return_value = invitation
result = validate_invitation("VALID_TOKEN", "user@example.com")
assert result == invitation
mock_db.get.assert_called_once_with(
token="VALID_TOKEN", email__iexact="user@example.com"
token="VALID_TOKEN", email="different@example.com"
)

File diff suppressed because it is too large Load Diff

View File

@@ -7,7 +7,7 @@ from rest_framework.exceptions import NotFound, ValidationError
from api.db_router import MainRouter
from api.exceptions import InvitationTokenExpiredException
from api.models import Invitation, Processor, Provider, Resource
from api.models import Invitation, Provider, Resource
from api.v1.serializers import FindingMetadataSerializer
from prowler.providers.aws.aws_provider import AwsProvider
from prowler.providers.azure.azure_provider import AzureProvider
@@ -83,14 +83,11 @@ def return_prowler_provider(
return prowler_provider
def get_prowler_provider_kwargs(
provider: Provider, mutelist_processor: Processor | None = None
) -> dict:
def get_prowler_provider_kwargs(provider: Provider) -> dict:
"""Get the Prowler provider kwargs based on the given provider type.
Args:
provider (Provider): The provider object containing the provider type and associated secret.
mutelist_processor (Processor): The mutelist processor object containing the mutelist configuration.
Returns:
dict: The provider kwargs for the corresponding provider class.
@@ -108,24 +105,16 @@ def get_prowler_provider_kwargs(
}
elif provider.provider == Provider.ProviderChoices.KUBERNETES.value:
prowler_provider_kwargs = {**prowler_provider_kwargs, "context": provider.uid}
if mutelist_processor:
mutelist_content = mutelist_processor.configuration.get("Mutelist", {})
if mutelist_content:
prowler_provider_kwargs["mutelist_content"] = mutelist_content
return prowler_provider_kwargs
def initialize_prowler_provider(
provider: Provider,
mutelist_processor: Processor | None = None,
) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider:
"""Initialize a Prowler provider instance based on the given provider type.
Args:
provider (Provider): The provider object containing the provider type and associated secrets.
mutelist_processor (Processor): The mutelist processor object containing the mutelist configuration.
Returns:
AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: An instance of the corresponding provider class
@@ -133,7 +122,7 @@ def initialize_prowler_provider(
provider's secrets.
"""
prowler_provider = return_prowler_provider(provider)
prowler_provider_kwargs = get_prowler_provider_kwargs(provider, mutelist_processor)
prowler_provider_kwargs = get_prowler_provider_kwargs(provider)
return prowler_provider(**prowler_provider_kwargs)
@@ -198,7 +187,7 @@ def validate_invitation(
# Admin DB connector is used to bypass RLS protection since the invitation belongs to a tenant the user
# is not a member of yet
invitation = Invitation.objects.using(MainRouter.admin_db).get(
token=invitation_token, email__iexact=email
token=invitation_token, email=email
)
except Invitation.DoesNotExist:
if raise_not_found:

View File

@@ -1,16 +1,5 @@
from django.urls import reverse
from django_celery_results.models import TaskResult
from rest_framework import status
from rest_framework.response import Response
from api.exceptions import (
TaskFailedException,
TaskInProgressException,
TaskNotFoundException,
)
from api.models import StateChoices, Task
from api.v1.serializers import TaskSerializer
class PaginateByPkMixin:
"""
@@ -24,211 +13,21 @@ class PaginateByPkMixin:
request, # noqa: F841
base_queryset,
manager,
select_related: list | None = None,
prefetch_related: list | None = None,
select_related: list[str] | None = None,
prefetch_related: list[str] | None = None,
) -> Response:
"""
Paginate a queryset by primary key.
This method is useful when you want to paginate a queryset that has been
filtered or annotated in a way that would be lost if you used the default
pagination method.
"""
pk_list = base_queryset.values_list("id", flat=True)
page = self.paginate_queryset(pk_list)
if page is None:
return Response(self.get_serializer(base_queryset, many=True).data)
queryset = manager.filter(id__in=page)
if select_related:
queryset = queryset.select_related(*select_related)
if prefetch_related:
queryset = queryset.prefetch_related(*prefetch_related)
# Optimize tags loading, if applicable
if hasattr(self, "_optimize_tags_loading"):
queryset = self._optimize_tags_loading(queryset)
queryset = sorted(queryset, key=lambda obj: page.index(obj.id))
serialized = self.get_serializer(queryset, many=True).data
return self.get_paginated_response(serialized)
class TaskManagementMixin:
"""
Mixin to manage task status checking.
This mixin provides functionality to check if a task with specific parameters
is running, completed, failed, or doesn't exist. It returns the task when running
and raises specific exceptions for failed/not found scenarios that can be handled
at the view level.
"""
def check_task_status(
self,
task_name: str,
task_kwargs: dict,
raise_on_failed: bool = True,
raise_on_not_found: bool = True,
) -> Task | None:
"""
Check the status of a task with given name and kwargs.
This method first checks for a related Task object, and if not found,
checks TaskResult directly. If a TaskResult is found and running but
there's no related Task, it raises TaskInProgressException.
Args:
task_name (str): The name of the task to check
task_kwargs (dict): The kwargs to match against the task
raise_on_failed (bool): Whether to raise exception if task failed
raise_on_not_found (bool): Whether to raise exception if task not found
Returns:
Task | None: The task instance if found (regardless of state), None if not found and raise_on_not_found=False
Raises:
TaskFailedException: If task failed and raise_on_failed=True
TaskNotFoundException: If task not found and raise_on_not_found=True
TaskInProgressException: If task is running but no related Task object exists
"""
# First, try to find a Task object with related TaskResult
try:
# Build the filter for task kwargs
task_filter = {
"task_runner_task__task_name": task_name,
}
# Add kwargs filters - we need to check if the task kwargs contain our parameters
for key, value in task_kwargs.items():
task_filter["task_runner_task__task_kwargs__contains"] = str(value)
task = (
Task.objects.filter(**task_filter)
.select_related("task_runner_task")
.order_by("-inserted_at")
.first()
)
if task:
# Get task state using the same logic as TaskSerializer
task_state_mapping = {
"PENDING": StateChoices.AVAILABLE,
"STARTED": StateChoices.EXECUTING,
"PROGRESS": StateChoices.EXECUTING,
"SUCCESS": StateChoices.COMPLETED,
"FAILURE": StateChoices.FAILED,
"REVOKED": StateChoices.CANCELLED,
}
celery_status = (
task.task_runner_task.status if task.task_runner_task else None
)
task_state = task_state_mapping.get(
celery_status or "", StateChoices.AVAILABLE
)
# Check task state and raise exceptions accordingly
if task_state in (StateChoices.FAILED, StateChoices.CANCELLED):
if raise_on_failed:
raise TaskFailedException(task=task)
return task
elif task_state == StateChoices.COMPLETED:
return None
return task
except Task.DoesNotExist:
pass
# If no Task found, check TaskResult directly
try:
# Build the filter for TaskResult
task_result_filter = {
"task_name": task_name,
}
# Add kwargs filters - check if the task kwargs contain our parameters
for key, value in task_kwargs.items():
task_result_filter["task_kwargs__contains"] = str(value)
task_result = (
TaskResult.objects.filter(**task_result_filter)
.order_by("-date_created")
.first()
)
if task_result:
# Check if the TaskResult indicates a running task
if task_result.status in ["PENDING", "STARTED", "PROGRESS"]:
# Task is running but no related Task object exists
raise TaskInProgressException(task_result=task_result)
elif task_result.status == "FAILURE":
if raise_on_failed:
raise TaskFailedException(task=None)
# For other statuses (SUCCESS, REVOKED), we don't have a Task to return,
# so we treat it as not found
except TaskResult.DoesNotExist:
pass
# No task found at all
if raise_on_not_found:
raise TaskNotFoundException()
return None
def get_task_response_if_running(
self,
task_name: str,
task_kwargs: dict,
raise_on_failed: bool = True,
raise_on_not_found: bool = True,
) -> Response | None:
"""
Get a 202 response with task details if the task is currently running.
This method is useful for endpoints that should return task status when
a background task is in progress, similar to the compliance overview endpoints.
Args:
task_name (str): The name of the task to check
task_kwargs (dict): The kwargs to match against the task
Returns:
Response | None: 202 response with task details if running, None otherwise
"""
task = self.check_task_status(
task_name=task_name,
task_kwargs=task_kwargs,
raise_on_failed=raise_on_failed,
raise_on_not_found=raise_on_not_found,
)
if not task:
return None
# Get task state
task_state_mapping = {
"PENDING": StateChoices.AVAILABLE,
"STARTED": StateChoices.EXECUTING,
"PROGRESS": StateChoices.EXECUTING,
"SUCCESS": StateChoices.COMPLETED,
"FAILURE": StateChoices.FAILED,
"REVOKED": StateChoices.CANCELLED,
}
celery_status = task.task_runner_task.status if task.task_runner_task else None
task_state = task_state_mapping.get(celery_status or "", StateChoices.AVAILABLE)
if task_state == StateChoices.EXECUTING:
self.response_serializer_class = TaskSerializer
serializer = TaskSerializer(task)
return Response(
data=serializer.data,
status=status.HTTP_202_ACCEPTED,
headers={
"Content-Location": reverse("task-detail", kwargs={"pk": task.id})
},
)

View File

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

View File

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

View File

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

View File

@@ -7,23 +7,20 @@ from django.contrib.auth.models import update_last_login
from django.contrib.auth.password_validation import validate_password
from drf_spectacular.utils import extend_schema_field
from jwt.exceptions import InvalidKeyError
from rest_framework.validators import UniqueTogetherValidator
from rest_framework_json_api import serializers
from rest_framework_json_api.relations import SerializerMethodResourceRelatedField
from rest_framework_json_api.serializers import ValidationError
from rest_framework_simplejwt.exceptions import TokenError
from rest_framework_simplejwt.serializers import TokenObtainPairSerializer
from rest_framework_simplejwt.tokens import RefreshToken
from api.models import (
ComplianceOverview,
Finding,
Integration,
IntegrationProviderRelationship,
Invitation,
InvitationRoleRelationship,
LighthouseConfiguration,
Membership,
Processor,
Provider,
ProviderGroup,
ProviderGroupMembership,
@@ -32,10 +29,8 @@ from api.models import (
ResourceTag,
Role,
RoleProviderGroupRelationship,
SAMLConfiguration,
Scan,
StateChoices,
StatusChoices,
Task,
User,
UserRoleRelationship,
@@ -47,9 +42,7 @@ from api.v1.serializer_utils.integrations import (
IntegrationCredentialField,
S3ConfigSerializer,
)
from api.v1.serializer_utils.processors import ProcessorConfigField
from api.v1.serializer_utils.providers import ProviderSecretField
from prowler.lib.mutelist.mutelist import Mutelist
# Tokens
@@ -135,12 +128,6 @@ class TokenSerializer(BaseTokenSerializer):
class TokenSocialLoginSerializer(BaseTokenSerializer):
email = serializers.EmailField(write_only=True)
tenant_id = serializers.UUIDField(
write_only=True,
required=False,
help_text="If not provided, the tenant ID of the first membership that was added"
" to the user will be used.",
)
# Output tokens
refresh = serializers.CharField(read_only=True)
@@ -862,7 +849,6 @@ class ScanSerializer(RLSSerializer):
"completed_at",
"scheduled_at",
"next_scan_at",
"processor",
"url",
]
@@ -1000,12 +986,8 @@ class ResourceSerializer(RLSSerializer):
tags = serializers.SerializerMethodField()
type_ = serializers.CharField(read_only=True)
failed_findings_count = serializers.IntegerField(read_only=True)
findings = SerializerMethodResourceRelatedField(
many=True,
read_only=True,
)
findings = serializers.ResourceRelatedField(many=True, read_only=True)
class Meta:
model = Resource
@@ -1021,7 +1003,6 @@ class ResourceSerializer(RLSSerializer):
"tags",
"provider",
"findings",
"failed_findings_count",
"url",
]
extra_kwargs = {
@@ -1031,8 +1012,8 @@ class ResourceSerializer(RLSSerializer):
}
included_serializers = {
"findings": "api.v1.serializers.FindingIncludeSerializer",
"provider": "api.v1.serializers.ProviderIncludeSerializer",
"findings": "api.v1.serializers.FindingSerializer",
"provider": "api.v1.serializers.ProviderSerializer",
}
@extend_schema_field(
@@ -1043,10 +1024,6 @@ class ResourceSerializer(RLSSerializer):
}
)
def get_tags(self, obj):
# Use prefetched tags if available to avoid N+1 queries
if hasattr(obj, "prefetched_tags"):
return {tag.key: tag.value for tag in obj.prefetched_tags}
# Fallback to the original method if prefetch is not available
return obj.get_tags(self.context.get("tenant_id"))
def get_fields(self):
@@ -1056,17 +1033,10 @@ class ResourceSerializer(RLSSerializer):
fields["type"] = type_
return fields
def get_findings(self, obj):
return (
obj.latest_findings
if hasattr(obj, "latest_findings")
else obj.findings.all()
)
class ResourceIncludeSerializer(RLSSerializer):
"""
Serializer for the included Resource model.
Serializer for the Resource model.
"""
tags = serializers.SerializerMethodField()
@@ -1099,10 +1069,6 @@ class ResourceIncludeSerializer(RLSSerializer):
}
)
def get_tags(self, obj):
# Use prefetched tags if available to avoid N+1 queries
if hasattr(obj, "prefetched_tags"):
return {tag.key: tag.value for tag in obj.prefetched_tags}
# Fallback to the original method if prefetch is not available
return obj.get_tags(self.context.get("tenant_id"))
def get_fields(self):
@@ -1113,17 +1079,6 @@ class ResourceIncludeSerializer(RLSSerializer):
return fields
class ResourceMetadataSerializer(serializers.Serializer):
services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
types = serializers.ListField(child=serializers.CharField(), allow_empty=True)
# Temporarily disabled until we implement tag filtering in the UI
# tags = serializers.JSONField(help_text="Tags are described as key-value pairs.")
class Meta:
resource_name = "resources-metadata"
class FindingSerializer(RLSSerializer):
"""
Serializer for the Finding model.
@@ -1147,7 +1102,6 @@ class FindingSerializer(RLSSerializer):
"updated_at",
"first_seen_at",
"muted",
"muted_reason",
"url",
# Relationships
"scan",
@@ -1160,28 +1114,6 @@ class FindingSerializer(RLSSerializer):
}
class FindingIncludeSerializer(RLSSerializer):
"""
Serializer for the include Finding model.
"""
class Meta:
model = Finding
fields = [
"id",
"uid",
"status",
"severity",
"check_id",
"check_metadata",
"inserted_at",
"updated_at",
"first_seen_at",
"muted",
"muted_reason",
]
# To be removed when the related endpoint is removed as well
class FindingDynamicFilterSerializer(serializers.Serializer):
services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
@@ -1266,8 +1198,8 @@ class M365ProviderSecret(serializers.Serializer):
client_id = serializers.CharField()
client_secret = serializers.CharField()
tenant_id = serializers.CharField()
user = serializers.EmailField(required=False)
password = serializers.CharField(required=False)
user = serializers.EmailField()
password = serializers.CharField()
class Meta:
resource_name = "provider-secrets"
@@ -1375,13 +1307,12 @@ class ProviderSecretUpdateSerializer(BaseWriteProviderSecretSerializer):
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
"provider": {"read_only": True},
"secret_type": {"required": False},
"secret_type": {"read_only": True},
}
def validate(self, attrs):
provider = self.instance.provider
# To allow updating a secret with the same type without making the `secret_type` mandatory
secret_type = attrs.get("secret_type") or self.instance.secret_type
secret_type = self.instance.secret_type
secret = attrs.get("secret")
validated_attrs = super().validate(attrs)
@@ -1748,63 +1679,130 @@ class RoleProviderGroupRelationshipSerializer(RLSSerializer, BaseWriteSerializer
# Compliance overview
class ComplianceOverviewSerializer(serializers.Serializer):
class ComplianceOverviewSerializer(RLSSerializer):
"""
Serializer for compliance requirement status aggregated by compliance framework.
This serializer is used to format aggregated compliance framework data,
providing counts of passed, failed, and manual requirements along with
an overall global status for each framework.
Serializer for the ComplianceOverview model.
"""
# Add ID field which will be used for resource identification
id = serializers.CharField()
framework = serializers.CharField()
version = serializers.CharField()
requirements_passed = serializers.IntegerField()
requirements_failed = serializers.IntegerField()
requirements_manual = serializers.IntegerField()
total_requirements = serializers.IntegerField()
requirements_status = serializers.SerializerMethodField(
read_only=True, method_name="get_requirements_status"
)
provider_type = serializers.SerializerMethodField(read_only=True)
class JSONAPIMeta:
resource_name = "compliance-overviews"
class Meta:
model = ComplianceOverview
fields = [
"id",
"inserted_at",
"compliance_id",
"framework",
"version",
"requirements_status",
"region",
"provider_type",
"scan",
"url",
]
@extend_schema_field(
{
"type": "object",
"properties": {
"passed": {"type": "integer"},
"failed": {"type": "integer"},
"manual": {"type": "integer"},
"total": {"type": "integer"},
},
}
)
def get_requirements_status(self, obj):
return {
"passed": obj.requirements_passed,
"failed": obj.requirements_failed,
"manual": obj.requirements_manual,
"total": obj.total_requirements,
}
@extend_schema_field(serializers.CharField(allow_null=True))
def get_provider_type(self, obj):
"""
Retrieves the provider_type from scan.provider.provider_type.
"""
try:
return obj.scan.provider.provider
except AttributeError:
return None
class ComplianceOverviewDetailSerializer(serializers.Serializer):
"""
Serializer for detailed compliance requirement information.
class ComplianceOverviewFullSerializer(ComplianceOverviewSerializer):
requirements = serializers.SerializerMethodField(read_only=True)
This serializer formats the aggregated requirement data, showing detailed status
and counts for each requirement across all regions.
"""
class Meta(ComplianceOverviewSerializer.Meta):
fields = ComplianceOverviewSerializer.Meta.fields + [
"description",
"requirements",
]
id = serializers.CharField()
framework = serializers.CharField()
version = serializers.CharField()
description = serializers.CharField()
status = serializers.ChoiceField(choices=StatusChoices.choices)
class JSONAPIMeta:
resource_name = "compliance-requirements-details"
class ComplianceOverviewAttributesSerializer(serializers.Serializer):
id = serializers.CharField()
framework_description = serializers.CharField()
name = serializers.CharField()
framework = serializers.CharField()
version = serializers.CharField()
description = serializers.CharField()
attributes = serializers.JSONField()
class JSONAPIMeta:
resource_name = "compliance-requirements-attributes"
@extend_schema_field(
{
"type": "object",
"properties": {
"requirement_id": {
"type": "object",
"properties": {
"name": {"type": "string"},
"checks": {
"type": "object",
"properties": {
"check_name": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": ["PASS", "FAIL", None],
},
},
}
},
"description": "Each key in the 'checks' object is a check name, with values as "
"'PASS', 'FAIL', or null.",
},
"status": {
"type": "string",
"enum": ["PASS", "FAIL", "MANUAL"],
},
"attributes": {
"type": "array",
"items": {
"type": "object",
},
},
"description": {"type": "string"},
"checks_status": {
"type": "object",
"properties": {
"total": {"type": "integer"},
"pass": {"type": "integer"},
"fail": {"type": "integer"},
"manual": {"type": "integer"},
},
},
},
}
},
}
)
def get_requirements(self, obj):
"""
Returns the detailed structure of requirements.
"""
return obj.requirements
class ComplianceOverviewMetadataSerializer(serializers.Serializer):
regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
class JSONAPIMeta:
class Meta:
resource_name = "compliance-overviews-metadata"
@@ -2130,278 +2128,3 @@ class IntegrationUpdateSerializer(BaseWriteIntegrationSerializer):
IntegrationProviderRelationship.objects.bulk_create(new_relationships)
return super().update(instance, validated_data)
# Processors
class ProcessorSerializer(RLSSerializer):
"""
Serializer for the Processor model.
"""
configuration = ProcessorConfigField()
class Meta:
model = Processor
fields = [
"id",
"inserted_at",
"updated_at",
"processor_type",
"configuration",
"url",
]
class ProcessorCreateSerializer(RLSSerializer, BaseWriteSerializer):
configuration = ProcessorConfigField(required=True)
class Meta:
model = Processor
fields = [
"inserted_at",
"updated_at",
"processor_type",
"configuration",
]
extra_kwargs = {
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
}
validators = [
UniqueTogetherValidator(
queryset=Processor.objects.all(),
fields=["processor_type"],
message="A processor with the same type already exists.",
)
]
def validate(self, attrs):
validated_attrs = super().validate(attrs)
self.validate_processor_data(attrs)
return validated_attrs
def validate_processor_data(self, attrs):
processor_type = attrs.get("processor_type")
configuration = attrs.get("configuration")
if processor_type == "mutelist":
self.validate_mutelist_configuration(configuration)
def validate_mutelist_configuration(self, configuration):
if not isinstance(configuration, dict):
raise serializers.ValidationError("Invalid Mutelist configuration.")
mutelist_configuration = configuration.get("Mutelist", {})
if not mutelist_configuration:
raise serializers.ValidationError(
"Invalid Mutelist configuration: 'Mutelist' is a required property."
)
try:
Mutelist.validate_mutelist(mutelist_configuration, raise_on_exception=True)
return
except Exception as error:
raise serializers.ValidationError(
f"Invalid Mutelist configuration: {error}"
)
class ProcessorUpdateSerializer(BaseWriteSerializer):
configuration = ProcessorConfigField(required=True)
class Meta:
model = Processor
fields = [
"inserted_at",
"updated_at",
"configuration",
]
extra_kwargs = {
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
}
def validate(self, attrs):
validated_attrs = super().validate(attrs)
self.validate_processor_data(attrs)
return validated_attrs
def validate_processor_data(self, attrs):
processor_type = self.instance.processor_type
configuration = attrs.get("configuration")
if processor_type == "mutelist":
self.validate_mutelist_configuration(configuration)
def validate_mutelist_configuration(self, configuration):
if not isinstance(configuration, dict):
raise serializers.ValidationError("Invalid Mutelist configuration.")
mutelist_configuration = configuration.get("Mutelist", {})
if not mutelist_configuration:
raise serializers.ValidationError(
"Invalid Mutelist configuration: 'Mutelist' is a required property."
)
try:
Mutelist.validate_mutelist(mutelist_configuration, raise_on_exception=True)
return
except Exception as error:
raise serializers.ValidationError(
f"Invalid Mutelist configuration: {error}"
)
# SSO
class SamlInitiateSerializer(serializers.Serializer):
email_domain = serializers.CharField()
class JSONAPIMeta:
resource_name = "saml-initiate"
class SamlMetadataSerializer(serializers.Serializer):
class JSONAPIMeta:
resource_name = "saml-meta"
class SAMLConfigurationSerializer(RLSSerializer):
class Meta:
model = SAMLConfiguration
fields = ["id", "email_domain", "metadata_xml", "created_at", "updated_at"]
read_only_fields = ["id", "created_at", "updated_at"]
class LighthouseConfigSerializer(RLSSerializer):
"""
Serializer for the LighthouseConfig model.
"""
api_key = serializers.CharField(required=False)
class Meta:
model = LighthouseConfiguration
fields = [
"id",
"name",
"api_key",
"model",
"temperature",
"max_tokens",
"business_context",
"is_active",
"inserted_at",
"updated_at",
"url",
]
extra_kwargs = {
"id": {"read_only": True},
"is_active": {"read_only": True},
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
}
def to_representation(self, instance):
data = super().to_representation(instance)
# Check if api_key is specifically requested in fields param
fields_param = self.context.get("request", None) and self.context[
"request"
].query_params.get("fields[lighthouse-config]", "")
if fields_param == "api_key":
# Return decrypted key if specifically requested
data["api_key"] = instance.api_key_decoded if instance.api_key else None
else:
# Return masked key for general requests
data["api_key"] = "*" * len(instance.api_key) if instance.api_key else None
return data
class LighthouseConfigCreateSerializer(RLSSerializer, BaseWriteSerializer):
"""Serializer for creating new Lighthouse configurations."""
api_key = serializers.CharField(write_only=True, required=True)
class Meta:
model = LighthouseConfiguration
fields = [
"id",
"name",
"api_key",
"model",
"temperature",
"max_tokens",
"business_context",
"is_active",
"inserted_at",
"updated_at",
]
extra_kwargs = {
"id": {"read_only": True},
"is_active": {"read_only": True},
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
}
def validate(self, attrs):
tenant_id = self.context.get("request").tenant_id
if LighthouseConfiguration.objects.filter(tenant_id=tenant_id).exists():
raise serializers.ValidationError(
{
"tenant_id": "Lighthouse configuration already exists for this tenant."
}
)
return super().validate(attrs)
def create(self, validated_data):
api_key = validated_data.pop("api_key")
instance = super().create(validated_data)
instance.api_key_decoded = api_key
instance.save()
return instance
def to_representation(self, instance):
data = super().to_representation(instance)
# Always mask the API key in the response
data["api_key"] = "*" * len(instance.api_key) if instance.api_key else None
return data
class LighthouseConfigUpdateSerializer(BaseWriteSerializer):
"""
Serializer for updating LighthouseConfig instances.
"""
api_key = serializers.CharField(write_only=True, required=False)
class Meta:
model = LighthouseConfiguration
fields = [
"id",
"name",
"api_key",
"model",
"temperature",
"max_tokens",
"business_context",
"is_active",
]
extra_kwargs = {
"id": {"read_only": True},
"is_active": {"read_only": True},
"name": {"required": False},
"model": {"required": False},
"temperature": {"required": False},
"max_tokens": {"required": False},
}
def update(self, instance, validated_data):
api_key = validated_data.pop("api_key", None)
instance = super().update(instance, validated_data)
if api_key:
instance.api_key_decoded = api_key
instance.save()
return instance

View File

@@ -1,11 +1,9 @@
from allauth.socialaccount.providers.saml.views import ACSView, MetadataView, SLSView
from django.urls import include, path
from drf_spectacular.views import SpectacularRedocView
from rest_framework_nested import routers
from api.v1.views import (
ComplianceOverviewViewSet,
CustomSAMLLoginView,
CustomTokenObtainView,
CustomTokenRefreshView,
CustomTokenSwitchTenantView,
@@ -15,10 +13,8 @@ from api.v1.views import (
IntegrationViewSet,
InvitationAcceptViewSet,
InvitationViewSet,
LighthouseConfigViewSet,
MembershipViewSet,
OverviewViewSet,
ProcessorViewSet,
ProviderGroupProvidersRelationshipView,
ProviderGroupViewSet,
ProviderSecretViewSet,
@@ -26,14 +22,10 @@ from api.v1.views import (
ResourceViewSet,
RoleProviderGroupRelationshipView,
RoleViewSet,
SAMLConfigurationViewSet,
SAMLInitiateAPIView,
SAMLTokenValidateView,
ScanViewSet,
ScheduleViewSet,
SchemaView,
TaskViewSet,
TenantFinishACSView,
TenantMembersViewSet,
TenantViewSet,
UserRoleRelationshipView,
@@ -57,13 +49,6 @@ router.register(
router.register(r"overviews", OverviewViewSet, basename="overview")
router.register(r"schedules", ScheduleViewSet, basename="schedule")
router.register(r"integrations", IntegrationViewSet, basename="integration")
router.register(r"processors", ProcessorViewSet, basename="processor")
router.register(r"saml-config", SAMLConfigurationViewSet, basename="saml-config")
router.register(
r"lighthouse-configurations",
LighthouseConfigViewSet,
basename="lighthouseconfiguration",
)
tenants_router = routers.NestedSimpleRouter(router, r"tenants", lookup="tenant")
tenants_router.register(
@@ -127,36 +112,6 @@ urlpatterns = [
),
name="provider_group-providers-relationship",
),
# API endpoint to start SAML SSO flow
path(
"auth/saml/initiate/", SAMLInitiateAPIView.as_view(), name="api_saml_initiate"
),
path(
"accounts/saml/<organization_slug>/login/",
CustomSAMLLoginView.as_view(),
name="saml_login",
),
path(
"accounts/saml/<organization_slug>/acs/",
ACSView.as_view(),
name="saml_acs",
),
path(
"accounts/saml/<organization_slug>/acs/finish/",
TenantFinishACSView.as_view(),
name="saml_finish_acs",
),
path(
"accounts/saml/<organization_slug>/sls/",
SLSView.as_view(),
name="saml_sls",
),
path(
"accounts/saml/<organization_slug>/metadata/",
MetadataView.as_view(),
name="saml_metadata",
),
path("tokens/saml", SAMLTokenValidateView.as_view(), name="token-saml"),
path("tokens/google", GoogleSocialLoginView.as_view(), name="token-google"),
path("tokens/github", GithubSocialLoginView.as_view(), name="token-github"),
path("", include(router.urls)),

File diff suppressed because it is too large Load Diff

View File

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

View File

@@ -1,13 +1,6 @@
import warnings
from celery import Celery, Task
from config.env import env
# Suppress specific warnings from django-rest-auth: https://github.com/iMerica/dj-rest-auth/issues/684
warnings.filterwarnings(
"ignore", category=UserWarning, module="dj_rest_auth.registration.serializers"
)
BROKER_VISIBILITY_TIMEOUT = env.int("DJANGO_BROKER_VISIBILITY_TIMEOUT", default=86400)
celery_app = Celery("tasks")

View File

@@ -10,8 +10,6 @@ from config.settings.social_login import * # noqa
SECRET_KEY = env("SECRET_KEY", default="secret")
DEBUG = env.bool("DJANGO_DEBUG", default=False)
ALLOWED_HOSTS = ["localhost", "127.0.0.1"]
SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
USE_X_FORWARDED_HOST = True
# Application definition
@@ -28,19 +26,16 @@ INSTALLED_APPS = [
"rest_framework",
"corsheaders",
"drf_spectacular",
"drf_spectacular_jsonapi",
"django_guid",
"rest_framework_json_api",
"django_celery_results",
"django_celery_beat",
"rest_framework_simplejwt.token_blacklist",
"allauth",
"django.contrib.sites",
"allauth.account",
"allauth.socialaccount",
"allauth.socialaccount.providers.google",
"allauth.socialaccount.providers.github",
"allauth.socialaccount.providers.saml",
"dj_rest_auth.registration",
"rest_framework.authtoken",
]
@@ -159,30 +154,6 @@ AUTH_PASSWORD_VALIDATORS = [
{
"NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
},
{
"NAME": "api.validators.SpecialCharactersValidator",
"OPTIONS": {
"min_special_characters": 1,
},
},
{
"NAME": "api.validators.UppercaseValidator",
"OPTIONS": {
"min_uppercase": 1,
},
},
{
"NAME": "api.validators.LowercaseValidator",
"OPTIONS": {
"min_lowercase": 1,
},
},
{
"NAME": "api.validators.NumericValidator",
"OPTIONS": {
"min_numeric": 1,
},
},
]
SIMPLE_JWT = {
@@ -273,7 +244,3 @@ X_FRAME_OPTIONS = "DENY"
SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)
# SAML requirement
CSRF_COOKIE_SECURE = True
SESSION_COOKIE_SECURE = True

View File

@@ -4,7 +4,6 @@ from config.env import env
IGNORED_EXCEPTIONS = [
# Provider is not connected due to credentials errors
"is not connected",
"ProviderConnectionError",
# Authentication Errors from AWS
"InvalidToken",
"AccessDeniedException",
@@ -17,7 +16,7 @@ IGNORED_EXCEPTIONS = [
"InternalServerErrorException",
"AccessDenied",
"No Shodan API Key", # Shodan Check
"RequestLimitExceeded", # For now, we don't want to log the RequestLimitExceeded errors
"RequestLimitExceeded", # For now we don't want to log the RequestLimitExceeded errors
"ThrottlingException",
"Rate exceeded",
"SubscriptionRequiredException",
@@ -43,9 +42,7 @@ IGNORED_EXCEPTIONS = [
"AWSAccessKeyIDInvalidError",
"AWSSessionTokenExpiredError",
"EndpointConnectionError", # AWS Service is not available in a region
# The following comes from urllib3: eu-west-1 -- HTTPClientError[126]: An HTTP Client raised an
# unhandled exception: AWSHTTPSConnectionPool(host='hostname.s3.eu-west-1.amazonaws.com', port=443): Pool is closed.
"Pool is closed",
"Pool is closed", # The following comes from urllib3: eu-west-1 -- HTTPClientError[126]: An HTTP Client raised an unhandled exception: AWSHTTPSConnectionPool(host='hostname.s3.eu-west-1.amazonaws.com', port=443): Pool is closed.
# Authentication Errors from GCP
"ClientAuthenticationError",
"AuthorizationFailed",
@@ -74,7 +71,7 @@ IGNORED_EXCEPTIONS = [
def before_send(event, hint):
"""
before_send handles the Sentry events in order to send them or not
before_send handles the Sentry events in order to sent them or not
"""
# Ignore logs with the ignored_exceptions
# https://docs.python.org/3/library/logging.html#logrecord-objects
@@ -82,16 +79,9 @@ def before_send(event, hint):
log_msg = hint["log_record"].msg
log_lvl = hint["log_record"].levelno
# Handle Error and Critical events and discard the rest
if log_lvl <= 40 and any(ignored in log_msg for ignored in IGNORED_EXCEPTIONS):
return None # Explicitly return None to drop the event
# Ignore exceptions with the ignored_exceptions
if "exc_info" in hint and hint["exc_info"]:
exc_value = str(hint["exc_info"][1])
if any(ignored in exc_value for ignored in IGNORED_EXCEPTIONS):
return None # Explicitly return None to drop the event
# Handle Error events and discard the rest
if log_lvl == 40 and any(ignored in log_msg for ignored in IGNORED_EXCEPTIONS):
return
return event

View File

@@ -11,7 +11,8 @@ GITHUB_OAUTH_CALLBACK_URL = env("SOCIAL_GITHUB_OAUTH_CALLBACK_URL", default="")
# Allauth settings
ACCOUNT_LOGIN_METHODS = {"email"} # Use Email / Password authentication
ACCOUNT_SIGNUP_FIELDS = ["email*", "password1*", "password2*"]
ACCOUNT_USERNAME_REQUIRED = False
ACCOUNT_EMAIL_REQUIRED = True
ACCOUNT_EMAIL_VERIFICATION = "none" # Do not require email confirmation
ACCOUNT_USER_MODEL_USERNAME_FIELD = None
REST_AUTH = {
@@ -24,20 +25,6 @@ SOCIALACCOUNT_EMAIL_AUTHENTICATION = True
# Connect local account and social account if local account with that email address already exists
SOCIALACCOUNT_EMAIL_AUTHENTICATION_AUTO_CONNECT = True
SOCIALACCOUNT_ADAPTER = "api.adapters.ProwlerSocialAccountAdapter"
# def inline(pem: str) -> str:
# return "".join(
# line.strip()
# for line in pem.splitlines()
# if "CERTIFICATE" not in line and "KEY" not in line
# )
# # SAML keys (TODO: Validate certificates)
# SAML_PUBLIC_CERT = inline(env("SAML_PUBLIC_CERT", default=""))
# SAML_PRIVATE_KEY = inline(env("SAML_PRIVATE_KEY", default=""))
SOCIALACCOUNT_PROVIDERS = {
"google": {
"APP": {
@@ -63,20 +50,4 @@ SOCIALACCOUNT_PROVIDERS = {
"read:org",
],
},
"saml": {
"use_nameid_for_email": True,
"sp": {
"entity_id": "urn:prowler.com:sp",
},
"advanced": {
# TODO: Validate certificates
# "x509cert": SAML_PUBLIC_CERT,
# "private_key": SAML_PRIVATE_KEY,
# "authn_request_signed": True,
# "want_message_signed": True,
# "want_assertion_signed": True,
"reject_idp_initiated_sso": False,
"name_id_format": "urn:oasis:names:tc:SAML:1.1:nameid-format:emailAddress",
},
},
}

View File

@@ -1,9 +1,8 @@
import logging
from datetime import datetime, timedelta, timezone
from unittest.mock import MagicMock, patch
from unittest.mock import patch
import pytest
from allauth.socialaccount.models import SocialLogin
from django.conf import settings
from django.db import connection as django_connection
from django.db import connections as django_connections
@@ -16,27 +15,20 @@ from tasks.jobs.backfill import backfill_resource_scan_summaries
from api.db_utils import rls_transaction
from api.models import (
ComplianceOverview,
ComplianceRequirementOverview,
Finding,
Integration,
IntegrationProviderRelationship,
Invitation,
LighthouseConfiguration,
Membership,
Processor,
Provider,
ProviderGroup,
ProviderSecret,
Resource,
ResourceTag,
ResourceTagMapping,
Role,
SAMLConfiguration,
SAMLDomainIndex,
Scan,
ScanSummary,
StateChoices,
StatusChoices,
Task,
User,
UserRoleRelationship,
@@ -46,19 +38,12 @@ from api.v1.serializers import TokenSerializer
from prowler.lib.check.models import Severity
from prowler.lib.outputs.finding import Status
TODAY = str(datetime.today().date())
API_JSON_CONTENT_TYPE = "application/vnd.api+json"
NO_TENANT_HTTP_STATUS = status.HTTP_401_UNAUTHORIZED
TEST_USER = "dev@prowler.com"
TEST_PASSWORD = "testing_psswd"
def today_after_n_days(n_days: int) -> str:
return datetime.strftime(
datetime.today().date() + timedelta(days=n_days), "%Y-%m-%d"
)
@pytest.fixture(scope="module")
def enforce_test_user_db_connection(django_db_setup, django_db_blocker):
"""Ensure tests use the test user for database connections."""
@@ -390,27 +375,8 @@ def providers_fixture(tenants_fixture):
tenant_id=tenant.id,
scanner_args={"key1": "value1", "key2": {"key21": "value21"}},
)
provider6 = Provider.objects.create(
provider="m365",
uid="m365.test.com",
alias="m365_testing",
tenant_id=tenant.id,
)
return provider1, provider2, provider3, provider4, provider5, provider6
@pytest.fixture
def processor_fixture(tenants_fixture):
tenant, *_ = tenants_fixture
processor = Processor.objects.create(
tenant_id=tenant.id,
processor_type="mutelist",
configuration="Mutelist:\n Accounts:\n *:\n Checks:\n iam_user_hardware_mfa_enabled:\n "
" Regions:\n - *\n Resources:\n - *",
)
return processor
return provider1, provider2, provider3, provider4, provider5
@pytest.fixture
@@ -662,7 +628,6 @@ def findings_fixture(scans_fixture, resources_fixture):
check_metadata={
"CheckId": "test_check_id",
"Description": "test description apple sauce",
"servicename": "ec2",
},
first_seen_at="2024-01-02T00:00:00Z",
)
@@ -689,7 +654,6 @@ def findings_fixture(scans_fixture, resources_fixture):
check_metadata={
"CheckId": "test_check_id",
"Description": "test description orange juice",
"servicename": "s3",
},
first_seen_at="2024-01-02T00:00:00Z",
muted=True,
@@ -813,131 +777,6 @@ def compliance_overviews_fixture(scans_fixture, tenants_fixture):
return compliance_overview1, compliance_overview2
@pytest.fixture
def compliance_requirements_overviews_fixture(scans_fixture, tenants_fixture):
"""Fixture for ComplianceRequirementOverview objects used by the new ComplianceOverviewViewSet."""
tenant = tenants_fixture[0]
scan1, scan2, scan3 = scans_fixture
# Create ComplianceRequirementOverview objects for scan1
requirement_overview1 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="aws_account_security_onboarding_aws",
framework="AWS-Account-Security-Onboarding",
version="1.0",
description="Description for AWS Account Security Onboarding",
region="eu-west-1",
requirement_id="requirement1",
requirement_status=StatusChoices.PASS,
passed_checks=2,
failed_checks=0,
total_checks=2,
)
requirement_overview2 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="aws_account_security_onboarding_aws",
framework="AWS-Account-Security-Onboarding",
version="1.0",
description="Description for AWS Account Security Onboarding",
region="eu-west-1",
requirement_id="requirement2",
requirement_status=StatusChoices.PASS,
passed_checks=2,
failed_checks=0,
total_checks=2,
)
requirement_overview3 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="aws_account_security_onboarding_aws",
framework="AWS-Account-Security-Onboarding",
version="1.0",
description="Description for AWS Account Security Onboarding",
region="eu-west-2",
requirement_id="requirement1",
requirement_status=StatusChoices.PASS,
passed_checks=2,
failed_checks=0,
total_checks=2,
)
requirement_overview4 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="aws_account_security_onboarding_aws",
framework="AWS-Account-Security-Onboarding",
version="1.0",
description="Description for AWS Account Security Onboarding",
region="eu-west-2",
requirement_id="requirement2",
requirement_status=StatusChoices.FAIL,
passed_checks=1,
failed_checks=1,
total_checks=2,
)
requirement_overview5 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="aws_account_security_onboarding_aws",
framework="AWS-Account-Security-Onboarding",
version="1.0",
description="Description for AWS Account Security Onboarding (MANUAL)",
region="eu-west-2",
requirement_id="requirement3",
requirement_status=StatusChoices.MANUAL,
passed_checks=0,
failed_checks=0,
total_checks=0,
)
# Create a different compliance framework for testing
requirement_overview6 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="cis_1.4_aws",
framework="CIS-1.4-AWS",
version="1.4",
description="CIS AWS Foundations Benchmark v1.4.0",
region="eu-west-1",
requirement_id="cis_requirement1",
requirement_status=StatusChoices.FAIL,
passed_checks=0,
failed_checks=3,
total_checks=3,
)
# Create another compliance framework for testing MITRE ATT&CK
requirement_overview7 = ComplianceRequirementOverview.objects.create(
tenant=tenant,
scan=scan1,
compliance_id="mitre_attack_aws",
framework="MITRE-ATTACK",
version="1.0",
description="MITRE ATT&CK",
region="eu-west-1",
requirement_id="mitre_requirement1",
requirement_status=StatusChoices.FAIL,
passed_checks=0,
failed_checks=0,
total_checks=0,
)
return (
requirement_overview1,
requirement_overview2,
requirement_overview3,
requirement_overview4,
requirement_overview5,
requirement_overview6,
requirement_overview7,
)
def get_api_tokens(
api_client, user_email: str, user_password: str, tenant_id: str = None
) -> tuple[str, str]:
@@ -1090,20 +929,6 @@ def backfill_scan_metadata_fixture(scans_fixture, findings_fixture):
backfill_resource_scan_summaries(tenant_id=tenant_id, scan_id=scan_id)
@pytest.fixture
def lighthouse_config_fixture(authenticated_client, tenants_fixture):
return LighthouseConfiguration.objects.create(
tenant_id=tenants_fixture[0].id,
name="OpenAI",
api_key_decoded="sk-test1234567890T3BlbkFJtest1234567890",
model="gpt-4o",
temperature=0,
max_tokens=4000,
business_context="Test business context",
is_active=True,
)
@pytest.fixture(scope="function")
def latest_scan_finding(authenticated_client, providers_fixture, resources_fixture):
provider = providers_fixture[0]
@@ -1145,127 +970,6 @@ def latest_scan_finding(authenticated_client, providers_fixture, resources_fixtu
return finding
@pytest.fixture(scope="function")
def latest_scan_resource(authenticated_client, providers_fixture):
provider = providers_fixture[0]
tenant_id = str(providers_fixture[0].tenant_id)
scan = Scan.objects.create(
name="latest completed scan for resource",
provider=provider,
trigger=Scan.TriggerChoices.MANUAL,
state=StateChoices.COMPLETED,
tenant_id=tenant_id,
)
resource = Resource.objects.create(
tenant_id=tenant_id,
provider=provider,
uid="latest_resource_uid",
name="Latest Resource",
region="us-east-1",
service="ec2",
type="instance",
metadata='{"test": "metadata"}',
details='{"test": "details"}',
)
resource_tag = ResourceTag.objects.create(
tenant_id=tenant_id,
key="environment",
value="test",
)
ResourceTagMapping.objects.create(
tenant_id=tenant_id,
resource=resource,
tag=resource_tag,
)
finding = Finding.objects.create(
tenant_id=tenant_id,
uid="test_finding_uid_latest",
scan=scan,
delta="new",
status=Status.FAIL,
status_extended="test status extended ",
impact=Severity.critical,
impact_extended="test impact extended",
severity=Severity.critical,
raw_result={
"status": Status.FAIL,
"impact": Severity.critical,
"severity": Severity.critical,
},
tags={"test": "latest"},
check_id="test_check_id_latest",
check_metadata={
"CheckId": "test_check_id_latest",
"Description": "test description latest",
},
first_seen_at="2024-01-02T00:00:00Z",
)
finding.add_resources([resource])
backfill_resource_scan_summaries(tenant_id, str(scan.id))
return resource
@pytest.fixture
def saml_setup(tenants_fixture):
tenant_id = tenants_fixture[0].id
domain = "prowler.com"
SAMLDomainIndex.objects.create(email_domain=domain, tenant_id=tenant_id)
metadata_xml = """<?xml version='1.0' encoding='UTF-8'?>
<md:EntityDescriptor entityID='TEST' xmlns:md='urn:oasis:names:tc:SAML:2.0:metadata'>
<md:IDPSSODescriptor WantAuthnRequestsSigned='false' protocolSupportEnumeration='urn:oasis:names:tc:SAML:2.0:protocol'>
<md:KeyDescriptor use='signing'>
<ds:KeyInfo xmlns:ds='http://www.w3.org/2000/09/xmldsig#'>
<ds:X509Data>
<ds:X509Certificate>TEST</ds:X509Certificate>
</ds:X509Data>
</ds:KeyInfo>
</md:KeyDescriptor>
<md:NameIDFormat>urn:oasis:names:tc:SAML:1.1:nameid-format:emailAddress</md:NameIDFormat>
<md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-POST' Location='https://TEST/sso/saml'/>
<md:SingleSignOnService Binding='urn:oasis:names:tc:SAML:2.0:bindings:HTTP-Redirect' Location='https://TEST/sso/saml'/>
</md:IDPSSODescriptor>
</md:EntityDescriptor>
"""
SAMLConfiguration.objects.create(
tenant_id=str(tenant_id),
email_domain=domain,
metadata_xml=metadata_xml,
)
return {
"email": f"user@{domain}",
"domain": domain,
"tenant_id": tenant_id,
}
@pytest.fixture
def saml_sociallogin(users_fixture):
user = users_fixture[0]
user.email = "samlsso@acme.com"
extra_data = {
"firstName": ["Test"],
"lastName": ["User"],
"organization": ["Prowler"],
"userType": ["member"],
}
account = MagicMock()
account.provider = "saml"
account.extra_data = extra_data
sociallogin = MagicMock(spec=SocialLogin)
sociallogin.account = account
sociallogin.user = user
return sociallogin
def get_authorization_header(access_token: str) -> dict:
return {"Authorization": f"Bearer {access_token}"}

View File

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

View File

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

View File

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

View File

@@ -1,5 +1,4 @@
import os
import re
import zipfile
import boto3
@@ -31,7 +30,6 @@ from prowler.lib.outputs.compliance.iso27001.iso27001_gcp import GCPISO27001
from prowler.lib.outputs.compliance.iso27001.iso27001_kubernetes import (
KubernetesISO27001,
)
from prowler.lib.outputs.compliance.iso27001.iso27001_m365 import M365ISO27001
from prowler.lib.outputs.compliance.kisa_ismsp.kisa_ismsp_aws import AWSKISAISMSP
from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_aws import AWSMitreAttack
from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_azure import (
@@ -91,7 +89,6 @@ COMPLIANCE_CLASS_MAP = {
"m365": [
(lambda name: name.startswith("cis_"), M365CIS),
(lambda name: name == "prowler_threatscore_m365", ProwlerThreatScoreM365),
(lambda name: name.startswith("iso27001_"), M365ISO27001),
],
}
@@ -241,18 +238,15 @@ def _generate_output_directory(
'/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56',
'/tmp/tenant-1234/aws/scan-5678/compliance/prowler-output-2023-02-15T12:34:56'
"""
# Sanitize the prowler provider name to ensure it is a valid directory name
prowler_provider_sanitized = re.sub(r"[^\w\-]", "-", prowler_provider)
path = (
f"{output_directory}/{tenant_id}/{scan_id}/prowler-output-"
f"{prowler_provider_sanitized}-{output_file_timestamp}"
f"{prowler_provider}-{output_file_timestamp}"
)
os.makedirs("/".join(path.split("/")[:-1]), exist_ok=True)
compliance_path = (
f"{output_directory}/{tenant_id}/{scan_id}/compliance/prowler-output-"
f"{prowler_provider_sanitized}-{output_file_timestamp}"
f"{prowler_provider}-{output_file_timestamp}"
)
os.makedirs("/".join(compliance_path.split("/")[:-1]), exist_ok=True)

View File

@@ -1,29 +1,22 @@
import json
import time
from collections import defaultdict
from copy import deepcopy
from datetime import datetime, timezone
from celery.utils.log import get_task_logger
from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
from django.db import IntegrityError, OperationalError
from django.db.models import Case, Count, IntegerField, Prefetch, Sum, When
from django.db.models import Case, Count, IntegerField, Sum, When
from tasks.utils import CustomEncoder
from api.compliance import (
PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
generate_scan_compliance,
)
from api.db_utils import (
create_objects_in_batches,
rls_transaction,
update_objects_in_batches,
)
from api.exceptions import ProviderConnectionError
from api.db_utils import rls_transaction
from api.models import (
ComplianceRequirementOverview,
ComplianceOverview,
Finding,
Processor,
Provider,
Resource,
ResourceScanSummary,
@@ -33,7 +26,7 @@ from api.models import (
StateChoices,
)
from api.models import StatusChoices as FindingStatus
from api.utils import initialize_prowler_provider, return_prowler_provider
from api.utils import initialize_prowler_provider
from api.v1.serializers import ScanTaskSerializer
from prowler.lib.outputs.finding import Finding as ProwlerFinding
from prowler.lib.scan.scan import Scan as ProwlerScan
@@ -108,10 +101,7 @@ def _store_resources(
def perform_prowler_scan(
tenant_id: str,
scan_id: str,
provider_id: str,
checks_to_execute: list[str] | None = None,
tenant_id: str, scan_id: str, provider_id: str, checks_to_execute: list[str] = None
):
"""
Perform a scan using Prowler and store the findings and resources in the database.
@@ -129,6 +119,7 @@ def perform_prowler_scan(
ValueError: If the provider cannot be connected.
"""
check_status_by_region = {}
exception = None
unique_resources = set()
scan_resource_cache: set[tuple[str, str, str, str]] = set()
@@ -142,28 +133,14 @@ def perform_prowler_scan(
scan_instance.started_at = datetime.now(tz=timezone.utc)
scan_instance.save()
# Find the mutelist processor if it exists
with rls_transaction(tenant_id):
try:
mutelist_processor = Processor.objects.get(
tenant_id=tenant_id, processor_type=Processor.ProcessorChoices.MUTELIST
)
except Processor.DoesNotExist:
mutelist_processor = None
except Exception as e:
logger.error(f"Error processing mutelist rules: {e}")
mutelist_processor = None
try:
with rls_transaction(tenant_id):
try:
prowler_provider = initialize_prowler_provider(
provider_instance, mutelist_processor
)
prowler_provider = initialize_prowler_provider(provider_instance)
provider_instance.connected = True
except Exception as e:
provider_instance.connected = False
exc = ProviderConnectionError(
exc = ValueError(
f"Provider {provider_instance.provider} is not connected: {e}"
)
finally:
@@ -173,8 +150,7 @@ def perform_prowler_scan(
provider_instance.save()
# If the provider is not connected, raise an exception outside the transaction.
# If raised within the transaction, the transaction will be rolled back and the provider will not be marked
# as not connected.
# If raised within the transaction, the transaction will be rolled back and the provider will not be marked as not connected.
if exc:
raise exc
@@ -183,7 +159,6 @@ def perform_prowler_scan(
resource_cache = {}
tag_cache = {}
last_status_cache = {}
resource_failed_findings_cache = defaultdict(int)
for progress, findings in prowler_scan.scan():
for finding in findings:
@@ -209,9 +184,6 @@ def perform_prowler_scan(
},
)
resource_cache[resource_uid] = resource_instance
# Initialize all processed resources in the cache
resource_failed_findings_cache[resource_uid] = 0
else:
resource_instance = resource_cache[resource_uid]
@@ -302,9 +274,6 @@ def perform_prowler_scan(
if not last_first_seen_at:
last_first_seen_at = datetime.now(tz=timezone.utc)
# If the finding is muted at this time the reason must be the configured Mutelist
muted_reason = "Muted by mutelist" if finding.muted else None
# Create the finding
finding_instance = Finding.objects.create(
tenant_id=tenant_id,
@@ -320,15 +289,19 @@ def perform_prowler_scan(
scan=scan_instance,
first_seen_at=last_first_seen_at,
muted=finding.muted,
muted_reason=muted_reason,
compliance=finding.compliance,
)
finding_instance.add_resources([resource_instance])
# Increment failed_findings_count cache if the finding status is FAIL and not muted
if status == FindingStatus.FAIL and not finding.muted:
resource_uid = finding.resource_uid
resource_failed_findings_cache[resource_uid] += 1
# Update compliance data if applicable
if finding.status.value == "MUTED":
continue
region_dict = check_status_by_region.setdefault(finding.region, {})
current_status = region_dict.get(finding.check_id)
if current_status == "FAIL":
continue
region_dict[finding.check_id] = finding.status.value
# Update scan resource summaries
scan_resource_cache.add(
@@ -347,24 +320,6 @@ def perform_prowler_scan(
scan_instance.state = StateChoices.COMPLETED
# Update failed_findings_count for all resources in batches if scan completed successfully
if resource_failed_findings_cache:
resources_to_update = []
for resource_uid, failed_count in resource_failed_findings_cache.items():
if resource_uid in resource_cache:
resource_instance = resource_cache[resource_uid]
resource_instance.failed_findings_count = failed_count
resources_to_update.append(resource_instance)
if resources_to_update:
update_objects_in_batches(
tenant_id=tenant_id,
model=Resource,
objects=resources_to_update,
fields=["failed_findings_count"],
batch_size=1000,
)
except Exception as e:
logger.error(f"Error performing scan {scan_id}: {e}")
exception = e
@@ -380,6 +335,63 @@ def perform_prowler_scan(
if exception is not None:
raise exception
try:
regions = prowler_provider.get_regions()
except AttributeError:
regions = set()
compliance_template = PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE[
provider_instance.provider
]
compliance_overview_by_region = {
region: deepcopy(compliance_template) for region in regions
}
for region, check_status in check_status_by_region.items():
compliance_data = compliance_overview_by_region.setdefault(
region, deepcopy(compliance_template)
)
for check_name, status in check_status.items():
generate_scan_compliance(
compliance_data,
provider_instance.provider,
check_name,
status,
)
# Prepare compliance overview objects
compliance_overview_objects = []
for region, compliance_data in compliance_overview_by_region.items():
for compliance_id, compliance in compliance_data.items():
compliance_overview_objects.append(
ComplianceOverview(
tenant_id=tenant_id,
scan=scan_instance,
region=region,
compliance_id=compliance_id,
framework=compliance["framework"],
version=compliance["version"],
description=compliance["description"],
requirements=compliance["requirements"],
requirements_passed=compliance["requirements_status"]["passed"],
requirements_failed=compliance["requirements_status"]["failed"],
requirements_manual=compliance["requirements_status"]["manual"],
total_requirements=compliance["total_requirements"],
)
)
try:
with rls_transaction(tenant_id):
ComplianceOverview.objects.bulk_create(
compliance_overview_objects, batch_size=500
)
except Exception as overview_exception:
import sentry_sdk
sentry_sdk.capture_exception(overview_exception)
logger.error(
f"Error storing compliance overview for scan {scan_id}: {overview_exception}"
)
try:
resource_scan_summaries = [
ResourceScanSummary(
@@ -417,9 +429,6 @@ def aggregate_findings(tenant_id: str, scan_id: str):
changed, unchanged). The results are grouped by `check_id`, `service`, `severity`, and `region`.
These aggregated metrics are then stored in the `ScanSummary` table.
Additionally, it updates the failed_findings_count field for each resource based on the most
recent findings for each finding.uid.
Args:
tenant_id (str): The ID of the tenant to which the scan belongs.
scan_id (str): The ID of the scan for which findings need to be aggregated.
@@ -561,123 +570,3 @@ def aggregate_findings(tenant_id: str, scan_id: str):
for agg in aggregation
}
ScanSummary.objects.bulk_create(scan_aggregations, batch_size=3000)
def create_compliance_requirements(tenant_id: str, scan_id: str):
"""
Create detailed compliance requirement overview records for a scan.
This function processes the compliance data collected during a scan and creates
individual records for each compliance requirement in each region. These detailed
records provide a granular view of compliance status.
Args:
tenant_id (str): The ID of the tenant for which to create records.
scan_id (str): The ID of the scan for which to create records.
Returns:
dict: A dictionary containing the number of requirements created and the regions processed.
Raises:
ValidationError: If tenant_id is not a valid UUID.
"""
try:
with rls_transaction(tenant_id):
scan_instance = Scan.objects.get(pk=scan_id)
provider_instance = scan_instance.provider
prowler_provider = return_prowler_provider(provider_instance)
# Get check status data by region from findings
findings = (
Finding.all_objects.filter(scan_id=scan_id, muted=False)
.only("id", "check_id", "status")
.prefetch_related(
Prefetch(
"resources",
queryset=Resource.objects.only("id", "region"),
to_attr="small_resources",
)
)
.iterator(chunk_size=1000)
)
check_status_by_region = {}
with rls_transaction(tenant_id):
for finding in findings:
for resource in finding.small_resources:
region = resource.region
current_status = check_status_by_region.setdefault(region, {})
if current_status.get(finding.check_id) != "FAIL":
current_status[finding.check_id] = finding.status
try:
# Try to get regions from provider
regions = prowler_provider.get_regions()
except (AttributeError, Exception):
# If not available, use regions from findings
regions = set(check_status_by_region.keys())
# Get compliance template for the provider
compliance_template = PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE[
provider_instance.provider
]
# Create compliance data by region
compliance_overview_by_region = {
region: deepcopy(compliance_template) for region in regions
}
# Apply check statuses to compliance data
for region, check_status in check_status_by_region.items():
compliance_data = compliance_overview_by_region.setdefault(
region, deepcopy(compliance_template)
)
for check_name, status in check_status.items():
generate_scan_compliance(
compliance_data,
provider_instance.provider,
check_name,
status,
)
# Prepare compliance requirement objects
compliance_requirement_objects = []
for region, compliance_data in compliance_overview_by_region.items():
for compliance_id, compliance in compliance_data.items():
# Create an overview record for each requirement within each compliance framework
for requirement_id, requirement in compliance["requirements"].items():
compliance_requirement_objects.append(
ComplianceRequirementOverview(
tenant_id=tenant_id,
scan=scan_instance,
region=region,
compliance_id=compliance_id,
framework=compliance["framework"],
version=compliance["version"],
requirement_id=requirement_id,
description=requirement["description"],
passed_checks=requirement["checks_status"]["pass"],
failed_checks=requirement["checks_status"]["fail"],
total_checks=requirement["checks_status"]["total"],
requirement_status=requirement["status"],
)
)
# Bulk create requirement records
create_objects_in_batches(
tenant_id, ComplianceRequirementOverview, compliance_requirement_objects
)
return {
"requirements_created": len(compliance_requirement_objects),
"regions_processed": list(regions),
"compliance_frameworks": (
list(compliance_overview_by_region.get(list(regions)[0], {}).keys())
if regions
else []
),
}
except Exception as e:
logger.error(f"Error creating compliance requirements for scan {scan_id}: {e}")
raise e

View File

@@ -8,7 +8,7 @@ from config.celery import RLSTask
from config.django.base import DJANGO_FINDINGS_BATCH_SIZE, DJANGO_TMP_OUTPUT_DIRECTORY
from django_celery_beat.models import PeriodicTask
from tasks.jobs.backfill import backfill_resource_scan_summaries
from tasks.jobs.connection import check_lighthouse_connection, check_provider_connection
from tasks.jobs.connection import check_provider_connection
from tasks.jobs.deletion import delete_provider, delete_tenant
from tasks.jobs.export import (
COMPLIANCE_CLASS_MAP,
@@ -17,11 +17,7 @@ from tasks.jobs.export import (
_generate_output_directory,
_upload_to_s3,
)
from tasks.jobs.scan import (
aggregate_findings,
create_compliance_requirements,
perform_prowler_scan,
)
from tasks.jobs.scan import aggregate_findings, perform_prowler_scan
from tasks.utils import batched, get_next_execution_datetime
from api.compliance import get_compliance_frameworks
@@ -37,26 +33,6 @@ from prowler.lib.outputs.finding import Finding as FindingOutput
logger = get_task_logger(__name__)
def _perform_scan_complete_tasks(tenant_id: str, scan_id: str, provider_id: str):
"""
Helper function to perform tasks after a scan is completed.
Args:
tenant_id (str): The tenant ID under which the scan was performed.
scan_id (str): The ID of the scan that was performed.
provider_id (str): The primary key of the Provider instance that was scanned.
"""
create_compliance_requirements_task.apply_async(
kwargs={"tenant_id": tenant_id, "scan_id": scan_id}
)
chain(
perform_scan_summary_task.si(tenant_id=tenant_id, scan_id=scan_id),
generate_outputs_task.si(
scan_id=scan_id, provider_id=provider_id, tenant_id=tenant_id
),
).apply_async()
@shared_task(base=RLSTask, name="provider-connection-check")
@set_tenant
def check_provider_connection_task(provider_id: str):
@@ -123,7 +99,12 @@ def perform_scan_task(
checks_to_execute=checks_to_execute,
)
_perform_scan_complete_tasks(tenant_id, scan_id, provider_id)
chain(
perform_scan_summary_task.si(tenant_id, scan_id),
generate_outputs.si(
scan_id=scan_id, provider_id=provider_id, tenant_id=tenant_id
),
).apply_async()
return result
@@ -228,12 +209,17 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
scheduler_task_id=periodic_task_instance.id,
)
_perform_scan_complete_tasks(tenant_id, str(scan_instance.id), provider_id)
chain(
perform_scan_summary_task.si(tenant_id, scan_instance.id),
generate_outputs.si(
scan_id=str(scan_instance.id), provider_id=provider_id, tenant_id=tenant_id
),
).apply_async()
return result
@shared_task(name="scan-summary", queue="overview")
@shared_task(name="scan-summary")
def perform_scan_summary_task(tenant_id: str, scan_id: str):
return aggregate_findings(tenant_id=tenant_id, scan_id=scan_id)
@@ -249,7 +235,7 @@ def delete_tenant_task(tenant_id: str):
queue="scan-reports",
)
@set_tenant(keep_tenant=True)
def generate_outputs_task(scan_id: str, provider_id: str, tenant_id: str):
def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
"""
Process findings in batches and generate output files in multiple formats.
@@ -385,38 +371,3 @@ def backfill_scan_resource_summaries_task(tenant_id: str, scan_id: str):
scan_id (str): The scan identifier.
"""
return backfill_resource_scan_summaries(tenant_id=tenant_id, scan_id=scan_id)
@shared_task(base=RLSTask, name="scan-compliance-overviews", queue="overview")
def create_compliance_requirements_task(tenant_id: str, scan_id: str):
"""
Creates detailed compliance requirement records for a scan.
This task processes the compliance data collected during a scan and creates
individual records for each compliance requirement in each region. These detailed
records provide a granular view of compliance status.
Args:
tenant_id (str): The tenant ID for which to create records.
scan_id (str): The ID of the scan for which to create records.
"""
return create_compliance_requirements(tenant_id=tenant_id, scan_id=scan_id)
@shared_task(base=RLSTask, name="lighthouse-connection-check")
@set_tenant
def check_lighthouse_connection_task(lighthouse_config_id: str, tenant_id: str = None):
"""
Task to check the connection status of a Lighthouse configuration.
Args:
lighthouse_config_id (str): The primary key of the LighthouseConfiguration instance to check.
tenant_id (str): The tenant ID for the task.
Returns:
dict: A dictionary containing:
- 'connected' (bool): Indicates whether the connection is successful.
- 'error' (str or None): The error message if the connection failed, otherwise `None`.
- 'available_models' (list): List of available models if connection is successful.
"""
return check_lighthouse_connection(lighthouse_config_id=lighthouse_config_id)

View File

@@ -3,9 +3,9 @@ from unittest.mock import patch
import pytest
from django_celery_beat.models import IntervalSchedule, PeriodicTask
from rest_framework_json_api.serializers import ValidationError
from tasks.beat import schedule_provider_scan
from api.exceptions import ConflictException
from api.models import Scan
@@ -48,29 +48,10 @@ class TestScheduleProviderScan:
with patch("tasks.tasks.perform_scheduled_scan_task.apply_async"):
schedule_provider_scan(provider_instance)
# Now, try scheduling again, should raise ConflictException
with pytest.raises(ConflictException) as exc_info:
# Now, try scheduling again, should raise ValidationError
with pytest.raises(ValidationError) as exc_info:
schedule_provider_scan(provider_instance)
assert "There is already a scheduled scan for this provider." in str(
exc_info.value
)
def test_remove_periodic_task(self, providers_fixture):
provider_instance = providers_fixture[0]
assert Scan.objects.count() == 0
with patch("tasks.tasks.perform_scheduled_scan_task.apply_async"):
schedule_provider_scan(provider_instance)
assert Scan.objects.count() == 1
scan = Scan.objects.first()
periodic_task = scan.scheduler_task
assert periodic_task is not None
periodic_task.delete()
scan.refresh_from_db()
# Assert the scan still exists but its scheduler_task is set to None
# Otherwise, Scan.DoesNotExist would be raised
assert Scan.objects.get(id=scan.id).scheduler_task is None

View File

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

View File

@@ -145,22 +145,3 @@ class TestOutputs:
assert path.endswith(f"{provider}-{output_file_timestamp}")
assert compliance.endswith(f"{provider}-{output_file_timestamp}")
def test_generate_output_directory_invalid_character(self, tmpdir):
from prowler.config.config import output_file_timestamp
base_tmp = Path(str(tmpdir.mkdir("generate_output")))
base_dir = str(base_tmp)
tenant_id = "t1"
scan_id = "s1"
provider = "aws/test@check"
path, compliance = _generate_output_directory(
base_dir, provider, tenant_id, scan_id
)
assert os.path.isdir(os.path.dirname(path))
assert os.path.isdir(os.path.dirname(compliance))
assert path.endswith(f"aws-test-check-{output_file_timestamp}")
assert compliance.endswith(f"aws-test-check-{output_file_timestamp}")

View File

@@ -7,14 +7,18 @@ import pytest
from tasks.jobs.scan import (
_create_finding_delta,
_store_resources,
create_compliance_requirements,
perform_prowler_scan,
)
from tasks.utils import CustomEncoder
from api.exceptions import ProviderConnectionError
from api.models import Finding, Provider, Resource, Scan, StateChoices, StatusChoices
from prowler.lib.check.models import Severity
from api.models import (
Finding,
Provider,
Resource,
Severity,
StateChoices,
StatusChoices,
)
@pytest.mark.django_db
@@ -152,7 +156,6 @@ class TestPerformScan:
assert scan_finding.raw_result == finding.raw
assert scan_finding.muted
assert scan_finding.compliance == finding.compliance
assert scan_finding.muted_reason == "Muted by mutelist"
assert scan_resource.tenant == tenant
assert scan_resource.uid == finding.resource_uid
@@ -174,9 +177,6 @@ class TestPerformScan:
assert tag_keys == set(finding.resource_tags.keys())
assert tag_values == set(finding.resource_tags.values())
# Assert that failed_findings_count is 0 (finding is PASS and muted)
assert scan_resource.failed_findings_count == 0
@patch("tasks.jobs.scan.ProwlerScan")
@patch(
"tasks.jobs.scan.initialize_prowler_provider",
@@ -201,7 +201,7 @@ class TestPerformScan:
provider_id = str(provider.id)
checks_to_execute = ["check1", "check2"]
with pytest.raises(ProviderConnectionError):
with pytest.raises(ValueError):
perform_prowler_scan(tenant_id, scan_id, provider_id, checks_to_execute)
scan.refresh_from_db()
@@ -235,7 +235,7 @@ class TestPerformScan:
):
tenant_id = uuid.uuid4()
provider_instance = MagicMock()
provider_instance.id = "provider123"
provider_instance.id = "provider456"
finding = MagicMock()
finding.resource_uid = "resource_uid_123"
@@ -250,16 +250,15 @@ class TestPerformScan:
resource_instance.region = finding.region
mock_get_or_create_resource.return_value = (resource_instance, True)
tag_instance = MagicMock()
mock_get_or_create_tag.return_value = (tag_instance, True)
resource, resource_uid_tuple = _store_resources(
finding, str(tenant_id), provider_instance
finding, tenant_id, provider_instance
)
mock_get_or_create_resource.assert_called_once_with(
tenant_id=str(tenant_id),
tenant_id=tenant_id,
provider=provider_instance,
uid=finding.resource_uid,
defaults={
@@ -306,11 +305,11 @@ class TestPerformScan:
mock_get_or_create_tag.return_value = (tag_instance, True)
resource, resource_uid_tuple = _store_resources(
finding, str(tenant_id), provider_instance
finding, tenant_id, provider_instance
)
mock_get_or_create_resource.assert_called_once_with(
tenant_id=str(tenant_id),
tenant_id=tenant_id,
provider=provider_instance,
uid=finding.resource_uid,
defaults={
@@ -364,14 +363,14 @@ class TestPerformScan:
]
resource, resource_uid_tuple = _store_resources(
finding, str(tenant_id), provider_instance
finding, tenant_id, provider_instance
)
mock_get_or_create_tag.assert_any_call(
tenant_id=str(tenant_id), key="tag1", value="value1"
tenant_id=tenant_id, key="tag1", value="value1"
)
mock_get_or_create_tag.assert_any_call(
tenant_id=str(tenant_id), key="tag2", value="value2"
tenant_id=tenant_id, key="tag2", value="value2"
)
resource_instance.upsert_or_delete_tags.assert_called_once()
tags_passed = resource_instance.upsert_or_delete_tags.call_args[1]["tags"]
@@ -381,667 +380,5 @@ class TestPerformScan:
assert resource == resource_instance
assert resource_uid_tuple == (resource_instance.uid, resource_instance.region)
def test_perform_prowler_scan_with_failed_findings(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
):
"""Test that failed findings increment the failed_findings_count"""
with (
patch("api.db_utils.rls_transaction"),
patch(
"tasks.jobs.scan.initialize_prowler_provider"
) as mock_initialize_prowler_provider,
patch("tasks.jobs.scan.ProwlerScan") as mock_prowler_scan_class,
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE",
new_callable=dict,
),
patch("api.compliance.PROWLER_CHECKS", new_callable=dict),
):
# Ensure the database is empty
assert Finding.objects.count() == 0
assert Resource.objects.count() == 0
tenant = tenants_fixture[0]
scan = scans_fixture[0]
provider = providers_fixture[0]
# Ensure the provider type is 'aws'
provider.provider = Provider.ProviderChoices.AWS
provider.save()
tenant_id = str(tenant.id)
scan_id = str(scan.id)
provider_id = str(provider.id)
# Mock a FAIL finding that is not muted
fail_finding = MagicMock()
fail_finding.uid = "fail_finding_uid"
fail_finding.status = StatusChoices.FAIL
fail_finding.status_extended = "test fail status"
fail_finding.severity = Severity.high
fail_finding.check_id = "fail_check"
fail_finding.get_metadata.return_value = {"key": "value"}
fail_finding.resource_uid = "resource_uid_fail"
fail_finding.resource_name = "fail_resource"
fail_finding.region = "us-east-1"
fail_finding.service_name = "ec2"
fail_finding.resource_type = "instance"
fail_finding.resource_tags = {"env": "test"}
fail_finding.muted = False
fail_finding.raw = {}
fail_finding.resource_metadata = {"test": "metadata"}
fail_finding.resource_details = {"details": "test"}
fail_finding.partition = "aws"
fail_finding.compliance = {"compliance1": "FAIL"}
# Mock the ProwlerScan instance
mock_prowler_scan_instance = MagicMock()
mock_prowler_scan_instance.scan.return_value = [(100, [fail_finding])]
mock_prowler_scan_class.return_value = mock_prowler_scan_instance
# Mock prowler_provider
mock_prowler_provider_instance = MagicMock()
mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
mock_initialize_prowler_provider.return_value = (
mock_prowler_provider_instance
)
# Call the function under test
perform_prowler_scan(tenant_id, scan_id, provider_id, [])
# Refresh instances from the database
scan.refresh_from_db()
scan_resource = Resource.objects.get(provider=provider)
# Assert that failed_findings_count is 1 (one FAIL finding not muted)
assert scan_resource.failed_findings_count == 1
def test_perform_prowler_scan_multiple_findings_same_resource(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
):
"""Test that multiple FAIL findings on the same resource increment the counter correctly"""
with (
patch("api.db_utils.rls_transaction"),
patch(
"tasks.jobs.scan.initialize_prowler_provider"
) as mock_initialize_prowler_provider,
patch("tasks.jobs.scan.ProwlerScan") as mock_prowler_scan_class,
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE",
new_callable=dict,
),
patch("api.compliance.PROWLER_CHECKS", new_callable=dict),
):
tenant = tenants_fixture[0]
scan = scans_fixture[0]
provider = providers_fixture[0]
provider.provider = Provider.ProviderChoices.AWS
provider.save()
tenant_id = str(tenant.id)
scan_id = str(scan.id)
provider_id = str(provider.id)
# Create multiple findings for the same resource
# Two FAIL findings (not muted) and one PASS finding
resource_uid = "shared_resource_uid"
fail_finding_1 = MagicMock()
fail_finding_1.uid = "fail_finding_1"
fail_finding_1.status = StatusChoices.FAIL
fail_finding_1.status_extended = "fail 1"
fail_finding_1.severity = Severity.high
fail_finding_1.check_id = "fail_check_1"
fail_finding_1.get_metadata.return_value = {"key": "value1"}
fail_finding_1.resource_uid = resource_uid
fail_finding_1.resource_name = "shared_resource"
fail_finding_1.region = "us-east-1"
fail_finding_1.service_name = "ec2"
fail_finding_1.resource_type = "instance"
fail_finding_1.resource_tags = {}
fail_finding_1.muted = False
fail_finding_1.raw = {}
fail_finding_1.resource_metadata = {}
fail_finding_1.resource_details = {}
fail_finding_1.partition = "aws"
fail_finding_1.compliance = {}
fail_finding_2 = MagicMock()
fail_finding_2.uid = "fail_finding_2"
fail_finding_2.status = StatusChoices.FAIL
fail_finding_2.status_extended = "fail 2"
fail_finding_2.severity = Severity.medium
fail_finding_2.check_id = "fail_check_2"
fail_finding_2.get_metadata.return_value = {"key": "value2"}
fail_finding_2.resource_uid = resource_uid
fail_finding_2.resource_name = "shared_resource"
fail_finding_2.region = "us-east-1"
fail_finding_2.service_name = "ec2"
fail_finding_2.resource_type = "instance"
fail_finding_2.resource_tags = {}
fail_finding_2.muted = False
fail_finding_2.raw = {}
fail_finding_2.resource_metadata = {}
fail_finding_2.resource_details = {}
fail_finding_2.partition = "aws"
fail_finding_2.compliance = {}
pass_finding = MagicMock()
pass_finding.uid = "pass_finding"
pass_finding.status = StatusChoices.PASS
pass_finding.status_extended = "pass"
pass_finding.severity = Severity.low
pass_finding.check_id = "pass_check"
pass_finding.get_metadata.return_value = {"key": "value3"}
pass_finding.resource_uid = resource_uid
pass_finding.resource_name = "shared_resource"
pass_finding.region = "us-east-1"
pass_finding.service_name = "ec2"
pass_finding.resource_type = "instance"
pass_finding.resource_tags = {}
pass_finding.muted = False
pass_finding.raw = {}
pass_finding.resource_metadata = {}
pass_finding.resource_details = {}
pass_finding.partition = "aws"
pass_finding.compliance = {}
# Mock the ProwlerScan instance
mock_prowler_scan_instance = MagicMock()
mock_prowler_scan_instance.scan.return_value = [
(100, [fail_finding_1, fail_finding_2, pass_finding])
]
mock_prowler_scan_class.return_value = mock_prowler_scan_instance
# Mock prowler_provider
mock_prowler_provider_instance = MagicMock()
mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
mock_initialize_prowler_provider.return_value = (
mock_prowler_provider_instance
)
# Call the function under test
perform_prowler_scan(tenant_id, scan_id, provider_id, [])
# Refresh instances from the database
scan_resource = Resource.objects.get(provider=provider, uid=resource_uid)
# Assert that failed_findings_count is 2 (two FAIL findings, one PASS)
assert scan_resource.failed_findings_count == 2
def test_perform_prowler_scan_with_muted_findings(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
):
"""Test that muted FAIL findings do not increment the failed_findings_count"""
with (
patch("api.db_utils.rls_transaction"),
patch(
"tasks.jobs.scan.initialize_prowler_provider"
) as mock_initialize_prowler_provider,
patch("tasks.jobs.scan.ProwlerScan") as mock_prowler_scan_class,
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE",
new_callable=dict,
),
patch("api.compliance.PROWLER_CHECKS", new_callable=dict),
):
tenant = tenants_fixture[0]
scan = scans_fixture[0]
provider = providers_fixture[0]
provider.provider = Provider.ProviderChoices.AWS
provider.save()
tenant_id = str(tenant.id)
scan_id = str(scan.id)
provider_id = str(provider.id)
# Mock a FAIL finding that is muted
muted_fail_finding = MagicMock()
muted_fail_finding.uid = "muted_fail_finding"
muted_fail_finding.status = StatusChoices.FAIL
muted_fail_finding.status_extended = "muted fail"
muted_fail_finding.severity = Severity.high
muted_fail_finding.check_id = "muted_fail_check"
muted_fail_finding.get_metadata.return_value = {"key": "value"}
muted_fail_finding.resource_uid = "muted_resource_uid"
muted_fail_finding.resource_name = "muted_resource"
muted_fail_finding.region = "us-east-1"
muted_fail_finding.service_name = "ec2"
muted_fail_finding.resource_type = "instance"
muted_fail_finding.resource_tags = {}
muted_fail_finding.muted = True
muted_fail_finding.raw = {}
muted_fail_finding.resource_metadata = {}
muted_fail_finding.resource_details = {}
muted_fail_finding.partition = "aws"
muted_fail_finding.compliance = {}
# Mock the ProwlerScan instance
mock_prowler_scan_instance = MagicMock()
mock_prowler_scan_instance.scan.return_value = [(100, [muted_fail_finding])]
mock_prowler_scan_class.return_value = mock_prowler_scan_instance
# Mock prowler_provider
mock_prowler_provider_instance = MagicMock()
mock_prowler_provider_instance.get_regions.return_value = ["us-east-1"]
mock_initialize_prowler_provider.return_value = (
mock_prowler_provider_instance
)
# Call the function under test
perform_prowler_scan(tenant_id, scan_id, provider_id, [])
# Refresh instances from the database
scan_resource = Resource.objects.get(provider=provider)
# Assert that failed_findings_count is 0 (FAIL finding is muted)
assert scan_resource.failed_findings_count == 0
def test_perform_prowler_scan_reset_failed_findings_count(
self,
tenants_fixture,
providers_fixture,
resources_fixture,
):
"""Test that failed_findings_count is reset to 0 at the beginning of each scan"""
# Use existing resource from fixture and set initial failed_findings_count
tenant = tenants_fixture[0]
provider = providers_fixture[0]
resource = resources_fixture[0]
# Set a non-zero failed_findings_count initially
resource.failed_findings_count = 5
resource.save()
# Create a new scan
scan = Scan.objects.create(
name="Reset Test Scan",
provider=provider,
trigger=Scan.TriggerChoices.MANUAL,
state=StateChoices.AVAILABLE,
tenant_id=tenant.id,
)
with (
patch("api.db_utils.rls_transaction"),
patch(
"tasks.jobs.scan.initialize_prowler_provider"
) as mock_initialize_prowler_provider,
patch("tasks.jobs.scan.ProwlerScan") as mock_prowler_scan_class,
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE",
new_callable=dict,
),
patch("api.compliance.PROWLER_CHECKS", new_callable=dict),
):
provider.provider = Provider.ProviderChoices.AWS
provider.save()
tenant_id = str(tenant.id)
scan_id = str(scan.id)
provider_id = str(provider.id)
# Mock a PASS finding for the existing resource
pass_finding = MagicMock()
pass_finding.uid = "reset_test_finding"
pass_finding.status = StatusChoices.PASS
pass_finding.status_extended = "reset test pass"
pass_finding.severity = Severity.low
pass_finding.check_id = "reset_test_check"
pass_finding.get_metadata.return_value = {"key": "value"}
pass_finding.resource_uid = resource.uid
pass_finding.resource_name = resource.name
pass_finding.region = resource.region
pass_finding.service_name = resource.service
pass_finding.resource_type = resource.type
pass_finding.resource_tags = {}
pass_finding.muted = False
pass_finding.raw = {}
pass_finding.resource_metadata = {}
pass_finding.resource_details = {}
pass_finding.partition = "aws"
pass_finding.compliance = {}
# Mock the ProwlerScan instance
mock_prowler_scan_instance = MagicMock()
mock_prowler_scan_instance.scan.return_value = [(100, [pass_finding])]
mock_prowler_scan_class.return_value = mock_prowler_scan_instance
# Mock prowler_provider
mock_prowler_provider_instance = MagicMock()
mock_prowler_provider_instance.get_regions.return_value = [resource.region]
mock_initialize_prowler_provider.return_value = (
mock_prowler_provider_instance
)
# Call the function under test
perform_prowler_scan(tenant_id, scan_id, provider_id, [])
# Refresh resource from the database
resource.refresh_from_db()
# Assert that failed_findings_count was reset to 0 during the scan
assert resource.failed_findings_count == 0
# TODO Add tests for aggregations
@pytest.mark.django_db
class TestCreateComplianceRequirements:
def test_create_compliance_requirements_success(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
resources_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {
"cis_1.4_aws": {
"framework": "CIS AWS Foundations Benchmark",
"version": "1.4.0",
"requirements": {
"1.1": {
"description": "Ensure root access key does not exist",
"checks_status": {
"pass": 0,
"fail": 0,
"manual": 0,
"total": 1,
},
"status": "PASS",
},
"1.2": {
"description": "Ensure MFA is enabled for root account",
"checks_status": {
"pass": 0,
"fail": 1,
"manual": 0,
"total": 1,
},
"status": "FAIL",
},
},
},
}
result = create_compliance_requirements(tenant_id, scan_id)
assert "requirements_created" in result
assert "regions_processed" in result
assert "compliance_frameworks" in result
def test_create_compliance_requirements_with_findings(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {
"test_compliance": {
"framework": "Test Framework",
"version": "1.0",
"requirements": {
"req_1": {
"description": "Test Requirement 1",
"checks_status": {
"pass": 2,
"fail": 1,
"manual": 0,
"total": 3,
},
"status": "FAIL",
},
},
}
}
result = create_compliance_requirements(tenant_id, scan_id)
assert "requirements_created" in result
def test_create_compliance_requirements_kubernetes_provider(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant = tenants_fixture[0]
scan = scans_fixture[0]
provider = providers_fixture[0]
provider.provider = Provider.ProviderChoices.KUBERNETES
provider.save()
scan.provider = provider
scan.save()
tenant_id = str(tenant.id)
scan_id = str(scan.id)
mock_compliance_template.__getitem__.return_value = {
"kubernetes_cis": {
"framework": "CIS Kubernetes Benchmark",
"version": "1.6.0",
"requirements": {
"1.1": {
"description": "Test requirement",
"checks_status": {
"pass": 0,
"fail": 0,
"manual": 0,
"total": 1,
},
"status": "PASS",
},
},
},
}
result = create_compliance_requirements(tenant_id, scan_id)
assert "regions_processed" in result
def test_create_compliance_requirements_empty_template(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {}
result = create_compliance_requirements(tenant_id, scan_id)
assert result["requirements_created"] == 0
def test_create_compliance_requirements_error_handling(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with patch("tasks.jobs.scan.return_prowler_provider") as mock_prowler_provider:
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_prowler_provider.side_effect = Exception(
"Provider initialization failed"
)
with pytest.raises(Exception, match="Provider initialization failed"):
create_compliance_requirements(tenant_id, scan_id)
def test_create_compliance_requirements_check_status_priority(
self, tenants_fixture, scans_fixture, providers_fixture, findings_fixture
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch(
"tasks.jobs.scan.generate_scan_compliance"
) as mock_generate_compliance,
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {
"cis_1.4_aws": {
"framework": "CIS AWS Foundations Benchmark",
"version": "1.4.0",
"requirements": {
"1.1": {
"description": "Test requirement",
"checks_status": {
"pass": 0,
"fail": 0,
"manual": 0,
"total": 1,
},
"status": "PASS",
},
},
},
}
create_compliance_requirements(tenant_id, scan_id)
assert mock_generate_compliance.call_count == 1
def test_create_compliance_requirements_multiple_regions(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {
"test_compliance": {
"framework": "Test Framework",
"version": "1.0",
"requirements": {
"req_1": {
"description": "Test Requirement 1",
"checks_status": {
"pass": 2,
"fail": 0,
"manual": 0,
"total": 2,
},
"status": "PASS",
}
},
}
}
result = create_compliance_requirements(tenant_id, scan_id)
assert "requirements_created" in result
assert len(result["regions_processed"]) >= 0
def test_create_compliance_requirements_mixed_status_requirements(
self,
tenants_fixture,
scans_fixture,
providers_fixture,
findings_fixture,
):
with (
patch(
"tasks.jobs.scan.PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE"
) as mock_compliance_template,
patch("tasks.jobs.scan.generate_scan_compliance"),
):
tenant_id = str(tenants_fixture[0].id)
scan_id = str(scans_fixture[0].id)
mock_compliance_template.__getitem__.return_value = {
"test_compliance": {
"framework": "Test Framework",
"version": "1.0",
"requirements": {
"req_1": {
"description": "Test Requirement 1",
"checks_status": {
"pass": 2,
"fail": 0,
"manual": 0,
"total": 2,
},
"status": "PASS",
},
"req_2": {
"description": "Test Requirement 2",
"checks_status": {
"pass": 1,
"fail": 1,
"manual": 0,
"total": 2,
},
"status": "FAIL",
},
},
}
}
result = create_compliance_requirements(tenant_id, scan_id)
assert "requirements_created" in result
assert result["requirements_created"] >= 0

View File

@@ -3,10 +3,9 @@ from pathlib import Path
from unittest.mock import MagicMock, patch
import pytest
from tasks.tasks import _perform_scan_complete_tasks, generate_outputs_task
from tasks.tasks import generate_outputs
# TODO Move this to outputs/reports jobs
@pytest.mark.django_db
class TestGenerateOutputs:
def setup_method(self):
@@ -18,7 +17,7 @@ class TestGenerateOutputs:
with patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter:
mock_filter.return_value.exists.return_value = False
result = generate_outputs_task(
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
@@ -100,7 +99,7 @@ class TestGenerateOutputs:
mock_compress.return_value = "/tmp/zipped.zip"
mock_upload.return_value = "s3://bucket/zipped.zip"
result = generate_outputs_task(
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
@@ -151,7 +150,7 @@ class TestGenerateOutputs:
True,
]
result = generate_outputs_task(
result = generate_outputs(
scan_id="scan",
provider_id="provider",
tenant_id=self.tenant_id,
@@ -209,7 +208,7 @@ class TestGenerateOutputs:
{"aws": [(lambda x: True, MagicMock())]},
),
):
generate_outputs_task(
generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
@@ -277,7 +276,7 @@ class TestGenerateOutputs:
}
},
):
result = generate_outputs_task(
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
@@ -347,7 +346,7 @@ class TestGenerateOutputs:
):
mock_summary.return_value.exists.return_value = True
result = generate_outputs_task(
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
@@ -408,31 +407,9 @@ class TestGenerateOutputs:
),
):
with caplog.at_level("ERROR"):
generate_outputs_task(
generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert "Error deleting output files" in caplog.text
class TestScanCompleteTasks:
@patch("tasks.tasks.create_compliance_requirements_task.apply_async")
@patch("tasks.tasks.perform_scan_summary_task.si")
@patch("tasks.tasks.generate_outputs_task.si")
def test_scan_complete_tasks(
self, mock_outputs_task, mock_scan_summary_task, mock_compliance_tasks
):
_perform_scan_complete_tasks("tenant-id", "scan-id", "provider-id")
mock_compliance_tasks.assert_called_once_with(
kwargs={"tenant_id": "tenant-id", "scan_id": "scan-id"},
)
mock_scan_summary_task.assert_called_once_with(
scan_id="scan-id",
tenant_id="tenant-id",
)
mock_outputs_task.assert_called_once_with(
scan_id="scan-id",
provider_id="provider-id",
tenant_id="tenant-id",
)

View File

@@ -1,128 +0,0 @@
import random
from collections import defaultdict
import requests
from locust import events, task
from utils.helpers import APIUserBase, get_api_token, get_auth_headers
GLOBAL = {
"token": None,
"available_scans_info": {},
}
SUPPORTED_COMPLIANCE_IDS = {
"aws": ["ens_rd2022", "cis_2.0", "prowler_threatscore", "soc2"],
"gcp": ["ens_rd2022", "cis_2.0", "prowler_threatscore", "soc2"],
"azure": ["ens_rd2022", "cis_2.0", "prowler_threatscore", "soc2"],
"m365": ["cis_4.0", "iso27001_2022", "prowler_threatscore"],
}
def _get_random_scan() -> tuple:
provider_type = random.choice(list(GLOBAL["available_scans_info"].keys()))
scan_info = random.choice(GLOBAL["available_scans_info"][provider_type])
return provider_type, scan_info
def _get_random_compliance_id(provider: str) -> str:
return f"{random.choice(SUPPORTED_COMPLIANCE_IDS[provider])}_{provider}"
def _get_compliance_available_scans_by_provider_type(host: str, token: str) -> dict:
excluded_providers = ["kubernetes"]
response_dict = defaultdict(list)
provider_response = requests.get(
f"{host}/providers?fields[providers]=id,provider&filter[connected]=true",
headers=get_auth_headers(token),
)
for provider in provider_response.json()["data"]:
provider_id = provider["id"]
provider_type = provider["attributes"]["provider"]
if provider_type in excluded_providers:
continue
scan_response = requests.get(
f"{host}/scans?fields[scans]=id&filter[provider]={provider_id}&filter[state]=completed",
headers=get_auth_headers(token),
)
scan_data = scan_response.json()["data"]
if not scan_data:
continue
scan_id = scan_data[0]["id"]
response_dict[provider_type].append(scan_id)
return response_dict
def _get_compliance_regions_from_scan(host: str, token: str, scan_id: str) -> list:
response = requests.get(
f"{host}/compliance-overviews/metadata?filter[scan_id]={scan_id}",
headers=get_auth_headers(token),
)
assert response.status_code == 200, f"Failed to get scan: {response.text}"
return response.json()["data"]["attributes"]["regions"]
@events.test_start.add_listener
def on_test_start(environment, **kwargs):
GLOBAL["token"] = get_api_token(environment.host)
scans_by_provider = _get_compliance_available_scans_by_provider_type(
environment.host, GLOBAL["token"]
)
scan_info = defaultdict(list)
for provider, scans in scans_by_provider.items():
for scan in scans:
scan_info[provider].append(
{
"scan_id": scan,
"regions": _get_compliance_regions_from_scan(
environment.host, GLOBAL["token"], scan
),
}
)
GLOBAL["available_scans_info"] = scan_info
class APIUser(APIUserBase):
def on_start(self):
self.token = GLOBAL["token"]
@task(3)
def compliance_overviews_default(self):
provider_type, scan_info = _get_random_scan()
name = f"/compliance-overviews ({provider_type})"
endpoint = f"/compliance-overviews?" f"filter[scan_id]={scan_info['scan_id']}"
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task(2)
def compliance_overviews_region(self):
provider_type, scan_info = _get_random_scan()
name = f"/compliance-overviews?filter[region] ({provider_type})"
endpoint = (
f"/compliance-overviews"
f"?filter[scan_id]={scan_info['scan_id']}"
f"&filter[region]={random.choice(scan_info['regions'])}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task(2)
def compliance_overviews_requirements(self):
provider_type, scan_info = _get_random_scan()
compliance_id = _get_random_compliance_id(provider_type)
name = f"/compliance-overviews/requirements ({compliance_id})"
endpoint = (
f"/compliance-overviews/requirements"
f"?filter[scan_id]={scan_info['scan_id']}"
f"&filter[compliance_id]={compliance_id}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def compliance_overviews_attributes(self):
provider_type, _ = _get_random_scan()
compliance_id = _get_random_compliance_id(provider_type)
name = f"/compliance-overviews/attributes ({compliance_id})"
endpoint = (
f"/compliance-overviews/attributes"
f"?filter[compliance_id]={compliance_id}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)

View File

@@ -1,117 +0,0 @@
# Prowler Multicloud CIS Benchmarks PowerBI Template
![Prowler Report](https://github.com/user-attachments/assets/560f7f83-1616-4836-811a-16963223c72f)
## Getting Started
1. Install Microsoft PowerBI Desktop
This report requires the Microsoft PowerBI Desktop software which can be downloaded for free from Microsoft.
2. Run compliance scans in Prowler
The report uses compliance csv outputs from Prowler. Compliance scans be run using either [Prowler CLI](https://docs.prowler.com/projects/prowler-open-source/en/latest/#prowler-cli) or [Prowler Cloud/App](https://cloud.prowler.com/sign-in)
1. Prowler CLI -&gt; Run a Prowler scan using the --compliance option
2. Prowler Cloud/App -&gt; Navigate to the compliance section to download csv outputs
![Download Compliance Scan](https://github.com/user-attachments/assets/42c11a60-8ce8-4c60-a663-2371199c052b)
The template supports the following CIS Benchmarks only:
| Compliance Framework | Version |
| ---------------------------------------------- | ------- |
| CIS Amazon Web Services Foundations Benchmark | v4.0.1 |
| CIS Google Cloud Platform Foundation Benchmark | v3.0.0 |
| CIS Microsoft Azure Foundations Benchmark | v3.0.0 |
| CIS Kubernetes Benchmark | v1.10.0 |
Ensure you run or download the correct benchmark versions.
3. Create a local directory to store Prowler csvoutputs
Once downloaded, place your csv outputs in a directory on your local machine. If you rename the files, they must maintain the provider in the filename.
To use time-series capabilities such as "compliance percent over time" you'll need scans from multiple dates.
4. Download and run the PowerBI template file (.pbit)
Running the .pbit file will open PowerBI Desktop and prompt you for the full filepath to the local directory
5. Enter the full filepath to the directory created in step 3
Provide the full filepath from the root directory.
Ensure that the filepath is not wrapped in quotation marks (""). If you use Window's "copy as path" feature, it will automatically include quotation marks.
6. Save the report as a PowerBI file (.pbix)
Once the filepath is entered, the template will automatically ingest and populate the report. You can then save this file as a new PowerBI report. If you'd like to generate another report, simply re-run the template file (.pbit) from step 4.
## Validation
After setting up your dashboard, you may want to validate the Prowler csv files were ingested correctly. To do this, navigate to the "Configuration" tab.
The "loaded CIS Benchmarks" table shows the supported benchmarks and versions. This is defined by the template file and not editable by the user. All benchmarks will be loaded regardless of which providers you provided csv outputs for.
The "Prowler CSV Folder" shows the path to the local directory you provided.
The "Loaded Prowler Exports" table shows the ingested csv files from the local directory. It will mark files that are treated as the latest assessment with a green checkmark.
![Prowler Validation](https://github.com/user-attachments/assets/a543ca9b-6cbe-4ad1-b32a-d4ac2163d447)
## Report Sections
The PowerBI Report is broken into three main report pages
| Report Page | Description |
| ----------- | ----------------------------------------------------------------------------------- |
| Overview | Provides general CIS Benchmark overview across both AWS, Azure, GCP, and Kubernetes |
| Benchmark | Provides overview of a single CIS Benchmark |
| Requirement | Drill-through page to view details of a single requirement |
### Overview Page
The overview page is a general CIS Benchmark overview across both AWS, Azure, GCP, and Kubernetes.
![image](https://github.com/user-attachments/assets/94164fa9-36a4-4bb9-890d-e9a9a63a3e7d)
The page has the following components:
| Component | Description |
| ---------------------------------------- | ------------------------------------------------------------------------ |
| CIS Benchmark Overview | Table with benchmark name, Version, and overall compliance percentage |
| Provider by Requirement Status | Bar chart showing benchmark requirements by status by provider |
| Compliance Percent Heatmap | Heatmap showing compliance percent by benchmark and profile level |
| Profile level by Requirement Status | Bar chart showing requirements by status and profile level |
| Compliance Percent Over Time by Provider | Line chart showing overall compliance perecentage over time by provider. |
### Benchmark Page
The benchmark page provides an overview of a single CIS Benchmark. You can select the benchmark from the dropdown as well as scope down to specific profile levels or regions.
![image](https://github.com/user-attachments/assets/34498ee8-317b-4b81-b241-c561451d8def)
The page has the following components:
| Component | Description |
| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| Compliance Percent Heatmap | Heatmap showing compliance percent by region and profile level |
| Benchmark Section by Requirement Status | Bar chart showing benchmark requirements by bennchmark section and status |
| Compliance percent Over Time by Region | Line chart showing overall compliance percentage over time by region |
| Benchmark Requirements | Table showing requirement section, requirement number, reuqirement title, number of resources tested, status, and number of failing checks |
### Requirement Page
The requirement page is a drill-through page to view details of a single requirement. To populate the requirement page right click on a requiement from the "Benchmark Requirements" table on the benchmark page and select "Drill through" -&gt; "Requirement".
![image](https://github.com/user-attachments/assets/5c9172d9-56fe-4514-b341-7e708863fad6)
The requirement page has the following components:
| Component | Description |
| ------------------------------------------ | --------------------------------------------------------------------------------- |
| Title | Title of the requirement |
| Rationale | Rationale of the requirement |
| Remediation | Remedation guidance for the requirement |
| Region by Check Status | Bar chart showing Prowler checks by region and status |
| Resource Checks for Benchmark Requirements | Table showing Resource ID, Resource Name, Status, Description, and Prowler Checkl |
## Walkthrough Video
[![image](https://github.com/user-attachments/assets/866642c6-43ac-4aac-83d3-bb625002da0b)](https://www.youtube.com/watch?v=lfKFkTqBxjU)

View File

@@ -23,7 +23,6 @@ import argparse
import json
import os
import re
import shlex
import signal
import socket
import subprocess
@@ -146,11 +145,11 @@ def _get_script_arguments():
def _run_prowler(prowler_args):
_debug("Running prowler with args: {0}".format(prowler_args), 1)
_prowler_command = shlex.split(
"{prowler}/prowler {args}".format(prowler=PATH_TO_PROWLER, args=prowler_args)
_prowler_command = "{prowler}/prowler {args}".format(
prowler=PATH_TO_PROWLER, args=prowler_args
)
_debug("Running command: {0}".format(" ".join(_prowler_command)), 2)
_process = subprocess.Popen(_prowler_command, stdout=subprocess.PIPE)
_debug("Running command: {0}".format(_prowler_command), 2)
_process = subprocess.Popen(_prowler_command, stdout=subprocess.PIPE, shell=True)
_output, _error = _process.communicate()
_debug("Raw prowler output: {0}".format(_output), 3)
_debug("Raw prowler error: {0}".format(_error), 3)

View File

@@ -1,23 +0,0 @@
import warnings
from dashboard.common_methods import get_section_container_iso
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ATTRIBUTES_CATEGORY",
"REQUIREMENTS_ATTRIBUTES_OBJETIVE_ID",
"REQUIREMENTS_ATTRIBUTES_OBJETIVE_NAME",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
]
return get_section_container_iso(
aux, "REQUIREMENTS_ATTRIBUTES_CATEGORY", "REQUIREMENTS_ATTRIBUTES_OBJETIVE_ID"
)

View File

@@ -1,43 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_3_levels
warnings.filterwarnings("ignore")
def get_table(data):
data["REQUIREMENTS_DESCRIPTION"] = (
data["REQUIREMENTS_ID"] + " - " + data["REQUIREMENTS_DESCRIPTION"]
)
data["REQUIREMENTS_DESCRIPTION"] = data["REQUIREMENTS_DESCRIPTION"].apply(
lambda x: x[:150] + "..." if len(str(x)) > 150 else x
)
data["REQUIREMENTS_ATTRIBUTES_SECTION"] = data[
"REQUIREMENTS_ATTRIBUTES_SECTION"
].apply(lambda x: x[:80] + "..." if len(str(x)) > 80 else x)
data["REQUIREMENTS_ATTRIBUTES_SUBSECTION"] = data[
"REQUIREMENTS_ATTRIBUTES_SUBSECTION"
].apply(lambda x: x[:150] + "..." if len(str(x)) > 150 else x)
aux = data[
[
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
]
return get_section_containers_3_levels(
aux,
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"REQUIREMENTS_DESCRIPTION",
)

View File

@@ -4,10 +4,7 @@ from dash import html
def create_provider_card(
provider: str,
provider_logo: str,
account_type: str,
filtered_data,
provider: str, provider_logo: str, account_type: str, filtered_data
) -> List[html.Div]:
"""
Card to display the provider's name and icon.

View File

@@ -245,31 +245,6 @@ def create_service_dropdown(services: list) -> html.Div:
)
def create_provider_dropdown(providers: list) -> html.Div:
"""
Dropdown to select the provider.
Args:
providers (list): List of providers.
Returns:
html.Div: Dropdown to select the provider.
"""
return html.Div(
[
html.Label(
"Provider:", className="text-prowler-stone-900 font-bold text-sm"
),
dcc.Dropdown(
id="provider-filter",
options=[{"label": i, "value": i} for i in providers],
value=["All"],
clearable=False,
multi=True,
style={"color": "#000000"},
),
],
)
def create_status_dropdown(status: list) -> html.Div:
"""
Dropdown to select the status.

View File

@@ -9,11 +9,9 @@ def create_layout_overview(
download_button_xlsx: html.Button,
severity_dropdown: html.Div,
service_dropdown: html.Div,
provider_dropdown: html.Div,
table_row_dropdown: html.Div,
status_dropdown: html.Div,
table_div_header: html.Div,
amount_providers: int,
) -> html.Div:
"""
Create the layout of the dashboard.
@@ -49,10 +47,9 @@ def create_layout_overview(
[
html.Div([severity_dropdown], className=""),
html.Div([service_dropdown], className=""),
html.Div([provider_dropdown], className=""),
html.Div([status_dropdown], className=""),
],
className="grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-4",
className="grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-3",
),
html.Div(
[
@@ -62,7 +59,7 @@ def create_layout_overview(
html.Div(className="flex", id="k8s_card", n_clicks=0),
html.Div(className="flex", id="m365_card", n_clicks=0),
],
className=f"grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-{amount_providers}",
className="grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-5",
),
html.H4(
"Count of Findings by severity",

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