Compare commits

..

19 Commits

Author SHA1 Message Date
Pablo Lara
a75755c8c5 WIP: add change role to the user's invitations 2024-12-15 10:37:51 +01:00
Pablo Lara
3e0568f381 chore: add change role to the user's invitations 2024-12-13 12:38:08 +01:00
Pablo Lara
fec66a3685 Merge branch 'master' into PRWLR-4669-Roles-Page-API-UI 2024-12-13 06:02:29 +01:00
Pablo Lara
ba335de6b3 chore: fix error with exports 2024-12-11 08:30:12 +01:00
Pablo Lara
93051d55d5 feat: add role when invite an user 2024-12-10 18:14:57 +01:00
Pablo Lara
161c56ffe4 feat: add permission column to roles table 2024-12-10 11:28:10 +01:00
Pablo Lara
e306322630 Merge branch 'PRWLR-5688-Implement-permission-status-filter' into PRWLR-4669-Roles-Page-API-UI 2024-12-10 10:47:14 +01:00
Adrián Jesús Peña Rodríguez
b4eb6e8076 feat(rbac): add permission_state field to role serializer 2024-12-10 10:45:09 +01:00
Pablo Lara
b54e9334b9 chore: add and edit roles is working now 2024-12-10 10:44:34 +01:00
Adrián Jesús Peña Rodríguez
5fd1af7559 feat(rbac): add permission_state filter 2024-12-10 10:33:26 +01:00
Pablo Lara
83c7ced6ff Merge branch 'feat-rbac' into PRWLR-4669-Roles-Page-API-UI 2024-12-10 09:29:24 +01:00
Adrián Jesús Peña Rodríguez
67d9ff2419 ref(provider_groups): ref the provider_groups relationships endpoint (#6033) 2024-12-10 09:28:22 +01:00
Pablo Lara
130fddae1e feat: edit role feature 2024-12-10 09:08:25 +01:00
Pablo Lara
04b9f81e26 feat: add new role feature 2024-12-10 07:24:01 +01:00
Pablo Lara
29bc697487 feat: add roles page 2024-12-05 15:25:07 +01:00
Pablo Lara
381aa93f55 chore: add roles item to the sidebar 2024-12-05 09:12:31 +01:00
Adrián Jesús Peña Rodríguez
2bee4b986f Merge branch 'master' into feat-rbac 2024-12-04 15:42:47 +01:00
Adrián Jesús Peña Rodríguez
9723b8fac1 Merge branch 'master' into feat-rbac 2024-12-04 12:51:39 +01:00
Adrián Jesús Peña Rodríguez
67ef67add9 feat(api-rbac): RBAC system (#5903) 2024-11-26 12:32:55 +01:00
2678 changed files with 36549 additions and 207853 deletions

58
.env
View File

@@ -3,17 +3,16 @@
# For production, it is recommended to use a secure method to store these variables and change the default secret keys.
#### Prowler UI Configuration ####
PROWLER_UI_VERSION="stable"
AUTH_URL=http://localhost:3000
PROWLER_UI_VERSION="latest"
SITE_URL=http://localhost:3000
API_BASE_URL=http://prowler-api:8080/api/v1
NEXT_PUBLIC_API_DOCS_URL=http://prowler-api:8080/api/v1/docs
AUTH_TRUST_HOST=true
UI_PORT=3000
# openssl rand -base64 32
AUTH_SECRET="N/c6mnaS5+SWq81+819OrzQZlmx1Vxtp/orjttJSmw8="
#### Prowler API Configuration ####
PROWLER_API_VERSION="stable"
PROWLER_API_VERSION="latest"
# PostgreSQL settings
# If running Django and celery on host, use 'localhost', else use 'postgres-db'
POSTGRES_HOST=postgres-db
@@ -30,30 +29,6 @@ VALKEY_HOST=valkey
VALKEY_PORT=6379
VALKEY_DB=0
# API scan settings
# The path to the directory where scan output should be stored
DJANGO_TMP_OUTPUT_DIRECTORY="/tmp/prowler_api_output"
# The maximum number of findings to process in a single batch
DJANGO_FINDINGS_BATCH_SIZE=1000
# The AWS access key to be used when uploading scan output to an S3 bucket
# If left empty, default AWS credentials resolution behavior will be used
DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID=""
# The AWS secret key to be used when uploading scan output to an S3 bucket
DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY=""
# An optional AWS session token
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN=""
# The AWS region where your S3 bucket is located (e.g., "us-east-1")
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION=""
# The name of the S3 bucket where scan output should be stored
DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET=""
# Django settings
DJANGO_ALLOWED_HOSTS=localhost,127.0.0.1,prowler-api
DJANGO_BIND_ADDRESS=0.0.0.0
@@ -65,12 +40,9 @@ DJANGO_LOGGING_FORMATTER=human_readable
# Select one of [DEBUG|INFO|WARNING|ERROR|CRITICAL]
# Applies to both Django and Celery Workers
DJANGO_LOGGING_LEVEL=INFO
# Defaults to the maximum available based on CPU cores if not set.
DJANGO_WORKERS=4
# Token lifetime is in minutes
DJANGO_ACCESS_TOKEN_LIFETIME=30
# Token lifetime is in minutes
DJANGO_REFRESH_TOKEN_LIFETIME=1440
DJANGO_WORKERS=4 # Defaults to the maximum available based on CPU cores if not set.
DJANGO_ACCESS_TOKEN_LIFETIME=30 # Token lifetime is in minutes
DJANGO_REFRESH_TOKEN_LIFETIME=1440 # Token lifetime is in minutes
DJANGO_CACHE_MAX_AGE=3600
DJANGO_STALE_WHILE_REVALIDATE=60
DJANGO_MANAGE_DB_PARTITIONS=True
@@ -115,21 +87,3 @@ jQIDAQAB
-----END PUBLIC KEY-----"
# openssl rand -base64 32
DJANGO_SECRETS_ENCRYPTION_KEY="oE/ltOhp/n1TdbHjVmzcjDPLcLA41CVI/4Rk+UB5ESc="
DJANGO_BROKER_VISIBILITY_TIMEOUT=86400
DJANGO_SENTRY_DSN=
# Sentry settings
SENTRY_ENVIRONMENT=local
SENTRY_RELEASE=local
#### Prowler release version ####
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.5.1
# Social login credentials
SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
SOCIAL_GOOGLE_OAUTH_CLIENT_ID=""
SOCIAL_GOOGLE_OAUTH_CLIENT_SECRET=""
SOCIAL_GITHUB_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/github"
SOCIAL_GITHUB_OAUTH_CLIENT_ID=""
SOCIAL_GITHUB_OAUTH_CLIENT_SECRET=""

View File

@@ -16,18 +16,6 @@ updates:
- "dependencies"
- "pip"
# Dependabot Updates are temporary disabled - 2025/03/19
# - package-ecosystem: "pip"
# directory: "/api"
# schedule:
# interval: "daily"
# open-pull-requests-limit: 10
# target-branch: master
# labels:
# - "dependencies"
# - "pip"
# - "component/api"
- package-ecosystem: "github-actions"
directory: "/"
schedule:
@@ -38,27 +26,15 @@ updates:
- "dependencies"
- "github_actions"
# Dependabot Updates are temporary disabled - 2025/03/19
# - package-ecosystem: "npm"
# directory: "/ui"
# schedule:
# interval: "daily"
# open-pull-requests-limit: 10
# target-branch: master
# labels:
# - "dependencies"
# - "npm"
# - "component/ui"
- package-ecosystem: "docker"
- package-ecosystem: "npm"
directory: "/"
schedule:
interval: "weekly"
interval: "daily"
open-pull-requests-limit: 10
target-branch: master
labels:
- "dependencies"
- "docker"
- "npm"
# v4.6
- package-ecosystem: "pip"
@@ -83,29 +59,17 @@ updates:
- "github_actions"
- "v4"
- package-ecosystem: "docker"
# v3
- package-ecosystem: "pip"
directory: "/"
schedule:
interval: "weekly"
interval: "monthly"
open-pull-requests-limit: 10
target-branch: v4.6
target-branch: v3
labels:
- "dependencies"
- "docker"
- "v4"
# Dependabot Updates are temporary disabled - 2025/03/19
# v3
# - package-ecosystem: "pip"
# directory: "/"
# schedule:
# interval: "monthly"
# open-pull-requests-limit: 10
# target-branch: v3
# labels:
# - "dependencies"
# - "pip"
# - "v3"
- "pip"
- "v3"
- package-ecosystem: "github-actions"
directory: "/"

15
.github/labeler.yml vendored
View File

@@ -22,11 +22,6 @@ provider/kubernetes:
- any-glob-to-any-file: "prowler/providers/kubernetes/**"
- any-glob-to-any-file: "tests/providers/kubernetes/**"
provider/github:
- changed-files:
- any-glob-to-any-file: "prowler/providers/github/**"
- any-glob-to-any-file: "tests/providers/github/**"
github_actions:
- changed-files:
- any-glob-to-any-file: ".github/workflows/*"
@@ -92,13 +87,3 @@ component/api:
component/ui:
- changed-files:
- any-glob-to-any-file: "ui/**"
compliance:
- changed-files:
- any-glob-to-any-file: "prowler/compliance/**"
- any-glob-to-any-file: "prowler/lib/outputs/compliance/**"
- any-glob-to-any-file: "tests/lib/outputs/compliance/**"
review-django-migrations:
- changed-files:
- any-glob-to-any-file: "api/src/backend/api/migrations/**"

View File

@@ -15,13 +15,7 @@ Please include a summary of the change and which issue is fixed. List any depend
- [ ] Review if the code is being covered by tests.
- [ ] Review if code is being documented following this specification https://github.com/google/styleguide/blob/gh-pages/pyguide.md#38-comments-and-docstrings
- [ ] Review if backport is needed.
- [ ] Review if is needed to change the [Readme.md](https://github.com/prowler-cloud/prowler/blob/master/README.md)
#### API
- [ ] Verify if API specs need to be regenerated.
- [ ] Check if version updates are required (e.g., specs, Poetry, etc.).
- [ ] Ensure new entries are added to [CHANGELOG.md](https://github.com/prowler-cloud/prowler/blob/master/api/CHANGELOG.md), if applicable.
### License
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

View File

@@ -23,7 +23,6 @@ env:
# Tags
LATEST_TAG: latest
RELEASE_TAG: ${{ github.event.release.tag_name }}
STABLE_TAG: stable
WORKING_DIRECTORY: ./api
@@ -32,83 +31,51 @@ env:
PROWLERCLOUD_DOCKERHUB_IMAGE: prowler-api
jobs:
repository-check:
name: Repository check
runs-on: ubuntu-latest
outputs:
is_repo: ${{ steps.repository_check.outputs.is_repo }}
steps:
- name: Repository check
id: repository_check
working-directory: /tmp
run: |
if [[ ${{ github.repository }} == "prowler-cloud/prowler" ]]
then
echo "is_repo=true" >> "${GITHUB_OUTPUT}"
else
echo "This action only runs for prowler-cloud/prowler"
echo "is_repo=false" >> "${GITHUB_OUTPUT}"
fi
# Build Prowler OSS container
container-build-push:
needs: repository-check
if: needs.repository-check.outputs.is_repo == 'true'
runs-on: ubuntu-latest
defaults:
run:
working-directory: ${{ env.WORKING_DIRECTORY }}
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set short git commit SHA
id: vars
- name: Repository check
working-directory: /tmp
run: |
shortSha=$(git rev-parse --short ${{ github.sha }})
echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
[[ ${{ github.repository }} != "prowler-cloud/prowler" ]] && echo "This action only runs for prowler-cloud/prowler"; exit 0
- name: Checkout
uses: actions/checkout@v4
- name: Login to DockerHub
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
uses: docker/setup-buildx-action@v3
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
context: ${{ env.WORKING_DIRECTORY }}
# Set push: false for testing
push: true
tags: |
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.LATEST_TAG }}
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.SHORT_SHA }}
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
context: ${{ env.WORKING_DIRECTORY }}
push: true
tags: |
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.RELEASE_TAG }}
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.STABLE_TAG }}
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Trigger deployment
if: github.event_name == 'push'
uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
repository: ${{ secrets.CLOUD_DISPATCH }}
event-type: prowler-api-deploy
client-payload: '{"sha": "${{ github.sha }}", "short_sha": "${{ env.SHORT_SHA }}"}'

View File

@@ -15,12 +15,16 @@ on:
push:
branches:
- "master"
- "v3"
- "v4.*"
- "v5.*"
paths:
- "api/**"
pull_request:
branches:
- "master"
- "v3"
- "v4.*"
- "v5.*"
paths:
- "api/**"
@@ -44,16 +48,16 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/api-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"

View File

@@ -4,17 +4,15 @@ on:
push:
branches:
- "master"
- "v5.*"
paths:
- ".github/workflows/api-pull-request.yml"
- "api/**"
pull_request:
branches:
- "master"
- "v5.*"
paths:
- "api/**"
env:
POSTGRES_HOST: localhost
POSTGRES_PORT: 5432
@@ -26,8 +24,7 @@ env:
VALKEY_HOST: localhost
VALKEY_PORT: 6379
VALKEY_DB: 0
API_WORKING_DIR: ./api
IMAGE_NAME: prowler-api
jobs:
test:
@@ -71,11 +68,11 @@ jobs:
--health-retries 5
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- name: Test if changes are in not ignored paths
id: are-non-ignored-files-changed
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
uses: tj-actions/changed-files@v45
with:
files: api/**
files_ignore: |
@@ -90,11 +87,11 @@ jobs:
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
python -m pip install --upgrade pip
pipx install poetry==2.1.1
pipx install poetry
- name: Set up Python ${{ matrix.python-version }}
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: "poetry"
@@ -103,7 +100,7 @@ jobs:
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry install --no-root
poetry install
poetry run pip list
VERSION=$(curl --silent "https://api.github.com/repos/hadolint/hadolint/releases/latest" | \
grep '"tag_name":' | \
@@ -115,7 +112,7 @@ jobs:
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry check --lock
poetry lock --check
- name: Lint with ruff
working-directory: ./api
@@ -167,23 +164,8 @@ jobs:
- name: Upload coverage reports to Codecov
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: codecov/codecov-action@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
uses: codecov/codecov-action@v5
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
with:
flags: api
test-container-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.API_WORKING_DIR }}
push: false
tags: ${{ env.IMAGE_NAME }}:latest
outputs: type=docker
cache-from: type=gha
cache-to: type=gha,mode=max

View File

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

View File

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

View File

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

View File

@@ -7,11 +7,11 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: TruffleHog OSS
uses: trufflesecurity/trufflehog@690e5c7aff8347c3885096f3962a0633d9129607 # v3.88.23
uses: trufflesecurity/trufflehog@v3.86.1
with:
path: ./
base: ${{ github.event.repository.default_branch }}

View File

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

View File

@@ -59,16 +59,16 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
uses: actions/setup-python@v5
with:
python-version: ${{ env.PYTHON_VERSION }}
- name: Install Poetry
run: |
pipx install poetry==2.*
pipx install poetry
pipx inject poetry poetry-bumpversion
- name: Get Prowler version
@@ -108,13 +108,13 @@ jobs:
esac
- name: Login to DockerHub
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to Public ECR
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
uses: docker/login-action@v3
with:
registry: public.ecr.aws
username: ${{ secrets.PUBLIC_ECR_AWS_ACCESS_KEY_ID }}
@@ -123,11 +123,11 @@ jobs:
AWS_REGION: ${{ env.AWS_REGION }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
uses: docker/setup-buildx-action@v3
- name: Build and push container image (latest)
if: github.event_name == 'push'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
push: true
tags: |
@@ -140,7 +140,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
# Use local context to get changes
# https://github.com/docker/build-push-action#path-context

View File

@@ -17,7 +17,6 @@ on:
- "master"
- "v3"
- "v4.*"
- "v5.*"
paths-ignore:
- 'ui/**'
- 'api/**'
@@ -26,7 +25,6 @@ on:
- "master"
- "v3"
- "v4.*"
- "v5.*"
paths-ignore:
- 'ui/**'
- 'api/**'
@@ -50,16 +48,16 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/sdk-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"

View File

@@ -21,11 +21,11 @@ jobs:
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- name: Test if changes are in not ignored paths
id: are-non-ignored-files-changed
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
uses: tj-actions/changed-files@v45
with:
files: ./**
files_ignore: |
@@ -34,24 +34,19 @@ jobs:
permissions/**
api/**
ui/**
prowler/CHANGELOG.md
README.md
mkdocs.yml
.backportrc.json
.env
docker-compose*
examples/**
.gitignore
- name: Install poetry
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
python -m pip install --upgrade pip
pipx install poetry==2.1.1
pipx install poetry
- name: Set up Python ${{ matrix.python-version }}
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: "poetry"
@@ -59,7 +54,7 @@ jobs:
- name: Install dependencies
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry install --no-root
poetry install
poetry run pip list
VERSION=$(curl --silent "https://api.github.com/repos/hadolint/hadolint/releases/latest" | \
grep '"tag_name":' | \
@@ -70,7 +65,7 @@ jobs:
- name: Poetry check
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry check --lock
poetry lock --check
- name: Lint with flake8
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -107,107 +102,15 @@ jobs:
run: |
/tmp/hadolint Dockerfile --ignore=DL3013
# Test AWS
- name: AWS - Check if any file has changed
id: aws-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/aws/**
./tests/providers/aws/**
- name: AWS - Test
if: steps.aws-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/aws --cov-report=xml:aws_coverage.xml tests/providers/aws
# Test Azure
- name: Azure - Check if any file has changed
id: azure-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/azure/**
./tests/providers/azure/**
- name: Azure - Test
if: steps.azure-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/azure --cov-report=xml:azure_coverage.xml tests/providers/azure
# Test GCP
- name: GCP - Check if any file has changed
id: gcp-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/gcp/**
./tests/providers/gcp/**
- name: GCP - Test
if: steps.gcp-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/gcp --cov-report=xml:gcp_coverage.xml tests/providers/gcp
# Test Kubernetes
- name: Kubernetes - Check if any file has changed
id: kubernetes-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/kubernetes/**
./tests/providers/kubernetes/**
- name: Kubernetes - Test
if: steps.kubernetes-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/kubernetes --cov-report=xml:kubernetes_coverage.xml tests/providers/kubernetes
# Test NHN
- name: NHN - Check if any file has changed
id: nhn-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/nhn/**
./tests/providers/nhn/**
- name: NHN - Test
if: steps.nhn-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/nhn --cov-report=xml:nhn_coverage.xml tests/providers/nhn
# Test M365
- name: M365 - Check if any file has changed
id: m365-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/m365/**
./tests/providers/m365/**
- name: M365 - Test
if: steps.m365-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/m365 --cov-report=xml:m365_coverage.xml tests/providers/m365
# Common Tests
- name: Lib - Test
- name: Test with pytest
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/lib --cov-report=xml:lib_coverage.xml tests/lib
poetry run pytest -n auto --cov=./prowler --cov-report=xml tests
- name: Config - Test
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/config --cov-report=xml:config_coverage.xml tests/config
# Codecov
- name: Upload coverage reports to Codecov
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: codecov/codecov-action@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
uses: codecov/codecov-action@v5
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
with:
flags: prowler
files: ./aws_coverage.xml,./azure_coverage.xml,./gcp_coverage.xml,./kubernetes_coverage.xml,./nhn_coverage.xml,./m365_coverage.xml,./lib_coverage.xml,./config_coverage.xml

View File

@@ -10,40 +10,12 @@ env:
CACHE: "poetry"
jobs:
repository-check:
name: Repository check
runs-on: ubuntu-latest
outputs:
is_repo: ${{ steps.repository_check.outputs.is_repo }}
steps:
- name: Repository check
id: repository_check
working-directory: /tmp
run: |
if [[ ${{ github.repository }} == "prowler-cloud/prowler" ]]
then
echo "is_repo=true" >> "${GITHUB_OUTPUT}"
else
echo "This action only runs for prowler-cloud/prowler"
echo "is_repo=false" >> "${GITHUB_OUTPUT}"
fi
release-prowler-job:
runs-on: ubuntu-latest
needs: repository-check
if: needs.repository-check.outputs.is_repo == 'true'
env:
POETRY_VIRTUALENVS_CREATE: "false"
name: Release Prowler to PyPI
steps:
- name: Repository check
working-directory: /tmp
run: |
if [[ "${{ github.repository }}" != "prowler-cloud/prowler" ]]; then
echo "This action only runs for prowler-cloud/prowler"
exit 1
fi
- name: Get Prowler version
run: |
PROWLER_VERSION="${{ env.RELEASE_TAG }}"
@@ -64,14 +36,14 @@ jobs:
;;
esac
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- name: Install dependencies
run: |
pipx install poetry==2.1.1
pipx install poetry
- name: Setup Python
uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
uses: actions/setup-python@v5
with:
python-version: ${{ env.PYTHON_VERSION }}
cache: ${{ env.CACHE }}

View File

@@ -23,12 +23,12 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
with:
ref: ${{ env.GITHUB_BRANCH }}
- name: setup python
uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
uses: actions/setup-python@v5
with:
python-version: 3.9 #install the python needed
@@ -38,7 +38,7 @@ jobs:
pip install boto3
- name: Configure AWS Credentials -- DEV
uses: aws-actions/configure-aws-credentials@ececac1a45f3b08a01d2dd070d28d111c5fe6722 # v4.1.0
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: ${{ env.AWS_REGION_DEV }}
role-to-assume: ${{ secrets.DEV_IAM_ROLE_ARN }}
@@ -50,13 +50,12 @@ jobs:
# Create pull request
- name: Create Pull Request
uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
uses: peter-evans/create-pull-request@v7
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
commit-message: "feat(regions_update): Update regions for AWS services"
branch: "aws-services-regions-updated-${{ github.sha }}"
labels: "status/waiting-for-revision, severity/low, provider/aws"
labels: "status/waiting-for-revision, severity/low, provider/aws, backport-to-v3"
title: "chore(regions_update): Changes in regions for AWS services"
body: |
### Description

View File

@@ -23,7 +23,6 @@ env:
# Tags
LATEST_TAG: latest
RELEASE_TAG: ${{ github.event.release.tag_name }}
STABLE_TAG: stable
WORKING_DIRECTORY: ./ui
@@ -32,87 +31,51 @@ env:
PROWLERCLOUD_DOCKERHUB_IMAGE: prowler-ui
jobs:
repository-check:
name: Repository check
runs-on: ubuntu-latest
outputs:
is_repo: ${{ steps.repository_check.outputs.is_repo }}
steps:
- name: Repository check
id: repository_check
working-directory: /tmp
run: |
if [[ ${{ github.repository }} == "prowler-cloud/prowler" ]]
then
echo "is_repo=true" >> "${GITHUB_OUTPUT}"
else
echo "This action only runs for prowler-cloud/prowler"
echo "is_repo=false" >> "${GITHUB_OUTPUT}"
fi
# Build Prowler OSS container
container-build-push:
needs: repository-check
if: needs.repository-check.outputs.is_repo == 'true'
runs-on: ubuntu-latest
defaults:
run:
working-directory: ${{ env.WORKING_DIRECTORY }}
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set short git commit SHA
id: vars
- name: Repository check
working-directory: /tmp
run: |
shortSha=$(git rev-parse --short ${{ github.sha }})
echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
[[ ${{ github.repository }} != "prowler-cloud/prowler" ]] && echo "This action only runs for prowler-cloud/prowler"; exit 0
- name: Checkout
uses: actions/checkout@v4
- name: Login to DockerHub
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
uses: docker/setup-buildx-action@v3
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=${{ env.SHORT_SHA }}
# Set push: false for testing
push: true
tags: |
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.LATEST_TAG }}
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.SHORT_SHA }}
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
uses: docker/build-push-action@v6
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${{ env.RELEASE_TAG }}
push: true
tags: |
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.RELEASE_TAG }}
${{ env.PROWLERCLOUD_DOCKERHUB_REPOSITORY }}/${{ env.PROWLERCLOUD_DOCKERHUB_IMAGE }}:${{ env.STABLE_TAG }}
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Trigger deployment
if: github.event_name == 'push'
uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
repository: ${{ secrets.CLOUD_DISPATCH }}
event-type: prowler-ui-deploy
client-payload: '{"sha": "${{ github.sha }}", "short_sha": "${{ env.SHORT_SHA }}"}'

View File

@@ -15,12 +15,14 @@ on:
push:
branches:
- "master"
- "v4.*"
- "v5.*"
paths:
- "ui/**"
pull_request:
branches:
- "master"
- "v4.*"
- "v5.*"
paths:
- "ui/**"
@@ -44,16 +46,16 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/ui-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"

View File

@@ -1,22 +1,11 @@
name: UI - Pull Request
on:
push:
branches:
- "master"
- "v5.*"
paths:
- ".github/workflows/ui-pull-request.yml"
- "ui/**"
pull_request:
branches:
- master
- "v5.*"
paths:
- 'ui/**'
env:
UI_WORKING_DIR: ./ui
IMAGE_NAME: prowler-ui
jobs:
test-and-coverage:
@@ -27,11 +16,11 @@ jobs:
node-version: [20.x]
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
with:
persist-credentials: false
- name: Setup Node.js ${{ matrix.node-version }}
uses: actions/setup-node@cdca7365b2dadb8aad0a33bc7601856ffabcc48e # v4.3.0
uses: actions/setup-node@v3
with:
node-version: ${{ matrix.node-version }}
- name: Install dependencies
@@ -43,20 +32,3 @@ jobs:
- name: Build the application
working-directory: ./ui
run: npm run build
test-container-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.UI_WORKING_DIR }}
# Always build using `prod` target
target: prod
push: false
tags: ${{ env.IMAGE_NAME }}:latest
outputs: type=docker
build-args: |
NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=pk_test_51LwpXXXX

4
.gitignore vendored
View File

@@ -31,7 +31,7 @@ tags
*.DS_Store
# Prowler output
/output
output/
# Prowler found secrets
secrets-*/
@@ -45,12 +45,10 @@ junit-reports/
# Terraform
.terraform*
*.tfstate
*.tfstate.*
# .env
ui/.env*
api/.env*
.env.local
# Coverage
.coverage*

View File

@@ -27,7 +27,6 @@ repos:
hooks:
- id: shellcheck
exclude: contrib
## PYTHON
- repo: https://github.com/myint/autoflake
rev: v2.3.1
@@ -59,28 +58,11 @@ repos:
args: ["--ignore=E266,W503,E203,E501,W605"]
- repo: https://github.com/python-poetry/poetry
rev: 2.1.1
rev: 1.8.0
hooks:
- id: poetry-check
name: API - poetry-check
args: ["--directory=./api"]
pass_filenames: false
- id: poetry-lock
name: API - poetry-lock
args: ["--directory=./api"]
pass_filenames: false
- id: poetry-check
name: SDK - poetry-check
args: ["--directory=./"]
pass_filenames: false
- id: poetry-lock
name: SDK - poetry-lock
args: ["--directory=./"]
pass_filenames: false
args: ["--no-update"]
- repo: https://github.com/hadolint/hadolint
rev: v2.13.0-beta
@@ -108,7 +90,7 @@ repos:
- id: bandit
name: bandit
description: "Bandit is a tool for finding common security issues in Python code"
entry: bash -c 'bandit -q -lll -x '*_test.py,./contrib/,./.venv/' -r .'
entry: bash -c 'bandit -q -lll -x '*_test.py,./contrib/' -r .'
language: system
files: '.*\.py'
@@ -121,6 +103,7 @@ repos:
- id: vulture
name: vulture
description: "Vulture finds unused code in Python programs."
entry: bash -c 'vulture --exclude "contrib,.venv,api/src/backend/api/tests/,api/src/backend/conftest.py,api/src/backend/tasks/tests/" --min-confidence 100 .'
entry: bash -c 'vulture --exclude "contrib" --min-confidence 100 .'
exclude: 'api/src/backend/'
language: system
files: '.*\.py'

View File

@@ -1,10 +1,10 @@
FROM python:3.12.9-alpine3.20
FROM python:3.12.8-alpine3.20
LABEL maintainer="https://github.com/prowler-cloud/prowler"
# Update system dependencies and install essential tools
#hadolint ignore=DL3018
RUN apk --no-cache upgrade && apk --no-cache add curl git gcc python3-dev musl-dev linux-headers
RUN apk --no-cache upgrade && apk --no-cache add curl git
# Create non-root user
RUN mkdir -p /home/prowler && \
@@ -18,25 +18,21 @@ WORKDIR /home/prowler
COPY prowler/ /home/prowler/prowler/
COPY dashboard/ /home/prowler/dashboard/
COPY pyproject.toml /home/prowler
COPY README.md /home/prowler/
COPY README.md /home/prowler
# Install Python dependencies
ENV HOME='/home/prowler'
ENV PATH="${HOME}/.local/bin:${PATH}"
#hadolint ignore=DL3013
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir poetry
# By default poetry does not compile Python source files to bytecode during installation.
# This speeds up the installation process, but the first execution may take a little more
# time because Python then compiles source files to bytecode automatically. If you want to
# compile source files to bytecode during installation, you can use the --compile option
RUN poetry install --compile && \
rm -rf ~/.cache/pip
ENV PATH="$HOME/.local/bin:$PATH"
RUN pip install --no-cache-dir --upgrade pip setuptools wheel && \
pip install --no-cache-dir .
# Remove deprecated dash dependencies
RUN pip uninstall dash-html-components -y && \
pip uninstall dash-core-components -y
# Remove Prowler directory and build files
USER 0
RUN rm -rf /home/prowler/prowler /home/prowler/pyproject.toml /home/prowler/README.md /home/prowler/build /home/prowler/prowler.egg-info
USER prowler
ENTRYPOINT ["poetry", "run", "prowler"]
ENTRYPOINT ["prowler"]

View File

@@ -71,14 +71,10 @@ It contains hundreds of controls covering CIS, NIST 800, NIST CSF, CISA, RBI, Fe
| Provider | Checks | Services | [Compliance Frameworks](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/compliance/) | [Categories](https://docs.prowler.com/projects/prowler-open-source/en/latest/tutorials/misc/#categories) |
|---|---|---|---|---|
| AWS | 564 | 82 | 33 | 10 |
| GCP | 78 | 13 | 7 | 3 |
| Azure | 140 | 18 | 7 | 3 |
| Kubernetes | 83 | 7 | 4 | 7 |
| Microsoft365 | 5 | 2 | 1 | 0 |
| NHN (Unofficial) | 6 | 2 | 1 | 0 |
> You can list the checks, services, compliance frameworks and categories with `prowler <provider> --list-checks`, `prowler <provider> --list-services`, `prowler <provider> --list-compliance` and `prowler <provider> --list-categories`.
| AWS | 561 | 81 -> `prowler aws --list-services` | 30 -> `prowler aws --list-compliance` | 9 -> `prowler aws --list-categories` |
| GCP | 77 | 13 -> `prowler gcp --list-services` | 3 -> `prowler gcp --list-compliance` | 2 -> `prowler gcp --list-categories`|
| Azure | 139 | 18 -> `prowler azure --list-services` | 4 -> `prowler azure --list-compliance` | 2 -> `prowler azure --list-categories` |
| Kubernetes | 83 | 7 -> `prowler kubernetes --list-services` | 1 -> `prowler kubernetes --list-compliance` | 7 -> `prowler kubernetes --list-categories` |
# 💻 Installation
@@ -102,7 +98,6 @@ curl -LO https://raw.githubusercontent.com/prowler-cloud/prowler/refs/heads/mast
docker compose up -d
```
> Containers are built for `linux/amd64`. If your workstation's architecture is different, please set `DOCKER_DEFAULT_PLATFORM=linux/amd64` in your environment or use the `--platform linux/amd64` flag in the docker command.
> Enjoy Prowler App at http://localhost:3000 by signing up with your email and password.
### From GitHub
@@ -110,7 +105,7 @@ docker compose up -d
**Requirements**
* `git` installed.
* `poetry` v2 installed: [poetry installation](https://python-poetry.org/docs/#installation).
* `poetry` installed: [poetry installation](https://python-poetry.org/docs/#installation).
* `npm` installed: [npm installation](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm).
* `Docker Compose` installed: https://docs.docker.com/compose/install/.
@@ -120,7 +115,7 @@ docker compose up -d
git clone https://github.com/prowler-cloud/prowler
cd prowler/api
poetry install
eval $(poetry env activate)
poetry shell
set -a
source .env
docker compose up postgres valkey -d
@@ -128,11 +123,6 @@ cd src/backend
python manage.py migrate --database admin
gunicorn -c config/guniconf.py config.wsgi:application
```
> [!IMPORTANT]
> Starting from Poetry v2.0.0, `poetry shell` has been deprecated in favor of `poetry env activate`.
>
> If your poetry version is below 2.0.0 you must keep using `poetry shell` to activate your environment.
> In case you have any doubts, consult the Poetry environment activation guide: https://python-poetry.org/docs/managing-environments/#activating-the-environment
> Now, you can access the API documentation at http://localhost:8080/api/v1/docs.
@@ -142,7 +132,7 @@ gunicorn -c config/guniconf.py config.wsgi:application
git clone https://github.com/prowler-cloud/prowler
cd prowler/api
poetry install
eval $(poetry env activate)
poetry shell
set -a
source .env
cd src/backend
@@ -155,7 +145,7 @@ python -m celery -A config.celery worker -l info -E
git clone https://github.com/prowler-cloud/prowler
cd prowler/api
poetry install
eval $(poetry env activate)
poetry shell
set -a
source .env
cd src/backend
@@ -176,7 +166,7 @@ npm start
## Prowler CLI
### Pip package
Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/), thus can be installed using pip with Python > 3.9.1, < 3.13:
Prowler CLI is available as a project in [PyPI](https://pypi.org/project/prowler-cloud/), thus can be installed using pip with Python >= 3.9, < 3.13:
```console
pip install prowler
@@ -206,21 +196,15 @@ The container images are available here:
### From GitHub
Python > 3.9.1, < 3.13 is required with pip and poetry:
Python >= 3.9, < 3.13 is required with pip and poetry:
``` console
git clone https://github.com/prowler-cloud/prowler
cd prowler
eval $(poetry env activate)
poetry shell
poetry install
python prowler-cli.py -v
python prowler.py -v
```
> [!IMPORTANT]
> Starting from Poetry v2.0.0, `poetry shell` has been deprecated in favor of `poetry env activate`.
>
> If your poetry version is below 2.0.0 you must keep using `poetry shell` to activate your environment.
> In case you have any doubts, consult the Poetry environment activation guide: https://python-poetry.org/docs/managing-environments/#activating-the-environment
> If you want to clone Prowler from Windows, use `git config core.longpaths true` to allow long file paths.
# 📐✏️ High level architecture

View File

@@ -22,8 +22,6 @@ DJANGO_SECRETS_ENCRYPTION_KEY=""
# Decide whether to allow Django manage database table partitions
DJANGO_MANAGE_DB_PARTITIONS=[True|False]
DJANGO_CELERY_DEADLOCK_ATTEMPTS=5
DJANGO_BROKER_VISIBILITY_TIMEOUT=86400
DJANGO_SENTRY_DSN=
# PostgreSQL settings
# If running django and celery on host, use 'localhost', else use 'postgres-db'
@@ -40,19 +38,3 @@ POSTGRES_DB=prowler_db
VALKEY_HOST=[localhost|valkey]
VALKEY_PORT=6379
VALKEY_DB=0
# Sentry settings
SENTRY_ENVIRONMENT=local
SENTRY_RELEASE=local
# Social login credentials
DJANGO_GOOGLE_OAUTH_CLIENT_ID=""
DJANGO_GOOGLE_OAUTH_CLIENT_SECRET=""
DJANGO_GOOGLE_OAUTH_CALLBACK_URL=""
DJANGO_GITHUB_OAUTH_CLIENT_ID=""
DJANGO_GITHUB_OAUTH_CLIENT_SECRET=""
DJANGO_GITHUB_OAUTH_CALLBACK_URL=""
# Deletion Task Batch Size
DJANGO_DELETION_BATCH_SIZE=5000

View File

@@ -1,74 +0,0 @@
# Prowler API Changelog
All notable changes to the **Prowler API** are documented in this file.
## [v1.6.0] (Prowler v5.5.0)
### Added
- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167).
- HTTP Security Headers [(#7289)](https://github.com/prowler-cloud/prowler/pull/7289).
- New endpoint to get the compliance overviews metadata [(#7333)](https://github.com/prowler-cloud/prowler/pull/7333).
- Support for muted findings [(#7378)](https://github.com/prowler-cloud/prowler/pull/7378).
- Added missing fields to API findings and resources [(#7318)](https://github.com/prowler-cloud/prowler/pull/7318).
---
## [v1.5.4] (Prowler v5.4.4)
### Fixed
- Fixed a bug with periodic tasks when trying to delete a provider ([#7466])(https://github.com/prowler-cloud/prowler/pull/7466).
---
## [v1.5.3] (Prowler v5.4.3)
### Fixed
- Added duplicated scheduled scans handling ([#7401])(https://github.com/prowler-cloud/prowler/pull/7401).
- Added environment variable to configure the deletion task batch size ([#7423])(https://github.com/prowler-cloud/prowler/pull/7423).
---
## [v1.5.2] (Prowler v5.4.2)
### Changed
- Refactored deletion logic and implemented retry mechanism for deletion tasks [(#7349)](https://github.com/prowler-cloud/prowler/pull/7349).
---
## [v1.5.1] (Prowler v5.4.1)
### Fixed
- Added a handled response in case local files are missing [(#7183)](https://github.com/prowler-cloud/prowler/pull/7183).
- Fixed a race condition when deleting export files after the S3 upload [(#7172)](https://github.com/prowler-cloud/prowler/pull/7172).
- Handled exception when a provider has no secret in test connection [(#7283)](https://github.com/prowler-cloud/prowler/pull/7283).
### Added
- Support for developing new integrations [(#7167)](https://github.com/prowler-cloud/prowler/pull/7167).
---
## [v1.5.0] (Prowler v5.4.0)
### Added
- Social login integration with Google and GitHub [(#6906)](https://github.com/prowler-cloud/prowler/pull/6906)
- Add API scan report system, now all scans launched from the API will generate a compressed file with the report in OCSF, CSV and HTML formats [(#6878)](https://github.com/prowler-cloud/prowler/pull/6878).
- Configurable Sentry integration [(#6874)](https://github.com/prowler-cloud/prowler/pull/6874)
### Changed
- Optimized `GET /findings` endpoint to improve response time and size [(#7019)](https://github.com/prowler-cloud/prowler/pull/7019).
---
## [v1.4.0] (Prowler v5.3.0)
### Changed
- Daily scheduled scan instances are now created beforehand with `SCHEDULED` state [(#6700)](https://github.com/prowler-cloud/prowler/pull/6700).
- Findings endpoints now require at least one date filter [(#6800)](https://github.com/prowler-cloud/prowler/pull/6800).
- Findings metadata endpoint received a performance improvement [(#6863)](https://github.com/prowler-cloud/prowler/pull/6863).
- Increased the allowed length of the provider UID for Kubernetes providers [(#6869)](https://github.com/prowler-cloud/prowler/pull/6869).
---

View File

@@ -1,4 +1,4 @@
FROM python:3.12.8-alpine3.20 AS build
FROM python:3.12-alpine AS build
LABEL maintainer="https://github.com/prowler-cloud/api"
@@ -21,8 +21,7 @@ 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 && \
RUN poetry install && \
rm -rf ~/.cache/pip
COPY docker-entrypoint.sh ./docker-entrypoint.sh

View File

@@ -269,66 +269,3 @@ poetry shell
cd src/backend
pytest
```
# Custom commands
Django provides a way to create custom commands that can be run from the command line.
> These commands can be found in: ```prowler/api/src/backend/api/management/commands```
To run a custom command, you need to be in the `prowler/api/src/backend` directory and run:
```console
poetry shell
python manage.py <command_name>
```
## Generate dummy data
```console
python manage.py findings --tenant
<TENANT_ID> --findings <NUM_FINDINGS> --re
sources <NUM_RESOURCES> --batch <TRANSACTION_BATCH_SIZE> --alias <ALIAS>
```
This command creates, for a given tenant, a provider, scan and a set of findings and resources related altogether.
> Scan progress and state are updated in real time.
> - 0-33%: Create resources.
> - 33-66%: Create findings.
> - 66%: Create resource-finding mapping.
>
> The last step is required to access the findings details, since the UI needs that to print all the information.
### Example
```console
~/backend $ poetry run python manage.py findings --tenant
fffb1893-3fc7-4623-a5d9-fae47da1c528 --findings 25000 --re
sources 1000 --batch 5000 --alias test-script
Starting data population
Tenant: fffb1893-3fc7-4623-a5d9-fae47da1c528
Alias: test-script
Resources: 1000
Findings: 25000
Batch size: 5000
Creating resources...
100%|███████████████████████| 1/1 [00:00<00:00, 7.72it/s]
Resources created successfully.
Creating findings...
100%|███████████████████████| 5/5 [00:05<00:00, 1.09s/it]
Findings created successfully.
Creating resource-finding mappings...
100%|███████████████████████| 5/5 [00:02<00:00, 1.81it/s]
Resource-finding mappings created successfully.
Successfully populated test data.
```

View File

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

2311
api/poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -2,48 +2,41 @@
build-backend = "poetry.core.masonry.api"
requires = ["poetry-core"]
[project]
authors = [{name = "Prowler Engineering", email = "engineering@prowler.com"}]
dependencies = [
"celery[pytest] (>=5.4.0,<6.0.0)",
"dj-rest-auth[with_social,jwt] (==7.0.1)",
"django==5.1.7",
"django-allauth==65.4.1",
"django-celery-beat (>=2.7.0,<3.0.0)",
"django-celery-results (>=2.5.1,<3.0.0)",
"django-cors-headers==4.4.0",
"django-environ==0.11.2",
"django-filter==24.3",
"django-guid==3.5.0",
"django-postgres-extra (>=2.0.8,<3.0.0)",
"djangorestframework==3.15.2",
"djangorestframework-jsonapi==7.0.2",
"djangorestframework-simplejwt (>=5.3.1,<6.0.0)",
"drf-nested-routers (>=0.94.1,<1.0.0)",
"drf-spectacular==0.27.2",
"drf-spectacular-jsonapi==0.5.1",
"gunicorn==23.0.0",
"prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.5",
"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"
]
[tool.poetry]
authors = ["Prowler Team"]
description = "Prowler's API (Django/DRF)"
license = "Apache-2.0"
name = "prowler-api"
package-mode = false
# Needed for the SDK compatibility
requires-python = ">=3.11,<3.13"
version = "1.6.0"
version = "1.0.0"
[project.scripts]
celery = "src.backend.config.settings.celery"
[tool.poetry.dependencies]
celery = {extras = ["pytest"], version = "^5.4.0"}
django = "5.1.1"
django-celery-beat = "^2.7.0"
django-celery-results = "^2.5.1"
django-cors-headers = "4.4.0"
django-environ = "0.11.2"
django-filter = "24.3"
django-guid = "3.5.0"
django-postgres-extra = "^2.0.8"
djangorestframework = "3.15.2"
djangorestframework-jsonapi = "7.0.2"
djangorestframework-simplejwt = "^5.3.1"
drf-nested-routers = "^0.94.1"
drf-spectacular = "0.27.2"
drf-spectacular-jsonapi = "0.5.1"
gunicorn = "23.0.0"
prowler = {git = "https://github.com/prowler-cloud/prowler.git", tag = "5.0.0"}
psycopg2-binary = "2.9.9"
pytest-celery = {extras = ["redis"], version = "^1.0.1"}
# Needed for prowler compatibility
python = ">=3.11,<3.13"
uuid6 = "2024.7.10"
[tool.poetry.group.dev.dependencies]
bandit = "1.7.9"
coverage = "7.5.4"
django-silk = "5.3.2"
docker = "7.1.0"
freezegun = "1.5.1"
mypy = "1.10.1"
@@ -55,6 +48,8 @@ pytest-env = "1.1.3"
pytest-randomly = "3.15.0"
pytest-xdist = "3.6.1"
ruff = "0.5.0"
safety = "3.2.9"
tqdm = "4.67.1"
vulture = "2.14"
safety = "3.2.3"
vulture = "2.11"
[tool.poetry.scripts]
celery = "src.backend.config.settings.celery"

View File

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

View File

@@ -1,23 +1,23 @@
import uuid
from django.core.exceptions import ObjectDoesNotExist
from django.db import transaction
from django.db import connection, transaction
from rest_framework import permissions
from rest_framework.exceptions import NotAuthenticated
from rest_framework.filters import SearchFilter
from rest_framework_json_api import filters
from rest_framework_json_api.serializers import ValidationError
from rest_framework_json_api.views import ModelViewSet
from rest_framework_simplejwt.authentication import JWTAuthentication
from api.db_router import MainRouter
from api.db_utils import POSTGRES_USER_VAR, rls_transaction
from api.filters import CustomDjangoFilterBackend
from api.models import Role, Tenant
from api.rbac.permissions import HasPermissions
from api.db_router import MainRouter
class BaseViewSet(ModelViewSet):
authentication_classes = [JWTAuthentication]
required_permissions = []
permission_classes = [permissions.IsAuthenticated, HasPermissions]
permission_classes = [permissions.IsAuthenticated]
filter_backends = [
filters.QueryParameterValidationFilter,
filters.OrderingFilter,
@@ -31,17 +31,6 @@ class BaseViewSet(ModelViewSet):
ordering_fields = "__all__"
ordering = ["id"]
def initial(self, request, *args, **kwargs):
"""
Sets required_permissions before permissions are checked.
"""
self.set_required_permissions()
super().initial(request, *args, **kwargs)
def set_required_permissions(self):
"""This is an abstract method that must be implemented by subclasses."""
NotImplemented
def get_queryset(self):
raise NotImplementedError
@@ -61,7 +50,13 @@ class BaseRLSViewSet(BaseViewSet):
if tenant_id is None:
raise NotAuthenticated("Tenant ID is not present in token")
with rls_transaction(tenant_id):
try:
uuid.UUID(tenant_id)
except ValueError:
raise ValidationError("Tenant ID must be a valid UUID")
with connection.cursor() as cursor:
cursor.execute(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
self.request.tenant_id = tenant_id
return super().initial(request, *args, **kwargs)
@@ -115,7 +110,8 @@ class BaseTenantViewset(BaseViewSet):
):
user_id = str(request.user.id)
with rls_transaction(value=user_id, parameter=POSTGRES_USER_VAR):
with connection.cursor() as cursor:
cursor.execute(f"SELECT set_config('api.user_id', '{user_id}', TRUE);")
return super().initial(request, *args, **kwargs)
# TODO: DRY this when we have time
@@ -126,7 +122,13 @@ class BaseTenantViewset(BaseViewSet):
if tenant_id is None:
raise NotAuthenticated("Tenant ID is not present in token")
with rls_transaction(tenant_id):
try:
uuid.UUID(tenant_id)
except ValueError:
raise ValidationError("Tenant ID must be a valid UUID")
with connection.cursor() as cursor:
cursor.execute(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
self.request.tenant_id = tenant_id
return super().initial(request, *args, **kwargs)
@@ -147,6 +149,12 @@ class BaseUserViewset(BaseViewSet):
if tenant_id is None:
raise NotAuthenticated("Tenant ID is not present in token")
with rls_transaction(tenant_id):
try:
uuid.UUID(tenant_id)
except ValueError:
raise ValidationError("Tenant ID must be a valid UUID")
with connection.cursor() as cursor:
cursor.execute(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
self.request.tenant_id = tenant_id
return super().initial(request, *args, **kwargs)

View File

@@ -1,29 +1,18 @@
ALLOWED_APPS = ("django", "socialaccount", "account", "authtoken", "silk")
class MainRouter:
default_db = "default"
admin_db = "admin"
def db_for_read(self, model, **hints): # noqa: F841
model_table_name = model._meta.db_table
if model_table_name.startswith("django_") or any(
model_table_name.startswith(f"{app}_") for app in ALLOWED_APPS
):
if model_table_name.startswith("django_"):
return self.admin_db
return None
def db_for_write(self, model, **hints): # noqa: F841
model_table_name = model._meta.db_table
if any(model_table_name.startswith(f"{app}_") for app in ALLOWED_APPS):
if model_table_name.startswith("django_"):
return self.admin_db
return None
def allow_migrate(self, db, app_label, model_name=None, **hints): # noqa: F841
return db == self.admin_db
def allow_relation(self, obj1, obj2, **hints): # noqa: F841
# Allow relations if both objects are in either "default" or "admin" db connectors
if {obj1._state.db, obj2._state.db} <= {self.default_db, self.admin_db}:
return True
return None

View File

@@ -1,15 +1,13 @@
import secrets
import uuid
from contextlib import contextmanager
from datetime import datetime, timedelta, timezone
from django.conf import settings
from django.contrib.auth.models import BaseUserManager
from django.core.paginator import Paginator
from django.db import connection, models, transaction
from django_celery_beat.models import PeriodicTask
from psycopg2 import connect as psycopg2_connect
from psycopg2.extensions import AsIs, new_type, register_adapter, register_type
from rest_framework_json_api.serializers import ValidationError
DB_USER = settings.DATABASES["default"]["USER"] if not settings.TESTING else "test"
DB_PASSWORD = (
@@ -25,8 +23,6 @@ TASK_RUNNER_DB_TABLE = "django_celery_results_taskresult"
POSTGRES_TENANT_VAR = "api.tenant_id"
POSTGRES_USER_VAR = "api.user_id"
SET_CONFIG_QUERY = "SELECT set_config(%s, %s::text, TRUE);"
@contextmanager
def psycopg_connection(database_alias: str):
@@ -48,23 +44,10 @@ def psycopg_connection(database_alias: str):
@contextmanager
def rls_transaction(value: str, parameter: str = POSTGRES_TENANT_VAR):
"""
Creates a new database transaction setting the given configuration value for Postgres RLS. It validates the
if the value is a valid UUID.
Args:
value (str): Database configuration parameter value.
parameter (str): Database configuration parameter name, by default is 'api.tenant_id'.
"""
def tenant_transaction(tenant_id: str):
with transaction.atomic():
with connection.cursor() as cursor:
try:
# just in case the value is an UUID object
uuid.UUID(str(value))
except ValueError:
raise ValidationError("Must be a valid UUID")
cursor.execute(SET_CONFIG_QUERY, [parameter, value])
cursor.execute(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
yield cursor
@@ -106,12 +89,11 @@ def generate_random_token(length: int = 14, symbols: str | None = None) -> str:
return "".join(secrets.choice(symbols or _symbols) for _ in range(length))
def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_SIZE):
def batch_delete(queryset, batch_size=5000):
"""
Deletes objects in batches and returns the total number of deletions and a summary.
Args:
tenant_id (str): Tenant ID the queryset belongs to.
queryset (QuerySet): The queryset of objects to delete.
batch_size (int): The number of objects to delete in each batch.
@@ -121,37 +103,21 @@ def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_
total_deleted = 0
deletion_summary = {}
while True:
with rls_transaction(tenant_id, POSTGRES_TENANT_VAR):
# Get a batch of IDs to delete
batch_ids = set(
queryset.values_list("id", flat=True).order_by("id")[:batch_size]
)
if not batch_ids:
# No more objects to delete
break
paginator = Paginator(queryset.order_by("id").only("id"), batch_size)
deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
for page_num in paginator.page_range:
batch_ids = [obj.id for obj in paginator.page(page_num).object_list]
deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
total_deleted += deleted_count
for model_label, count in deleted_info.items():
deletion_summary[model_label] = deletion_summary.get(model_label, 0) + count
return total_deleted, deletion_summary
def delete_related_daily_task(provider_id: str):
"""
Deletes the periodic task associated with a specific provider.
Args:
provider_id (str): The unique identifier for the provider
whose related periodic task should be deleted.
"""
task_name = f"scan-perform-scheduled-{provider_id}"
PeriodicTask.objects.filter(name=task_name).delete()
# Postgres Enums
@@ -333,15 +299,3 @@ class InvitationStateEnum(EnumType):
class InvitationStateEnumField(PostgresEnumField):
def __init__(self, *args, **kwargs):
super().__init__("invitation_state", *args, **kwargs)
# Postgres enum definition for Integration type
class IntegrationTypeEnum(EnumType):
enum_type_name = "integration_type"
class IntegrationTypeEnumField(PostgresEnumField):
def __init__(self, *args, **kwargs):
super().__init__("integration_type", *args, **kwargs)

View File

@@ -1,13 +1,9 @@
import uuid
from functools import wraps
from django.db import connection, transaction
from rest_framework_json_api.serializers import ValidationError
from api.db_utils import POSTGRES_TENANT_VAR, SET_CONFIG_QUERY
def set_tenant(func=None, *, keep_tenant=False):
def set_tenant(func):
"""
Decorator to set the tenant context for a Celery task based on the provided tenant_id.
@@ -35,34 +31,22 @@ def set_tenant(func=None, *, keep_tenant=False):
pass
# When calling the task
some_task.delay(arg1, tenant_id="8db7ca86-03cc-4d42-99f6-5e480baf6ab5")
some_task.delay(arg1, tenant_id="1234-abcd-5678")
# The tenant context will be set before the task logic executes.
"""
def decorator(func):
@wraps(func)
@transaction.atomic
def wrapper(*args, **kwargs):
try:
if not keep_tenant:
tenant_id = kwargs.pop("tenant_id")
else:
tenant_id = kwargs["tenant_id"]
except KeyError:
raise KeyError("This task requires the tenant_id")
try:
uuid.UUID(tenant_id)
except ValueError:
raise ValidationError("Tenant ID must be a valid UUID")
with connection.cursor() as cursor:
cursor.execute(SET_CONFIG_QUERY, [POSTGRES_TENANT_VAR, tenant_id])
@wraps(func)
@transaction.atomic
def wrapper(*args, **kwargs):
try:
tenant_id = kwargs.pop("tenant_id")
except KeyError:
raise KeyError("This task requires the tenant_id")
return func(*args, **kwargs)
with connection.cursor() as cursor:
cursor.execute(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
return wrapper
return func(*args, **kwargs)
if func is None:
return decorator
else:
return decorator(func)
return wrapper

View File

@@ -1,4 +1,4 @@
from datetime import date, datetime, timedelta, timezone
from datetime import date, datetime, timezone
from django.conf import settings
from django.db.models import Q
@@ -22,23 +22,21 @@ from api.db_utils import (
StatusEnumField,
)
from api.models import (
ComplianceOverview,
Finding,
Integration,
Invitation,
Membership,
PermissionChoices,
Provider,
ProviderGroup,
ProviderSecret,
Resource,
ResourceTag,
Role,
Scan,
ScanSummary,
SeverityChoices,
StateChoices,
StatusChoices,
ProviderSecret,
Invitation,
Role,
ComplianceOverview,
Task,
User,
)
@@ -287,9 +285,6 @@ class FindingFilter(FilterSet):
status = ChoiceFilter(choices=StatusChoices.choices)
severity = ChoiceFilter(choices=SeverityChoices)
impact = ChoiceFilter(choices=SeverityChoices)
muted = BooleanFilter(
help_text="If this filter is not provided, muted and non-muted findings will be returned."
)
resources = UUIDInFilter(field_name="resource__id", lookup_expr="in")
@@ -323,41 +318,13 @@ class FindingFilter(FilterSet):
field_name="resources__type", lookup_expr="icontains"
)
# Temporarily disabled until we implement tag filtering in the UI
# resource_tag_key = CharFilter(field_name="resources__tags__key")
# resource_tag_key__in = CharInFilter(
# field_name="resources__tags__key", lookup_expr="in"
# )
# resource_tag_key__icontains = CharFilter(
# field_name="resources__tags__key", lookup_expr="icontains"
# )
# resource_tag_value = CharFilter(field_name="resources__tags__value")
# resource_tag_value__in = CharInFilter(
# field_name="resources__tags__value", lookup_expr="in"
# )
# resource_tag_value__icontains = CharFilter(
# field_name="resources__tags__value", lookup_expr="icontains"
# )
# resource_tags = CharInFilter(
# method="filter_resource_tag",
# lookup_expr="in",
# help_text="Filter by resource tags `key:value` pairs.\nMultiple values may be "
# "separated by commas.",
# )
scan = UUIDFilter(method="filter_scan_id")
scan__in = UUIDInFilter(method="filter_scan_id_in")
inserted_at = DateFilter(method="filter_inserted_at", lookup_expr="date")
inserted_at__date = DateFilter(method="filter_inserted_at", lookup_expr="date")
inserted_at__gte = DateFilter(
method="filter_inserted_at_gte",
help_text=f"Maximum date range is {settings.FINDINGS_MAX_DAYS_IN_RANGE} days.",
)
inserted_at__lte = DateFilter(
method="filter_inserted_at_lte",
help_text=f"Maximum date range is {settings.FINDINGS_MAX_DAYS_IN_RANGE} days.",
)
inserted_at__gte = DateFilter(method="filter_inserted_at_gte")
inserted_at__lte = DateFilter(method="filter_inserted_at_lte")
class Meta:
model = Finding
@@ -385,52 +352,6 @@ class FindingFilter(FilterSet):
},
}
def filter_queryset(self, queryset):
if not (self.data.get("scan") or self.data.get("scan__in")) and not (
self.data.get("inserted_at")
or self.data.get("inserted_at__date")
or self.data.get("inserted_at__gte")
or self.data.get("inserted_at__lte")
):
raise ValidationError(
[
{
"detail": "At least one date filter is required: filter[inserted_at], filter[inserted_at.gte], "
"or filter[inserted_at.lte].",
"status": 400,
"source": {"pointer": "/data/attributes/inserted_at"},
"code": "required",
}
]
)
gte_date = (
datetime.strptime(self.data.get("inserted_at__gte"), "%Y-%m-%d").date()
if self.data.get("inserted_at__gte")
else datetime.now(timezone.utc).date()
)
lte_date = (
datetime.strptime(self.data.get("inserted_at__lte"), "%Y-%m-%d").date()
if self.data.get("inserted_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/inserted_at"},
"code": "invalid",
}
]
)
return super().filter_queryset(queryset)
# Convert filter values to UUIDv7 values for use with partitioning
def filter_scan_id(self, queryset, name, value):
try:
@@ -451,7 +372,9 @@ class FindingFilter(FilterSet):
)
return (
queryset.filter(id__gte=start).filter(id__lt=end).filter(scan_id=value_uuid)
queryset.filter(id__gte=start)
.filter(id__lt=end)
.filter(scan__id=value_uuid)
)
def filter_scan_id_in(self, queryset, name, value):
@@ -476,42 +399,31 @@ class FindingFilter(FilterSet):
]
)
if start == end:
return queryset.filter(id__gte=start).filter(scan_id__in=uuid_list)
return queryset.filter(id__gte=start).filter(scan__id__in=uuid_list)
else:
return (
queryset.filter(id__gte=start)
.filter(id__lt=end)
.filter(scan_id__in=uuid_list)
.filter(scan__id__in=uuid_list)
)
def filter_inserted_at(self, queryset, name, value):
datetime_value = self.maybe_date_to_datetime(value)
start = uuid7_start(datetime_to_uuid7(datetime_value))
end = uuid7_start(datetime_to_uuid7(datetime_value + timedelta(days=1)))
value = self.maybe_date_to_datetime(value)
start = uuid7_start(datetime_to_uuid7(value))
return queryset.filter(id__gte=start, id__lt=end)
return queryset.filter(id__gte=start).filter(inserted_at__date=value)
def filter_inserted_at_gte(self, queryset, name, value):
datetime_value = self.maybe_date_to_datetime(value)
start = uuid7_start(datetime_to_uuid7(datetime_value))
value = self.maybe_date_to_datetime(value)
start = uuid7_start(datetime_to_uuid7(value))
return queryset.filter(id__gte=start)
return queryset.filter(id__gte=start).filter(inserted_at__gte=value)
def filter_inserted_at_lte(self, queryset, name, value):
datetime_value = self.maybe_date_to_datetime(value)
end = uuid7_start(datetime_to_uuid7(datetime_value + timedelta(days=1)))
value = self.maybe_date_to_datetime(value)
end = uuid7_start(datetime_to_uuid7(value))
return queryset.filter(id__lt=end)
def filter_resource_tag(self, queryset, name, value):
overall_query = Q()
for key_value_pair in value:
tag_key, tag_value = key_value_pair.split(":", 1)
overall_query |= Q(
resources__tags__key__icontains=tag_key,
resources__tags__value__icontains=tag_value,
)
return queryset.filter(overall_query).distinct()
return queryset.filter(id__lte=end).filter(inserted_at__lte=value)
@staticmethod
def maybe_date_to_datetime(value):
@@ -573,12 +485,29 @@ class UserFilter(FilterSet):
class RoleFilter(FilterSet):
inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
permission_state = ChoiceFilter(
choices=PermissionChoices.choices, method="filter_permission_state"
)
permission_state = CharFilter(method="filter_permission_state")
def filter_permission_state(self, queryset, name, value):
return Role.filter_by_permission_state(queryset, value)
permission_fields = [
"manage_users",
"manage_account",
"manage_billing",
"manage_providers",
"manage_integrations",
"manage_scans",
]
q_all_true = Q(**{field: True for field in permission_fields})
q_all_false = Q(**{field: False for field in permission_fields})
if value == "unlimited":
return queryset.filter(q_all_true)
elif value == "none":
return queryset.filter(q_all_false)
elif value == "limited":
return queryset.exclude(q_all_true | q_all_false)
else:
return queryset.none()
class Meta:
model = Role
@@ -617,6 +546,12 @@ class ScanSummaryFilter(FilterSet):
field_name="scan__provider__provider", choices=Provider.ProviderChoices.choices
)
region = CharFilter(field_name="region")
muted_findings = BooleanFilter(method="filter_muted_findings")
def filter_muted_findings(self, queryset, name, value):
if not value:
return queryset.exclude(muted__gt=0)
return queryset
class Meta:
model = ScanSummary
@@ -624,39 +559,3 @@ class ScanSummaryFilter(FilterSet):
"inserted_at": ["date", "gte", "lte"],
"region": ["exact", "icontains", "in"],
}
class ServiceOverviewFilter(ScanSummaryFilter):
def is_valid(self):
# Check if at least one of the inserted_at filters is present
inserted_at_filters = [
self.data.get("inserted_at"),
self.data.get("inserted_at__gte"),
self.data.get("inserted_at__lte"),
]
if not any(inserted_at_filters):
raise ValidationError(
{
"inserted_at": [
"At least one of filter[inserted_at], filter[inserted_at__gte], or "
"filter[inserted_at__lte] is required."
]
}
)
return super().is_valid()
class IntegrationFilter(FilterSet):
inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
integration_type = ChoiceFilter(choices=Integration.IntegrationChoices.choices)
integration_type__in = ChoiceInFilter(
choices=Integration.IntegrationChoices.choices,
field_name="integration_type",
lookup_expr="in",
)
class Meta:
model = Integration
fields = {
"inserted_at": ["date", "gte", "lte"],
}

View File

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

View File

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

View File

@@ -6,7 +6,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.823Z",
"updated_at": "2024-10-18T10:46:04.841Z",
"first_seen_at": "2024-10-18T10:46:04.823Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-south-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -62,7 +61,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.855Z",
"updated_at": "2024-10-18T10:46:04.858Z",
"first_seen_at": "2024-10-18T10:46:04.855Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-3-112233445566",
"delta": "new",
"status": "FAIL",
@@ -118,7 +116,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.869Z",
"updated_at": "2024-10-18T10:46:04.876Z",
"first_seen_at": "2024-10-18T10:46:04.869Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-central-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -174,7 +171,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.888Z",
"updated_at": "2024-10-18T10:46:04.892Z",
"first_seen_at": "2024-10-18T10:46:04.888Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -230,7 +226,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.901Z",
"updated_at": "2024-10-18T10:46:04.905Z",
"first_seen_at": "2024-10-18T10:46:04.901Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-east-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -286,7 +281,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.915Z",
"updated_at": "2024-10-18T10:46:04.919Z",
"first_seen_at": "2024-10-18T10:46:04.915Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-south-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -342,7 +336,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.929Z",
"updated_at": "2024-10-18T10:46:04.934Z",
"first_seen_at": "2024-10-18T10:46:04.929Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-west-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -398,7 +391,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.944Z",
"updated_at": "2024-10-18T10:46:04.947Z",
"first_seen_at": "2024-10-18T10:46:04.944Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ca-central-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -454,7 +446,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.957Z",
"updated_at": "2024-10-18T10:46:04.962Z",
"first_seen_at": "2024-10-18T10:46:04.957Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-east-1-ConsoleAnalyzer-83b66ad7-d024-454e-b851-52d11cc1cf7c",
"delta": "new",
"status": "PASS",
@@ -510,7 +501,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.971Z",
"updated_at": "2024-10-18T10:46:04.975Z",
"first_seen_at": "2024-10-18T10:46:04.971Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -566,7 +556,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.984Z",
"updated_at": "2024-10-18T10:46:04.989Z",
"first_seen_at": "2024-10-18T10:46:04.984Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-sa-east-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -622,7 +611,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:04.999Z",
"updated_at": "2024-10-18T10:46:05.003Z",
"first_seen_at": "2024-10-18T10:46:04.999Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-north-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -678,7 +666,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.013Z",
"updated_at": "2024-10-18T10:46:05.018Z",
"first_seen_at": "2024-10-18T10:46:05.013Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-west-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -734,7 +721,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.029Z",
"updated_at": "2024-10-18T10:46:05.033Z",
"first_seen_at": "2024-10-18T10:46:05.029Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-southeast-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -790,7 +776,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.045Z",
"updated_at": "2024-10-18T10:46:05.050Z",
"first_seen_at": "2024-10-18T10:46:05.045Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-central-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -846,7 +831,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.061Z",
"updated_at": "2024-10-18T10:46:05.065Z",
"first_seen_at": "2024-10-18T10:46:05.061Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-1-112233445566",
"delta": "new",
"status": "FAIL",
@@ -902,7 +886,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.080Z",
"updated_at": "2024-10-18T10:46:05.085Z",
"first_seen_at": "2024-10-18T10:46:05.080Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-southeast-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -958,7 +941,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.099Z",
"updated_at": "2024-10-18T10:46:05.104Z",
"first_seen_at": "2024-10-18T10:46:05.099Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-2-112233445566",
"delta": "new",
"status": "FAIL",
@@ -1014,7 +996,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T10:46:05.115Z",
"updated_at": "2024-10-18T10:46:05.121Z",
"first_seen_at": "2024-10-18T10:46:05.115Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-3-112233445566",
"delta": "new",
"status": "FAIL",
@@ -1070,7 +1051,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.489Z",
"updated_at": "2024-10-18T11:16:24.506Z",
"first_seen_at": "2024-10-18T10:46:04.823Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-south-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -1126,7 +1106,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.518Z",
"updated_at": "2024-10-18T11:16:24.521Z",
"first_seen_at": "2024-10-18T10:46:04.855Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-3-112233445566",
"delta": null,
"status": "FAIL",
@@ -1182,7 +1161,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.526Z",
"updated_at": "2024-10-18T11:16:24.529Z",
"first_seen_at": "2024-10-18T10:46:04.869Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-central-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -1238,7 +1216,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.535Z",
"updated_at": "2024-10-18T11:16:24.538Z",
"first_seen_at": "2024-10-18T10:46:04.888Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1294,7 +1271,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.544Z",
"updated_at": "2024-10-18T11:16:24.546Z",
"first_seen_at": "2024-10-18T10:46:04.901Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-east-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -1350,7 +1326,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.551Z",
"updated_at": "2024-10-18T11:16:24.554Z",
"first_seen_at": "2024-10-18T10:46:04.915Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-south-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1406,7 +1381,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.560Z",
"updated_at": "2024-10-18T11:16:24.562Z",
"first_seen_at": "2024-10-18T10:46:04.929Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-west-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1462,7 +1436,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.567Z",
"updated_at": "2024-10-18T11:16:24.569Z",
"first_seen_at": "2024-10-18T10:46:04.944Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ca-central-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1518,7 +1491,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.573Z",
"updated_at": "2024-10-18T11:16:24.575Z",
"first_seen_at": "2024-10-18T10:46:04.957Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-east-1-ConsoleAnalyzer-83b66ad7-d024-454e-b851-52d11cc1cf7c",
"delta": null,
"status": "PASS",
@@ -1574,7 +1546,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.580Z",
"updated_at": "2024-10-18T11:16:24.582Z",
"first_seen_at": "2024-10-18T10:46:04.971Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-west-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -1630,7 +1601,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.587Z",
"updated_at": "2024-10-18T11:16:24.589Z",
"first_seen_at": "2024-10-18T10:46:04.984Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-sa-east-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1686,7 +1656,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.595Z",
"updated_at": "2024-10-18T11:16:24.597Z",
"first_seen_at": "2024-10-18T10:46:04.999Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-north-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1742,7 +1711,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.602Z",
"updated_at": "2024-10-18T11:16:24.604Z",
"first_seen_at": "2024-10-18T10:46:05.013Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-us-west-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -1798,7 +1766,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.610Z",
"updated_at": "2024-10-18T11:16:24.612Z",
"first_seen_at": "2024-10-18T10:46:05.029Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-southeast-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1854,7 +1821,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.617Z",
"updated_at": "2024-10-18T11:16:24.620Z",
"first_seen_at": "2024-10-18T10:46:05.045Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-eu-central-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1910,7 +1876,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.625Z",
"updated_at": "2024-10-18T11:16:24.627Z",
"first_seen_at": "2024-10-18T10:46:05.061Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-1-112233445566",
"delta": null,
"status": "FAIL",
@@ -1966,7 +1931,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.632Z",
"updated_at": "2024-10-18T11:16:24.634Z",
"first_seen_at": "2024-10-18T10:46:05.080Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-southeast-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -2022,7 +1986,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.639Z",
"updated_at": "2024-10-18T11:16:24.642Z",
"first_seen_at": "2024-10-18T10:46:05.099Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-2-112233445566",
"delta": null,
"status": "FAIL",
@@ -2078,7 +2041,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:24.646Z",
"updated_at": "2024-10-18T11:16:24.648Z",
"first_seen_at": "2024-10-18T10:46:05.115Z",
"uid": "prowler-aws-accessanalyzer_enabled-112233445566-ap-northeast-3-112233445566",
"delta": null,
"status": "FAIL",
@@ -2134,7 +2096,6 @@
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"inserted_at": "2024-10-18T11:16:26.033Z",
"updated_at": "2024-10-18T11:16:26.045Z",
"first_seen_at": "2024-10-18T11:16:26.033Z",
"uid": "prowler-aws-account_security_contact_information_is_registered-112233445566-us-east-1-112233445566",
"delta": "new",
"status": "MANUAL",

View File

@@ -64,7 +64,7 @@
"pk": "3f01e759-bdf9-4a99-8888-1ab805b79f93",
"fields": {
"tenant": "12646005-9067-4d2a-a098-8bb378604362",
"name": "admin_test",
"name": "admin",
"manage_users": true,
"manage_account": true,
"manage_billing": true,

View File

@@ -1,237 +0,0 @@
import random
from datetime import datetime, timezone
from math import ceil
from uuid import uuid4
from django.core.management.base import BaseCommand
from tqdm import tqdm
from api.db_utils import rls_transaction
from api.models import (
Finding,
Provider,
Resource,
ResourceFindingMapping,
Scan,
StatusChoices,
)
from prowler.lib.check.models import CheckMetadata
class Command(BaseCommand):
help = "Populates the database with test data for performance testing."
def add_arguments(self, parser):
parser.add_argument(
"--tenant",
type=str,
required=True,
help="Tenant id for which the data will be populated.",
)
parser.add_argument(
"--resources",
type=int,
required=True,
help="The number of resources to create.",
)
parser.add_argument(
"--findings",
type=int,
required=True,
help="The number of findings to create.",
)
parser.add_argument(
"--batch", type=int, required=True, help="The batch size for bulk creation."
)
parser.add_argument(
"--alias",
type=str,
required=False,
help="Optional alias for the provider and scan",
)
def handle(self, *args, **options):
tenant_id = options["tenant"]
num_resources = options["resources"]
num_findings = options["findings"]
batch_size = options["batch"]
alias = options["alias"] or "Testing"
uid_token = str(uuid4())
self.stdout.write(self.style.NOTICE("Starting data population"))
self.stdout.write(self.style.NOTICE(f"\tTenant: {tenant_id}"))
self.stdout.write(self.style.NOTICE(f"\tAlias: {alias}"))
self.stdout.write(self.style.NOTICE(f"\tResources: {num_resources}"))
self.stdout.write(self.style.NOTICE(f"\tFindings: {num_findings}"))
self.stdout.write(self.style.NOTICE(f"\tBatch size: {batch_size}\n\n"))
# Resource metadata
possible_regions = [
"us-east-1",
"us-east-2",
"us-west-1",
"us-west-2",
"ca-central-1",
"eu-central-1",
"eu-west-1",
"eu-west-2",
"eu-west-3",
"ap-southeast-1",
"ap-southeast-2",
"ap-northeast-1",
"ap-northeast-2",
"ap-south-1",
"sa-east-1",
]
possible_services = []
possible_types = []
bulk_check_metadata = CheckMetadata.get_bulk(provider="aws")
for check_metadata in bulk_check_metadata.values():
if check_metadata.ServiceName not in possible_services:
possible_services.append(check_metadata.ServiceName)
if (
check_metadata.ResourceType
and check_metadata.ResourceType not in possible_types
):
possible_types.append(check_metadata.ResourceType)
with rls_transaction(tenant_id):
provider, _ = Provider.all_objects.get_or_create(
tenant_id=tenant_id,
provider="aws",
connected=True,
uid=str(random.randint(100000000000, 999999999999)),
defaults={
"alias": alias,
},
)
with rls_transaction(tenant_id):
scan = Scan.all_objects.create(
tenant_id=tenant_id,
provider=provider,
name=alias,
trigger="manual",
state="executing",
progress=0,
started_at=datetime.now(timezone.utc),
)
scan_state = "completed"
try:
# Create resources
resources = []
for i in range(num_resources):
resources.append(
Resource(
tenant_id=tenant_id,
provider_id=provider.id,
uid=f"testing-{uid_token}-{i}",
name=f"Testing {uid_token}-{i}",
region=random.choice(possible_regions),
service=random.choice(possible_services),
type=random.choice(possible_types),
)
)
num_batches = ceil(len(resources) / batch_size)
self.stdout.write(self.style.WARNING("Creating resources..."))
for i in tqdm(range(0, len(resources), batch_size), total=num_batches):
with rls_transaction(tenant_id):
Resource.all_objects.bulk_create(resources[i : i + batch_size])
self.stdout.write(self.style.SUCCESS("Resources created successfully.\n\n"))
with rls_transaction(tenant_id):
scan.progress = 33
scan.save()
# Create Findings
findings = []
possible_deltas = ["new", "changed", None]
possible_severities = ["critical", "high", "medium", "low"]
findings_resources_mapping = []
for i in range(num_findings):
severity = random.choice(possible_severities)
check_id = random.randint(1, 1000)
assigned_resource_num = random.randint(0, len(resources) - 1)
assigned_resource = resources[assigned_resource_num]
findings_resources_mapping.append(assigned_resource_num)
findings.append(
Finding(
tenant_id=tenant_id,
scan=scan,
uid=f"testing-{uid_token}-{i}",
delta=random.choice(possible_deltas),
check_id=f"check-{check_id}",
status=random.choice(list(StatusChoices)),
severity=severity,
impact=severity,
raw_result={},
check_metadata={
"checktitle": f"Test title for check {check_id}",
"risk": f"Testing risk {uid_token}-{i}",
"provider": "aws",
"severity": severity,
"categories": ["category1", "category2", "category3"],
"description": "This is a random description that should not matter for testing purposes.",
"servicename": assigned_resource.service,
"resourcetype": assigned_resource.type,
},
)
)
num_batches = ceil(len(findings) / batch_size)
self.stdout.write(self.style.WARNING("Creating findings..."))
for i in tqdm(range(0, len(findings), batch_size), total=num_batches):
with rls_transaction(tenant_id):
Finding.all_objects.bulk_create(findings[i : i + batch_size])
self.stdout.write(self.style.SUCCESS("Findings created successfully.\n\n"))
with rls_transaction(tenant_id):
scan.progress = 66
scan.save()
# Create ResourceFindingMapping
mappings = []
for index, f in enumerate(findings):
mappings.append(
ResourceFindingMapping(
tenant_id=tenant_id,
resource=resources[findings_resources_mapping[index]],
finding=f,
)
)
num_batches = ceil(len(mappings) / batch_size)
self.stdout.write(
self.style.WARNING("Creating resource-finding mappings...")
)
for i in tqdm(range(0, len(mappings), batch_size), total=num_batches):
with rls_transaction(tenant_id):
ResourceFindingMapping.objects.bulk_create(
mappings[i : i + batch_size]
)
self.stdout.write(
self.style.SUCCESS(
"Resource-finding mappings created successfully.\n\n"
)
)
except Exception as e:
self.stdout.write(self.style.ERROR(f"Failed to populate test data: {e}"))
scan_state = "failed"
finally:
scan.completed_at = datetime.now(timezone.utc)
scan.duration = int(
(datetime.now(timezone.utc) - scan.started_at).total_seconds()
)
scan.progress = 100
scan.state = scan_state
scan.unique_resource_count = num_resources
with rls_transaction(tenant_id):
scan.save()
self.stdout.write(self.style.NOTICE("Successfully populated test data."))

View File

@@ -552,7 +552,7 @@ class Migration(migrations.Migration):
migrations.AddConstraint(
model_name="providergroupmembership",
constraint=models.UniqueConstraint(
fields=("provider_id", "provider_group"),
fields=("provider_id", "provider_group_id"),
name="unique_provider_group_membership",
),
),

View File

@@ -1,17 +1,15 @@
# Generated by Django 5.1.1 on 2024-12-05 12:29
import uuid
import api.rls
import django.db.models.deletion
import uuid
from django.conf import settings
from django.db import migrations, models
import api.rls
class Migration(migrations.Migration):
dependencies = [
("api", "0003_update_provider_unique_constraint_with_is_deleted"),
("api", "0002_token_migrations"),
]
operations = [

View File

@@ -1,23 +0,0 @@
# Generated by Django 5.1.1 on 2024-12-20 13:16
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("api", "0002_token_migrations"),
]
operations = [
migrations.RemoveConstraint(
model_name="provider",
name="unique_provider_uids",
),
migrations.AddConstraint(
model_name="provider",
constraint=models.UniqueConstraint(
fields=("tenant_id", "provider", "uid", "is_deleted"),
name="unique_provider_uids",
),
),
]

View File

@@ -1,44 +0,0 @@
from django.db import migrations
from api.db_router import MainRouter
def create_admin_role(apps, schema_editor):
Tenant = apps.get_model("api", "Tenant")
Role = apps.get_model("api", "Role")
User = apps.get_model("api", "User")
UserRoleRelationship = apps.get_model("api", "UserRoleRelationship")
for tenant in Tenant.objects.using(MainRouter.admin_db).all():
admin_role, _ = Role.objects.using(MainRouter.admin_db).get_or_create(
name="admin",
tenant=tenant,
defaults={
"manage_users": True,
"manage_account": True,
"manage_billing": True,
"manage_providers": True,
"manage_integrations": True,
"manage_scans": True,
"unlimited_visibility": True,
},
)
users = User.objects.using(MainRouter.admin_db).filter(
membership__tenant=tenant
)
for user in users:
UserRoleRelationship.objects.using(MainRouter.admin_db).get_or_create(
user=user,
role=admin_role,
tenant=tenant,
)
class Migration(migrations.Migration):
dependencies = [
("api", "0004_rbac"),
]
operations = [
migrations.RunPython(create_admin_role),
]

View File

@@ -1,15 +0,0 @@
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("api", "0005_rbac_missing_admin_roles"),
]
operations = [
migrations.AddField(
model_name="finding",
name="first_seen_at",
field=models.DateTimeField(editable=False, null=True),
),
]

View File

@@ -1,25 +0,0 @@
# Generated by Django 5.1.5 on 2025-01-28 15:03
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("api", "0006_findings_first_seen"),
]
operations = [
migrations.AddIndex(
model_name="scan",
index=models.Index(
fields=["tenant_id", "provider_id", "state", "inserted_at"],
name="scans_prov_state_insert_idx",
),
),
migrations.AddIndex(
model_name="scansummary",
index=models.Index(
fields=["tenant_id", "scan_id"], name="scan_summaries_tenant_scan_idx"
),
),
]

View File

@@ -1,64 +0,0 @@
import json
from datetime import datetime, timedelta, timezone
import django.db.models.deletion
from django.db import migrations, models
from django_celery_beat.models import PeriodicTask
from api.db_utils import rls_transaction
from api.models import Scan, StateChoices
def migrate_daily_scheduled_scan_tasks(apps, schema_editor):
for daily_scheduled_scan_task in PeriodicTask.objects.filter(
task="scan-perform-scheduled"
):
task_kwargs = json.loads(daily_scheduled_scan_task.kwargs)
tenant_id = task_kwargs["tenant_id"]
provider_id = task_kwargs["provider_id"]
current_time = datetime.now(timezone.utc)
scheduled_time_today = datetime.combine(
current_time.date(),
daily_scheduled_scan_task.start_time.time(),
tzinfo=timezone.utc,
)
if current_time < scheduled_time_today:
next_scan_date = scheduled_time_today
else:
next_scan_date = scheduled_time_today + timedelta(days=1)
with rls_transaction(tenant_id):
Scan.objects.create(
tenant_id=tenant_id,
name="Daily scheduled scan",
provider_id=provider_id,
trigger=Scan.TriggerChoices.SCHEDULED,
state=StateChoices.SCHEDULED,
scheduled_at=next_scan_date,
scheduler_task_id=daily_scheduled_scan_task.id,
)
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0007_scan_and_scan_summaries_indexes"),
("django_celery_beat", "0019_alter_periodictasks_options"),
]
operations = [
migrations.AddField(
model_name="scan",
name="scheduler_task",
field=models.ForeignKey(
blank=True,
null=True,
on_delete=django.db.models.deletion.CASCADE,
to="django_celery_beat.periodictask",
),
),
migrations.RunPython(migrate_daily_scheduled_scan_tasks),
]

View File

@@ -1,22 +0,0 @@
# Generated by Django 5.1.5 on 2025-02-07 09:42
import django.core.validators
from django.db import migrations, models
class Migration(migrations.Migration):
dependencies = [
("api", "0008_daily_scheduled_tasks_update"),
]
operations = [
migrations.AlterField(
model_name="provider",
name="uid",
field=models.CharField(
max_length=250,
validators=[django.core.validators.MinLengthValidator(3)],
verbose_name="Unique identifier for the provider, set by the provider",
),
),
]

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -11,7 +11,6 @@ from django.core.validators import MinLengthValidator
from django.db import models
from django.db.models import Q
from django.utils.translation import gettext_lazy as _
from django_celery_beat.models import PeriodicTask
from django_celery_results.models import TaskResult
from psqlextra.manager import PostgresManager
from psqlextra.models import PostgresPartitionedModel
@@ -21,7 +20,6 @@ from uuid6 import uuid7
from api.db_utils import (
CustomUserManager,
FindingDeltaEnumField,
IntegrationTypeEnumField,
InvitationStateEnumField,
MemberRoleEnumField,
ProviderEnumField,
@@ -59,6 +57,7 @@ class StatusChoices(models.TextChoices):
FAIL = "FAIL", _("Fail")
PASS = "PASS", _("Pass")
MANUAL = "MANUAL", _("Manual")
MUTED = "MUTED", _("Muted")
class StateChoices(models.TextChoices):
@@ -70,21 +69,6 @@ class StateChoices(models.TextChoices):
CANCELLED = "cancelled", _("Cancelled")
class PermissionChoices(models.TextChoices):
"""
Represents the different permission states that a role can have.
Attributes:
UNLIMITED: Indicates that the role possesses all permissions.
LIMITED: Indicates that the role has some permissions but not all.
NONE: Indicates that the role does not have any permissions.
"""
UNLIMITED = "unlimited", _("Unlimited permissions")
LIMITED = "limited", _("Limited permissions")
NONE = "none", _("No permissions")
class ActiveProviderManager(models.Manager):
def get_queryset(self):
return super().get_queryset().filter(self.active_provider_filter())
@@ -227,13 +211,13 @@ class Provider(RowLevelSecurityProtectedModel):
@staticmethod
def validate_kubernetes_uid(value):
if not re.match(
r"^[a-z0-9][A-Za-z0-9_.:\/-]{1,250}$",
r"(^[a-z0-9]([-a-z0-9]{1,61}[a-z0-9])?$)|(^arn:aws(-cn|-us-gov|-iso|-iso-b)?:[a-zA-Z0-9\-]+:([a-z]{2}-[a-z]+-\d{1})?:(\d{12})?:[a-zA-Z0-9\-_\/:\.\*]+(:\d+)?$)",
value,
):
raise ModelValidationError(
detail="The value must either be a valid Kubernetes UID (up to 63 characters, "
"starting and ending with a lowercase letter or number, containing only "
"lowercase alphanumeric characters and hyphens) or a valid AWS EKS Cluster ARN, GCP GKE Context Name or Azure AKS Cluster Name.",
"lowercase alphanumeric characters and hyphens) or a valid EKS ARN.",
code="kubernetes-uid",
pointer="/data/attributes/uid",
)
@@ -247,7 +231,7 @@ class Provider(RowLevelSecurityProtectedModel):
)
uid = models.CharField(
"Unique identifier for the provider, set by the provider",
max_length=250,
max_length=63,
blank=False,
validators=[MinLengthValidator(3)],
)
@@ -272,7 +256,7 @@ class Provider(RowLevelSecurityProtectedModel):
constraints = [
models.UniqueConstraint(
fields=("tenant_id", "provider", "uid", "is_deleted"),
fields=("tenant_id", "provider", "uid"),
name="unique_provider_uids",
),
RowLevelSecurityConstraint(
@@ -310,7 +294,7 @@ class ProviderGroup(RowLevelSecurityProtectedModel):
]
class JSONAPIMeta:
resource_name = "provider-groups"
resource_name = "provider-group"
class ProviderGroupMembership(RowLevelSecurityProtectedModel):
@@ -323,7 +307,7 @@ class ProviderGroupMembership(RowLevelSecurityProtectedModel):
db_table = "provider_group_memberships"
constraints = [
models.UniqueConstraint(
fields=["provider_id", "provider_group"],
fields=["provider_id", "provider_group_id"],
name="unique_provider_group_membership",
),
RowLevelSecurityConstraint(
@@ -411,10 +395,6 @@ class Scan(RowLevelSecurityProtectedModel):
started_at = models.DateTimeField(null=True, blank=True)
completed_at = models.DateTimeField(null=True, blank=True)
next_scan_at = models.DateTimeField(null=True, blank=True)
scheduler_task = models.ForeignKey(
PeriodicTask, on_delete=models.CASCADE, null=True, blank=True
)
output_location = models.CharField(blank=True, null=True, max_length=200)
# TODO: mutelist foreign key
class Meta(RowLevelSecurityProtectedModel.Meta):
@@ -433,10 +413,6 @@ class Scan(RowLevelSecurityProtectedModel):
fields=["provider", "state", "trigger", "scheduled_at"],
name="scans_prov_state_trig_sche_idx",
),
models.Index(
fields=["tenant_id", "provider_id", "state", "inserted_at"],
name="scans_prov_state_insert_idx",
),
]
class JSONAPIMeta:
@@ -518,19 +494,14 @@ class Resource(RowLevelSecurityProtectedModel):
editable=False,
)
metadata = models.TextField(blank=True, null=True)
details = models.TextField(blank=True, null=True)
partition = models.TextField(blank=True, null=True)
# Relationships
tags = models.ManyToManyField(
ResourceTag,
verbose_name="Tags associated with the resource, by provider",
through="ResourceTagMapping",
)
def get_tags(self, tenant_id: str) -> dict:
return {tag.key: tag.value for tag in self.tags.filter(tenant_id=tenant_id)}
def get_tags(self) -> dict:
return {tag.key: tag.value for tag in self.tags.all()}
def clear_tags(self):
self.tags.clear()
@@ -558,10 +529,6 @@ class Resource(RowLevelSecurityProtectedModel):
fields=["uid", "region", "service", "name"],
name="resource_uid_reg_serv_name_idx",
),
models.Index(
fields=["tenant_id", "service", "region", "type"],
name="resource_tenant_metadata_idx",
),
GinIndex(fields=["text_search"], name="gin_resources_search_idx"),
]
@@ -609,12 +576,6 @@ class ResourceTagMapping(RowLevelSecurityProtectedModel):
),
]
indexes = [
models.Index(
fields=["tenant_id", "resource_id"], name="resource_tag_tenant_idx"
),
]
class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
"""
@@ -639,7 +600,6 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
id = models.UUIDField(primary_key=True, default=uuid7, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
updated_at = models.DateTimeField(auto_now=True, editable=False)
first_seen_at = models.DateTimeField(editable=False, null=True)
uid = models.CharField(max_length=300)
delta = FindingDeltaEnumField(
@@ -660,8 +620,6 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
tags = models.JSONField(default=dict, null=True, blank=True)
check_id = models.CharField(max_length=100, blank=False, null=False)
check_metadata = models.JSONField(default=dict, null=False)
muted = models.BooleanField(default=False, null=False)
compliance = models.JSONField(default=dict, null=True, blank=True)
# Relationships
scan = models.ForeignKey(to=Scan, related_name="findings", on_delete=models.CASCADE)
@@ -715,17 +673,7 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
],
name="findings_filter_idx",
),
models.Index(fields=["tenant_id", "id"], name="findings_tenant_and_id_idx"),
GinIndex(fields=["text_search"], name="gin_findings_search_idx"),
models.Index(fields=["tenant_id", "scan_id"], name="find_tenant_scan_idx"),
models.Index(
fields=["tenant_id", "scan_id", "id"], name="find_tenant_scan_id_idx"
),
models.Index(
fields=["tenant_id", "id"],
condition=Q(delta="new"),
name="find_delta_new_idx",
),
]
class JSONAPIMeta:
@@ -916,38 +864,6 @@ class Role(RowLevelSecurityProtectedModel):
Invitation, through="InvitationRoleRelationship", related_name="roles"
)
# Filter permission_state
PERMISSION_FIELDS = [
"manage_users",
"manage_account",
"manage_billing",
"manage_providers",
"manage_integrations",
"manage_scans",
]
@property
def permission_state(self):
values = [getattr(self, field) for field in self.PERMISSION_FIELDS]
if all(values):
return PermissionChoices.UNLIMITED
elif not any(values):
return PermissionChoices.NONE
else:
return PermissionChoices.LIMITED
@classmethod
def filter_by_permission_state(cls, queryset, value):
q_all_true = Q(**{field: True for field in cls.PERMISSION_FIELDS})
q_all_false = Q(**{field: False for field in cls.PERMISSION_FIELDS})
if value == PermissionChoices.UNLIMITED:
return queryset.filter(q_all_true)
elif value == PermissionChoices.NONE:
return queryset.filter(q_all_false)
else:
return queryset.exclude(q_all_true | q_all_false)
class Meta:
db_table = "roles"
constraints = [
@@ -963,7 +879,7 @@ class Role(RowLevelSecurityProtectedModel):
]
class JSONAPIMeta:
resource_name = "roles"
resource_name = "role"
class RoleProviderGroupRelationship(RowLevelSecurityProtectedModel):
@@ -1136,89 +1052,6 @@ class ScanSummary(RowLevelSecurityProtectedModel):
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]
indexes = [
models.Index(
fields=["tenant_id", "scan_id"],
name="scan_summaries_tenant_scan_idx",
)
]
class JSONAPIMeta:
resource_name = "scan-summaries"
class Integration(RowLevelSecurityProtectedModel):
class IntegrationChoices(models.TextChoices):
S3 = "amazon_s3", _("Amazon S3")
SAML = "saml", _("SAML")
AWS_SECURITY_HUB = "aws_security_hub", _("AWS Security Hub")
JIRA = "jira", _("JIRA")
SLACK = "slack", _("Slack")
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
updated_at = models.DateTimeField(auto_now=True, editable=False)
enabled = models.BooleanField(default=False)
connected = models.BooleanField(null=True, blank=True)
connection_last_checked_at = models.DateTimeField(null=True, blank=True)
integration_type = IntegrationTypeEnumField(choices=IntegrationChoices.choices)
configuration = models.JSONField(default=dict)
_credentials = models.BinaryField(db_column="credentials")
providers = models.ManyToManyField(
Provider,
related_name="integrations",
through="IntegrationProviderRelationship",
blank=True,
)
class Meta(RowLevelSecurityProtectedModel.Meta):
db_table = "integrations"
constraints = [
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]
class JSONAPIMeta:
resource_name = "integrations"
@property
def credentials(self):
if isinstance(self._credentials, memoryview):
encrypted_bytes = self._credentials.tobytes()
elif isinstance(self._credentials, str):
encrypted_bytes = self._credentials.encode()
else:
encrypted_bytes = self._credentials
decrypted_data = fernet.decrypt(encrypted_bytes)
return json.loads(decrypted_data.decode())
@credentials.setter
def credentials(self, value):
encrypted_data = fernet.encrypt(json.dumps(value).encode())
self._credentials = encrypted_data
class IntegrationProviderRelationship(RowLevelSecurityProtectedModel):
id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
integration = models.ForeignKey(Integration, on_delete=models.CASCADE)
provider = models.ForeignKey(Provider, on_delete=models.CASCADE)
inserted_at = models.DateTimeField(auto_now_add=True)
class Meta:
db_table = "integration_provider_mappings"
constraints = [
models.UniqueConstraint(
fields=["integration_id", "provider_id"],
name="unique_integration_provider_rel",
),
RowLevelSecurityConstraint(
field="tenant_id",
name="rls_on_%(class)s",
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
),
]

View File

@@ -1,12 +1,8 @@
from config.django.base import DISABLE_RBAC
from enum import Enum
from typing import Optional
from django.db.models import QuerySet
from rest_framework.permissions import BasePermission
from api.db_router import MainRouter
from api.models import Provider, Role, User
class Permissions(Enum):
MANAGE_USERS = "manage_users"
@@ -25,13 +21,15 @@ class HasPermissions(BasePermission):
"""
def has_permission(self, request, view):
# This is for testing/demo purposes only
if DISABLE_RBAC:
return True
required_permissions = getattr(view, "required_permissions", [])
if not required_permissions:
return True
user_roles = (
User.objects.using(MainRouter.admin_db).get(id=request.user.id).roles.all()
)
user_roles = request.user.roles.all()
if not user_roles:
return False
@@ -40,36 +38,3 @@ class HasPermissions(BasePermission):
return False
return True
def get_role(user: User) -> Optional[Role]:
"""
Retrieve the first role assigned to the given user.
Returns:
The user's first Role instance if the user has any roles, otherwise None.
"""
return user.roles.first()
def get_providers(role: Role) -> QuerySet[Provider]:
"""
Return a distinct queryset of Providers accessible by the given role.
If the role has no associated provider groups, an empty queryset is returned.
Args:
role: A Role instance.
Returns:
A QuerySet of Provider objects filtered by the role's provider groups.
If the role has no provider groups, returns an empty queryset.
"""
tenant = role.tenant
provider_groups = role.provider_groups.all()
if not provider_groups.exists():
return Provider.objects.none()
return Provider.objects.filter(
tenant=tenant, provider_groups__in=provider_groups
).distinct()

View File

@@ -2,7 +2,7 @@ from contextlib import nullcontext
from rest_framework_json_api.renderers import JSONRenderer
from api.db_utils import rls_transaction
from api.db_utils import tenant_transaction
class APIJSONRenderer(JSONRenderer):
@@ -13,9 +13,9 @@ class APIJSONRenderer(JSONRenderer):
tenant_id = getattr(request, "tenant_id", None) if request else None
include_param_present = "include" in request.query_params if request else False
# Use rls_transaction if needed for included resources, otherwise do nothing
# Use tenant_transaction if needed for included resources, otherwise do nothing
context_manager = (
rls_transaction(tenant_id)
tenant_transaction(tenant_id)
if tenant_id and include_param_present
else nullcontext()
)

View File

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

View File

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

File diff suppressed because it is too large Load Diff

View File

@@ -1,11 +1,12 @@
import pytest
from conftest import TEST_PASSWORD, get_api_tokens, get_authorization_header
from django.urls import reverse
from unittest.mock import patch
from rest_framework.test import APIClient
from api.models import Membership, User
from conftest import TEST_PASSWORD, get_api_tokens, get_authorization_header
@patch("api.v1.views.MainRouter.admin_db", new="default")
@pytest.mark.django_db
def test_basic_authentication():
client = APIClient()
@@ -97,204 +98,3 @@ def test_refresh_token(create_test_user, tenants_fixture):
format="vnd.api+json",
)
assert new_refresh_response.status_code == 200
@pytest.mark.django_db
def test_user_me_when_inviting_users(create_test_user, tenants_fixture, roles_fixture):
client = APIClient()
role = roles_fixture[0]
user1_email = "user1@testing.com"
user2_email = "user2@testing.com"
password = "thisisapassword123"
user1_response = client.post(
reverse("user-list"),
data={
"data": {
"type": "users",
"attributes": {
"name": "user1",
"email": user1_email,
"password": password,
},
}
},
format="vnd.api+json",
)
assert user1_response.status_code == 201
user1_access_token, _ = get_api_tokens(client, user1_email, password)
user1_headers = get_authorization_header(user1_access_token)
user2_invitation = client.post(
reverse("invitation-list"),
data={
"data": {
"type": "invitations",
"attributes": {"email": user2_email},
"relationships": {
"roles": {
"data": [
{
"type": "roles",
"id": str(role.id),
}
]
}
},
}
},
format="vnd.api+json",
headers=user1_headers,
)
assert user2_invitation.status_code == 201
invitation_token = user2_invitation.json()["data"]["attributes"]["token"]
user2_response = client.post(
reverse("user-list") + f"?invitation_token={invitation_token}",
data={
"data": {
"type": "users",
"attributes": {
"name": "user2",
"email": user2_email,
"password": password,
},
}
},
format="vnd.api+json",
)
assert user2_response.status_code == 201
user2_access_token, _ = get_api_tokens(client, user2_email, password)
user2_headers = get_authorization_header(user2_access_token)
user1_me = client.get(reverse("user-me"), headers=user1_headers)
assert user1_me.status_code == 200
assert user1_me.json()["data"]["attributes"]["email"] == user1_email
user2_me = client.get(reverse("user-me"), headers=user2_headers)
assert user2_me.status_code == 200
assert user2_me.json()["data"]["attributes"]["email"] == user2_email
@pytest.mark.django_db
class TestTokenSwitchTenant:
def test_switch_tenant_with_valid_token(self, tenants_fixture, providers_fixture):
client = APIClient()
test_user = "test_email@prowler.com"
test_password = "test_password"
# Check that we can create a new user without any kind of authentication
user_creation_response = client.post(
reverse("user-list"),
data={
"data": {
"type": "users",
"attributes": {
"name": "test",
"email": test_user,
"password": test_password,
},
}
},
format="vnd.api+json",
)
assert user_creation_response.status_code == 201
# Create a new relationship between this user and another tenant
tenant_id = tenants_fixture[0].id
user_instance = User.objects.get(email=test_user)
Membership.objects.create(user=user_instance, tenant_id=tenant_id)
# Check that using our new user's credentials we can authenticate and get the providers
access_token, _ = get_api_tokens(client, test_user, test_password)
auth_headers = get_authorization_header(access_token)
user_me_response = client.get(
reverse("user-me"),
headers=auth_headers,
)
assert user_me_response.status_code == 200
# Assert this user belongs to two tenants
assert (
user_me_response.json()["data"]["relationships"]["memberships"]["meta"][
"count"
]
== 2
)
provider_response = client.get(
reverse("provider-list"),
headers=auth_headers,
)
assert provider_response.status_code == 200
# Empty response since there are no providers in this tenant
assert not provider_response.json()["data"]
switch_tenant_response = client.post(
reverse("token-switch"),
data={
"data": {
"type": "tokens-switch-tenant",
"attributes": {"tenant_id": tenant_id},
}
},
headers=auth_headers,
)
assert switch_tenant_response.status_code == 200
new_access_token = switch_tenant_response.json()["data"]["attributes"]["access"]
new_auth_headers = get_authorization_header(new_access_token)
provider_response = client.get(
reverse("provider-list"),
headers=new_auth_headers,
)
assert provider_response.status_code == 200
# Now it must be data because we switched to another tenant with providers
assert provider_response.json()["data"]
def test_switch_tenant_with_invalid_token(self, create_test_user, tenants_fixture):
client = APIClient()
access_token, refresh_token = get_api_tokens(
client, create_test_user.email, TEST_PASSWORD
)
auth_headers = get_authorization_header(access_token)
invalid_token_response = client.post(
reverse("token-switch"),
data={
"data": {
"type": "tokens-switch-tenant",
"attributes": {"tenant_id": "invalid_tenant_id"},
}
},
headers=auth_headers,
)
assert invalid_token_response.status_code == 400
assert invalid_token_response.json()["errors"][0]["code"] == "invalid"
assert (
invalid_token_response.json()["errors"][0]["detail"]
== "Must be a valid UUID."
)
invalid_tenant_response = client.post(
reverse("token-switch"),
data={
"data": {
"type": "tokens-switch-tenant",
"attributes": {"tenant_id": tenants_fixture[-1].id},
}
},
headers=auth_headers,
)
assert invalid_tenant_response.status_code == 400
assert invalid_tenant_response.json()["errors"][0]["code"] == "invalid"
assert invalid_tenant_response.json()["errors"][0]["detail"] == (
"Tenant does not exist or user is not a " "member."
)

View File

@@ -1,85 +0,0 @@
from unittest.mock import Mock, patch
import pytest
from conftest import get_api_tokens, get_authorization_header
from django.urls import reverse
from rest_framework.test import APIClient
from api.models import Provider
@patch("api.v1.views.Task.objects.get")
@patch("api.v1.views.delete_provider_task.delay")
@pytest.mark.django_db
def test_delete_provider_without_executing_task(
mock_delete_task, mock_task_get, create_test_user, tenants_fixture, tasks_fixture
):
client = APIClient()
test_user = "test_email@prowler.com"
test_password = "test_password"
prowler_task = tasks_fixture[0]
task_mock = Mock()
task_mock.id = prowler_task.id
mock_delete_task.return_value = task_mock
mock_task_get.return_value = prowler_task
user_creation_response = client.post(
reverse("user-list"),
data={
"data": {
"type": "users",
"attributes": {
"name": "test",
"email": test_user,
"password": test_password,
},
}
},
format="vnd.api+json",
)
assert user_creation_response.status_code == 201
access_token, _ = get_api_tokens(client, test_user, test_password)
auth_headers = get_authorization_header(access_token)
create_provider_response = client.post(
reverse("provider-list"),
data={
"data": {
"type": "providers",
"attributes": {
"provider": Provider.ProviderChoices.AWS,
"uid": "123456789012",
},
}
},
format="vnd.api+json",
headers=auth_headers,
)
assert create_provider_response.status_code == 201
provider_id = create_provider_response.json()["data"]["id"]
provider_uid = create_provider_response.json()["data"]["attributes"]["uid"]
remove_provider = client.delete(
reverse("provider-detail", kwargs={"pk": provider_id}),
headers=auth_headers,
)
assert remove_provider.status_code == 202
recreate_provider_response = client.post(
reverse("provider-list"),
data={
"data": {
"type": "providers",
"attributes": {
"provider": Provider.ProviderChoices.AWS,
"uid": provider_uid,
},
}
},
format="vnd.api+json",
headers=auth_headers,
)
assert recreate_provider_response.status_code == 201

View File

@@ -11,9 +11,9 @@ from conftest import TEST_USER, TEST_PASSWORD, get_api_tokens, get_authorization
def test_check_resources_between_different_tenants(
schedule_mock,
enforce_test_user_db_connection,
patch_testing_flag,
authenticated_api_client,
tenants_fixture,
set_user_admin_roles_fixture,
):
client = authenticated_api_client

View File

@@ -1,19 +1,9 @@
from unittest.mock import ANY, Mock, patch
# TODO: Enable this tests
import pytest
from django.urls import reverse
from rest_framework import status
from api.models import (
Membership,
ProviderGroup,
ProviderGroupMembership,
Role,
RoleProviderGroupRelationship,
User,
UserRoleRelationship,
)
from api.v1.serializers import TokenSerializer
from unittest.mock import patch, ANY, Mock
@pytest.mark.django_db
@@ -41,14 +31,6 @@ class TestUserViewSet:
== create_test_user_rbac.email
)
def test_retrieve_user_with_no_roles(
self, authenticated_client_rbac_noroles, create_test_user_rbac_no_roles
):
response = authenticated_client_rbac_noroles.get(
reverse("user-detail", kwargs={"pk": create_test_user_rbac_no_roles.id})
)
assert response.status_code == status.HTTP_403_FORBIDDEN
def test_retrieve_user_with_no_permissions(
self, authenticated_client_no_permissions_rbac, create_test_user
):
@@ -57,6 +39,7 @@ class TestUserViewSet:
)
assert response.status_code == status.HTTP_403_FORBIDDEN
@patch("api.db_router.MainRouter.admin_db", new="default")
def test_create_user_with_all_permissions(self, authenticated_client_rbac):
valid_user_payload = {
"name": "test",
@@ -69,6 +52,7 @@ class TestUserViewSet:
assert response.status_code == status.HTTP_201_CREATED
assert response.json()["data"]["attributes"]["email"] == "new_user@test.com"
@patch("api.db_router.MainRouter.admin_db", new="default")
def test_create_user_with_no_permissions(
self, authenticated_client_no_permissions_rbac
):
@@ -316,96 +300,3 @@ class TestProviderViewSet:
reverse("provider-connection", kwargs={"pk": provider.id})
)
assert response.status_code == status.HTTP_403_FORBIDDEN
@pytest.mark.django_db
class TestLimitedVisibility:
TEST_EMAIL = "rbac@rbac.com"
TEST_PASSWORD = "thisisapassword123"
@pytest.fixture
def limited_admin_user(
self, django_db_setup, django_db_blocker, tenants_fixture, providers_fixture
):
with django_db_blocker.unblock():
tenant = tenants_fixture[0]
provider = providers_fixture[0]
user = User.objects.create_user(
name="testing",
email=self.TEST_EMAIL,
password=self.TEST_PASSWORD,
)
Membership.objects.create(
user=user,
tenant=tenant,
role=Membership.RoleChoices.OWNER,
)
role = Role.objects.create(
name="limited_visibility",
tenant=tenant,
manage_users=True,
manage_account=True,
manage_billing=True,
manage_providers=True,
manage_integrations=True,
manage_scans=True,
unlimited_visibility=False,
)
UserRoleRelationship.objects.create(
user=user,
role=role,
tenant=tenant,
)
provider_group = ProviderGroup.objects.create(
name="limited_visibility_group",
tenant=tenant,
)
ProviderGroupMembership.objects.create(
tenant=tenant,
provider=provider,
provider_group=provider_group,
)
RoleProviderGroupRelationship.objects.create(
tenant=tenant, role=role, provider_group=provider_group
)
return user
@pytest.fixture
def authenticated_client_rbac_limited(
self, limited_admin_user, tenants_fixture, client
):
client.user = limited_admin_user
tenant_id = tenants_fixture[0].id
serializer = TokenSerializer(
data={
"type": "tokens",
"email": self.TEST_EMAIL,
"password": self.TEST_PASSWORD,
"tenant_id": tenant_id,
}
)
serializer.is_valid(raise_exception=True)
access_token = serializer.validated_data["access"]
client.defaults["HTTP_AUTHORIZATION"] = f"Bearer {access_token}"
return client
def test_integrations(
self, authenticated_client_rbac_limited, integrations_fixture, providers_fixture
):
# Integration 2 is related to provider1 and provider 2
# This user cannot see provider 2
integration = integrations_fixture[1]
response = authenticated_client_rbac_limited.get(
reverse("integration-detail", kwargs={"pk": integration.id})
)
assert response.status_code == status.HTTP_200_OK
assert integration.providers.count() == 2
assert (
response.json()["data"]["relationships"]["providers"]["meta"]["count"] == 1
)

View File

@@ -6,10 +6,8 @@ from django.db.utils import ConnectionRouter
from api.db_router import MainRouter
from api.rls import Tenant
from config.django.base import DATABASE_ROUTERS as PROD_DATABASE_ROUTERS
from unittest.mock import patch
@patch("api.db_router.MainRouter.admin_db", new="admin")
class TestMainDatabaseRouter:
@pytest.fixture(scope="module")
def router(self):

View File

@@ -2,15 +2,7 @@ from datetime import datetime, timezone
from enum import Enum
from unittest.mock import patch
import pytest
from api.db_utils import (
batch_delete,
enum_to_choices,
generate_random_token,
one_week_from_now,
)
from api.models import Provider
from api.db_utils import enum_to_choices, one_week_from_now, generate_random_token
class TestEnumToChoices:
@@ -114,27 +106,3 @@ class TestGenerateRandomToken:
token = generate_random_token(length=5, symbols="")
# Default symbols
assert len(token) == 5
class TestBatchDelete:
@pytest.fixture
def create_test_providers(self, tenants_fixture):
tenant = tenants_fixture[0]
provider_id = 123456789012
provider_count = 10
for i in range(provider_count):
Provider.objects.create(
tenant=tenant,
uid=f"{provider_id + i}",
provider=Provider.ProviderChoices.AWS,
)
return provider_count
@pytest.mark.django_db
def test_batch_delete(self, tenants_fixture, create_test_providers):
tenant_id = str(tenants_fixture[0].id)
_, summary = batch_delete(
tenant_id, Provider.objects.all(), batch_size=create_test_providers // 2
)
assert Provider.objects.all().count() == 0
assert summary == {"api.Provider": create_test_providers}

View File

@@ -1,9 +1,7 @@
import uuid
from unittest.mock import call, patch
from unittest.mock import patch, call
import pytest
from api.db_utils import POSTGRES_TENANT_VAR, SET_CONFIG_QUERY
from api.decorators import set_tenant
@@ -17,12 +15,12 @@ class TestSetTenantDecorator:
def random_func(arg):
return arg
tenant_id = str(uuid.uuid4())
tenant_id = "1234-abcd-5678"
result = random_func("test_arg", tenant_id=tenant_id)
assert (
call(SET_CONFIG_QUERY, [POSTGRES_TENANT_VAR, tenant_id])
call(f"SELECT set_config('api.tenant_id', '{tenant_id}', TRUE);")
in mock_cursor.execute.mock_calls
)
assert result == "test_arg"

View File

@@ -7,10 +7,9 @@ from api.models import Resource, ResourceTag
class TestResourceModel:
def test_setting_tags(self, providers_fixture):
provider, *_ = providers_fixture
tenant_id = provider.tenant_id
resource = Resource.objects.create(
tenant_id=tenant_id,
tenant_id=provider.tenant_id,
provider=provider,
uid="arn:aws:ec2:us-east-1:123456789012:instance/i-1234567890abcdef0",
name="My Instance 1",
@@ -21,12 +20,12 @@ class TestResourceModel:
tags = [
ResourceTag.objects.create(
tenant_id=tenant_id,
tenant_id=provider.tenant_id,
key="key",
value="value",
),
ResourceTag.objects.create(
tenant_id=tenant_id,
tenant_id=provider.tenant_id,
key="key2",
value="value2",
),
@@ -34,9 +33,9 @@ class TestResourceModel:
resource.upsert_or_delete_tags(tags)
assert len(tags) == len(resource.tags.filter(tenant_id=tenant_id))
assert len(tags) == len(resource.tags.all())
tags_dict = resource.get_tags(tenant_id=tenant_id)
tags_dict = resource.get_tags()
for tag in tags:
assert tag.key in tags_dict
@@ -44,79 +43,47 @@ class TestResourceModel:
def test_adding_tags(self, resources_fixture):
resource, *_ = resources_fixture
tenant_id = str(resource.tenant_id)
tags = [
ResourceTag.objects.create(
tenant_id=tenant_id,
tenant_id=resource.tenant_id,
key="env",
value="test",
),
]
before_count = len(resource.tags.filter(tenant_id=tenant_id))
before_count = len(resource.tags.all())
resource.upsert_or_delete_tags(tags)
assert before_count + 1 == len(resource.tags.filter(tenant_id=tenant_id))
assert before_count + 1 == len(resource.tags.all())
tags_dict = resource.get_tags(tenant_id=tenant_id)
tags_dict = resource.get_tags()
assert "env" in tags_dict
assert tags_dict["env"] == "test"
def test_adding_duplicate_tags(self, resources_fixture):
resource, *_ = resources_fixture
tenant_id = str(resource.tenant_id)
tags = resource.tags.filter(tenant_id=tenant_id)
tags = resource.tags.all()
before_count = len(resource.tags.filter(tenant_id=tenant_id))
before_count = len(resource.tags.all())
resource.upsert_or_delete_tags(tags)
# should be the same number of tags
assert before_count == len(resource.tags.filter(tenant_id=tenant_id))
assert before_count == len(resource.tags.all())
def test_add_tags_none(self, resources_fixture):
resource, *_ = resources_fixture
tenant_id = str(resource.tenant_id)
resource.upsert_or_delete_tags(None)
assert len(resource.tags.filter(tenant_id=tenant_id)) == 0
assert resource.get_tags(tenant_id=tenant_id) == {}
assert len(resource.tags.all()) == 0
assert resource.get_tags() == {}
def test_clear_tags(self, resources_fixture):
resource, *_ = resources_fixture
tenant_id = str(resource.tenant_id)
resource.clear_tags()
assert len(resource.tags.filter(tenant_id=tenant_id)) == 0
assert resource.get_tags(tenant_id=tenant_id) == {}
# @pytest.mark.django_db
# class TestFindingModel:
# def test_add_finding_with_long_uid(
# self, providers_fixture, scans_fixture, resources_fixture
# ):
# provider, *_ = providers_fixture
# tenant_id = provider.tenant_id
# long_uid = "1" * 500
# _ = Finding.objects.create(
# tenant_id=tenant_id,
# uid=long_uid,
# delta=Finding.DeltaChoices.NEW,
# check_metadata={},
# status=StatusChoices.PASS,
# status_extended="",
# severity="high",
# impact="high",
# raw_result={},
# check_id="test_check",
# scan=scans_fixture[0],
# first_seen_at=None,
# muted=False,
# compliance={},
# )
# assert Finding.objects.filter(uid=long_uid).exists()
assert len(resource.tags.all()) == 0
assert resource.get_tags() == {}

View File

@@ -1,24 +1,25 @@
from datetime import datetime, timedelta, timezone
from unittest.mock import MagicMock, patch
from unittest.mock import patch, MagicMock
import pytest
from rest_framework.exceptions import NotFound, ValidationError
from api.db_router import MainRouter
from api.exceptions import InvitationTokenExpiredException
from api.models import Invitation, Provider
from api.utils import (
get_prowler_provider_kwargs,
initialize_prowler_provider,
merge_dicts,
prowler_provider_connection_test,
return_prowler_provider,
validate_invitation,
)
from prowler.providers.aws.aws_provider import AwsProvider
from prowler.providers.azure.azure_provider import AzureProvider
from prowler.providers.gcp.gcp_provider import GcpProvider
from prowler.providers.kubernetes.kubernetes_provider import KubernetesProvider
from rest_framework.exceptions import ValidationError, NotFound
from api.db_router import MainRouter
from api.exceptions import InvitationTokenExpiredException
from api.models import Invitation
from api.models import Provider
from api.utils import (
merge_dicts,
return_prowler_provider,
initialize_prowler_provider,
prowler_provider_connection_test,
get_prowler_provider_kwargs,
)
from api.utils import validate_invitation
class TestMergeDicts:
@@ -143,18 +144,6 @@ class TestProwlerProviderConnectionTest:
key="value", provider_id="1234567890", raise_on_exception=False
)
@pytest.mark.django_db
@patch("api.utils.return_prowler_provider")
def test_prowler_provider_connection_test_without_secret(
self, mock_return_prowler_provider, providers_fixture
):
mock_return_prowler_provider.return_value = MagicMock()
connection = prowler_provider_connection_test(providers_fixture[0])
assert connection.is_connected is False
assert isinstance(connection.error, Provider.secret.RelatedObjectDoesNotExist)
assert str(connection.error) == "Provider has no secret."
class TestGetProwlerProviderKwargs:
@pytest.mark.parametrize(
@@ -285,10 +274,9 @@ class TestValidateInvitation:
expired_time = datetime.now(timezone.utc) - timedelta(days=1)
invitation.expires_at = expired_time
with (
patch("api.utils.Invitation.objects.using") as mock_using,
patch("api.utils.datetime") as mock_datetime,
):
with patch("api.utils.Invitation.objects.using") as mock_using, patch(
"api.utils.datetime"
) as mock_datetime:
mock_db = mock_using.return_value
mock_db.get.return_value = invitation
mock_datetime.now.return_value = datetime.now(timezone.utc)

File diff suppressed because it is too large Load Diff

View File

@@ -1,25 +1,15 @@
from datetime import datetime, timezone
from allauth.socialaccount.providers.oauth2.client import OAuth2Client
from rest_framework.exceptions import NotFound, ValidationError
from api.db_router import MainRouter
from api.exceptions import InvitationTokenExpiredException
from api.models import Invitation, Provider
from prowler.providers.aws.aws_provider import AwsProvider
from prowler.providers.azure.azure_provider import AzureProvider
from prowler.providers.common.models import Connection
from prowler.providers.gcp.gcp_provider import GcpProvider
from prowler.providers.kubernetes.kubernetes_provider import KubernetesProvider
from rest_framework.exceptions import ValidationError, NotFound
class CustomOAuth2Client(OAuth2Client):
def __init__(self, client_id, secret, *args, **kwargs):
# Remove any duplicate "scope_delimiter" from kwargs
# Bug present in dj-rest-auth after version v7.0.1
# https://github.com/iMerica/dj-rest-auth/issues/673
kwargs.pop("scope_delimiter", None)
super().__init__(client_id, secret, *args, **kwargs)
from api.db_router import MainRouter
from api.exceptions import InvitationTokenExpiredException
from api.models import Provider, Invitation
def merge_dicts(default_dict: dict, replacement_dict: dict) -> dict:
@@ -130,10 +120,7 @@ def prowler_provider_connection_test(provider: Provider) -> Connection:
Connection: A connection object representing the result of the connection test for the specified provider.
"""
prowler_provider = return_prowler_provider(provider)
try:
prowler_provider_kwargs = provider.secret.secret
except Provider.secret.RelatedObjectDoesNotExist as secret_error:
return Connection(is_connected=False, error=secret_error)
prowler_provider_kwargs = provider.secret.secret
return prowler_provider.test_connection(
**prowler_provider_kwargs, provider_id=provider.uid, raise_on_exception=False
)

View File

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

View File

@@ -1,122 +0,0 @@
from drf_spectacular.utils import extend_schema_field
from rest_framework_json_api import serializers
from rest_framework_json_api.serializers import ValidationError
class BaseValidateSerializer(serializers.Serializer):
def validate(self, data):
if hasattr(self, "initial_data"):
initial_data = set(self.initial_data.keys()) - {"id", "type"}
unknown_keys = initial_data - set(self.fields.keys())
if unknown_keys:
raise ValidationError(f"Invalid fields: {unknown_keys}")
return data
# Integrations
class S3ConfigSerializer(BaseValidateSerializer):
bucket_name = serializers.CharField()
output_directory = serializers.CharField()
class Meta:
resource_name = "integrations"
class AWSCredentialSerializer(BaseValidateSerializer):
role_arn = serializers.CharField(required=False)
external_id = serializers.CharField(required=False)
role_session_name = serializers.CharField(required=False)
session_duration = serializers.IntegerField(
required=False, min_value=900, max_value=43200
)
aws_access_key_id = serializers.CharField(required=False)
aws_secret_access_key = serializers.CharField(required=False)
aws_session_token = serializers.CharField(required=False)
class Meta:
resource_name = "integrations"
@extend_schema_field(
{
"oneOf": [
{
"type": "object",
"title": "AWS Credentials",
"properties": {
"role_arn": {
"type": "string",
"description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
"assumption.",
},
"external_id": {
"type": "string",
"description": "An identifier to enhance security for role assumption.",
},
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Only required if the environment lacks pre-configured "
"AWS credentials.",
},
"aws_secret_access_key": {
"type": "string",
"description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
"no AWS credentials are pre-configured.",
},
"aws_session_token": {
"type": "string",
"description": "The session token for temporary credentials, if applicable.",
},
"session_duration": {
"type": "integer",
"minimum": 900,
"maximum": 43200,
"default": 3600,
"description": "The duration (in seconds) for the role session.",
},
"role_session_name": {
"type": "string",
"description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
"The regex used to validate this parameter is a string of characters consisting of "
"upper- and lower-case alphanumeric characters with no spaces. You can also include "
"underscores or any of the following characters: =,.@-\n\n"
"Examples:\n"
"- MySession123\n"
"- User_Session-1\n"
"- Test.Session@2",
"pattern": "^[a-zA-Z0-9=,.@_-]+$",
},
},
},
]
}
)
class IntegrationCredentialField(serializers.JSONField):
pass
@extend_schema_field(
{
"oneOf": [
{
"type": "object",
"title": "Amazon S3",
"properties": {
"bucket_name": {
"type": "string",
"description": "The name of the S3 bucket where files will be stored.",
},
"output_directory": {
"type": "string",
"description": "The directory path within the bucket where files will be saved.",
},
},
"required": ["bucket_name", "output_directory"],
},
]
}
)
class IntegrationConfigField(serializers.JSONField):
pass

View File

@@ -14,97 +14,31 @@ from rest_framework_simplejwt.serializers import TokenObtainPairSerializer
from rest_framework_simplejwt.tokens import RefreshToken
from api.models import (
ComplianceOverview,
Finding,
Integration,
IntegrationProviderRelationship,
Invitation,
InvitationRoleRelationship,
Membership,
Provider,
ProviderGroup,
ProviderGroupMembership,
ProviderSecret,
Resource,
ResourceTag,
Finding,
ProviderSecret,
Invitation,
InvitationRoleRelationship,
Role,
RoleProviderGroupRelationship,
UserRoleRelationship,
ComplianceOverview,
Scan,
StateChoices,
Task,
User,
UserRoleRelationship,
)
from api.rls import Tenant
from api.v1.serializer_utils.integrations import (
AWSCredentialSerializer,
IntegrationConfigField,
IntegrationCredentialField,
S3ConfigSerializer,
)
# Tokens
def generate_tokens(user: User, tenant_id: str) -> dict:
try:
refresh = RefreshToken.for_user(user)
except InvalidKeyError:
# Handle invalid key error
raise ValidationError(
{
"detail": "Token generation failed due to invalid key configuration. Provide valid "
"DJANGO_TOKEN_SIGNING_KEY and DJANGO_TOKEN_VERIFYING_KEY in the environment."
}
)
except Exception as e:
raise ValidationError({"detail": str(e)})
# Post-process the tokens
# Set the tenant_id
refresh["tenant_id"] = tenant_id
# Set the nbf (not before) claim to the iat (issued at) claim. At this moment, simplejwt does not provide a
# way to set the nbf claim
refresh.payload["nbf"] = refresh["iat"]
# Get the access token
access = refresh.access_token
if settings.SIMPLE_JWT["UPDATE_LAST_LOGIN"]:
update_last_login(None, user)
return {"access": str(access), "refresh": str(refresh)}
class BaseTokenSerializer(TokenObtainPairSerializer):
def custom_validate(self, attrs, social: bool = False):
email = attrs.get("email")
password = attrs.get("password")
tenant_id = str(attrs.get("tenant_id", ""))
# Authenticate user
user = (
User.objects.get(email=email)
if social
else authenticate(username=email, password=password)
)
if user is None:
raise ValidationError("Invalid credentials")
if tenant_id:
if not user.is_member_of_tenant(tenant_id):
raise ValidationError("Tenant does not exist or user is not a member.")
else:
first_membership = user.memberships.order_by("date_joined").first()
if first_membership is None:
raise ValidationError("User has no memberships.")
tenant_id = str(first_membership.tenant_id)
return generate_tokens(user, tenant_id)
class TokenSerializer(BaseTokenSerializer):
class TokenSerializer(TokenObtainPairSerializer):
email = serializers.EmailField(write_only=True)
password = serializers.CharField(write_only=True)
tenant_id = serializers.UUIDField(
@@ -122,25 +56,53 @@ class TokenSerializer(BaseTokenSerializer):
resource_name = "tokens"
def validate(self, attrs):
return super().custom_validate(attrs)
email = attrs.get("email")
password = attrs.get("password")
tenant_id = str(attrs.get("tenant_id", ""))
# Authenticate user
user = authenticate(username=email, password=password)
if user is None:
raise ValidationError("Invalid credentials")
class TokenSocialLoginSerializer(BaseTokenSerializer):
email = serializers.EmailField(write_only=True)
if tenant_id:
if not user.is_member_of_tenant(tenant_id):
raise ValidationError("Tenant does not exist or user is not a member.")
else:
first_membership = user.memberships.order_by("date_joined").first()
if first_membership is None:
raise ValidationError("User has no memberships.")
tenant_id = str(first_membership.tenant_id)
# Output tokens
refresh = serializers.CharField(read_only=True)
access = serializers.CharField(read_only=True)
# Generate tokens
try:
refresh = RefreshToken.for_user(user)
except InvalidKeyError:
# Handle invalid key error
raise ValidationError(
{
"detail": "Token generation failed due to invalid key configuration. Provide valid "
"DJANGO_TOKEN_SIGNING_KEY and DJANGO_TOKEN_VERIFYING_KEY in the environment."
}
)
except Exception as e:
raise ValidationError({"detail": str(e)})
class JSONAPIMeta:
resource_name = "tokens"
# Post-process the tokens
# Set the tenant_id
refresh["tenant_id"] = tenant_id
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.fields.pop("password", None)
# Set the nbf (not before) claim to the iat (issued at) claim. At this moment, simplejwt does not provide a
# way to set the nbf claim
refresh.payload["nbf"] = refresh["iat"]
def validate(self, attrs):
return super().custom_validate(attrs, social=True)
# Get the access token
access = refresh.access_token
if settings.SIMPLE_JWT["UPDATE_LAST_LOGIN"]:
update_last_login(None, user)
return {"access": str(access), "refresh": str(refresh)}
# TODO: Check if we can change the parent class to TokenRefreshSerializer from rest_framework_simplejwt.serializers
@@ -178,30 +140,6 @@ class TokenRefreshSerializer(serializers.Serializer):
raise ValidationError({"refresh": "Invalid or expired token"})
class TokenSwitchTenantSerializer(serializers.Serializer):
tenant_id = serializers.UUIDField(
write_only=True, help_text="The tenant ID for which to request a new token."
)
access = serializers.CharField(read_only=True)
refresh = serializers.CharField(read_only=True)
class JSONAPIMeta:
resource_name = "tokens-switch-tenant"
def validate(self, attrs):
request = self.context["request"]
user = request.user
if not user.is_authenticated:
raise ValidationError("Invalid or expired token.")
tenant_id = str(attrs.get("tenant_id"))
if not user.is_member_of_tenant(tenant_id):
raise ValidationError("Tenant does not exist or user is not a member.")
return generate_tokens(user, tenant_id)
# Base
@@ -507,12 +445,7 @@ class MembershipSerializer(serializers.ModelSerializer):
# Provider Groups
class ProviderGroupSerializer(RLSSerializer, BaseWriteSerializer):
providers = serializers.ResourceRelatedField(
queryset=Provider.objects.all(), many=True, required=False
)
roles = serializers.ResourceRelatedField(
queryset=Role.objects.all(), many=True, required=False
)
providers = serializers.ResourceRelatedField(many=True, read_only=True)
def validate(self, attrs):
if ProviderGroup.objects.filter(name=attrs.get("name")).exists():
@@ -542,93 +475,21 @@ class ProviderGroupSerializer(RLSSerializer, BaseWriteSerializer):
}
class ProviderGroupIncludedSerializer(ProviderGroupSerializer):
class ProviderGroupIncludedSerializer(RLSSerializer, BaseWriteSerializer):
class Meta:
model = ProviderGroup
fields = ["id", "name"]
class ProviderGroupCreateSerializer(ProviderGroupSerializer):
providers = serializers.ResourceRelatedField(
queryset=Provider.objects.all(), many=True, required=False
)
roles = serializers.ResourceRelatedField(
queryset=Role.objects.all(), many=True, required=False
)
class ProviderGroupUpdateSerializer(RLSSerializer, BaseWriteSerializer):
"""
Serializer for updating the ProviderGroup model.
Only allows "name" field to be updated.
"""
class Meta:
model = ProviderGroup
fields = [
"id",
"name",
"inserted_at",
"updated_at",
"providers",
"roles",
]
def create(self, validated_data):
providers = validated_data.pop("providers", [])
roles = validated_data.pop("roles", [])
tenant_id = self.context.get("tenant_id")
provider_group = ProviderGroup.objects.create(
tenant_id=tenant_id, **validated_data
)
through_model_instances = [
ProviderGroupMembership(
provider_group=provider_group,
provider=provider,
tenant_id=tenant_id,
)
for provider in providers
]
ProviderGroupMembership.objects.bulk_create(through_model_instances)
through_model_instances = [
RoleProviderGroupRelationship(
provider_group=provider_group,
role=role,
tenant_id=tenant_id,
)
for role in roles
]
RoleProviderGroupRelationship.objects.bulk_create(through_model_instances)
return provider_group
class ProviderGroupUpdateSerializer(ProviderGroupSerializer):
def update(self, instance, validated_data):
tenant_id = self.context.get("tenant_id")
if "providers" in validated_data:
providers = validated_data.pop("providers")
instance.providers.clear()
through_model_instances = [
ProviderGroupMembership(
provider_group=instance,
provider=provider,
tenant_id=tenant_id,
)
for provider in providers
]
ProviderGroupMembership.objects.bulk_create(through_model_instances)
if "roles" in validated_data:
roles = validated_data.pop("roles")
instance.roles.clear()
through_model_instances = [
RoleProviderGroupRelationship(
provider_group=instance,
role=role,
tenant_id=tenant_id,
)
for role in roles
]
RoleProviderGroupRelationship.objects.bulk_create(through_model_instances)
return super().update(instance, validated_data)
fields = ["id", "name"]
class ProviderResourceIdentifierSerializer(serializers.Serializer):
@@ -753,43 +614,6 @@ class ProviderSerializer(RLSSerializer):
}
class ProviderIncludeSerializer(RLSSerializer):
"""
Serializer for the Provider model.
"""
provider = ProviderEnumSerializerField()
connection = serializers.SerializerMethodField(read_only=True)
class Meta:
model = Provider
fields = [
"id",
"inserted_at",
"updated_at",
"provider",
"uid",
"alias",
"connection",
# "scanner_args",
]
@extend_schema_field(
{
"type": "object",
"properties": {
"connected": {"type": "boolean"},
"last_checked_at": {"type": "string", "format": "date-time"},
},
}
)
def get_connection(self, obj):
return {
"connected": obj.connected,
"last_checked_at": obj.connection_last_checked_at,
}
class ProviderCreateSerializer(RLSSerializer, BaseWriteSerializer):
class Meta:
model = Provider
@@ -851,39 +675,6 @@ class ScanSerializer(RLSSerializer):
"url",
]
included_serializers = {
"provider": "api.v1.serializers.ProviderIncludeSerializer",
}
class ScanIncludeSerializer(RLSSerializer):
trigger = serializers.ChoiceField(
choices=Scan.TriggerChoices.choices, read_only=True
)
state = StateEnumSerializerField(read_only=True)
class Meta:
model = Scan
fields = [
"id",
"name",
"trigger",
"state",
"unique_resource_count",
"progress",
# "scanner_args",
"duration",
"inserted_at",
"started_at",
"completed_at",
"scheduled_at",
"provider",
]
included_serializers = {
"provider": "api.v1.serializers.ProviderIncludeSerializer",
}
class ScanCreateSerializer(RLSSerializer, BaseWriteSerializer):
class Meta:
@@ -951,14 +742,6 @@ class ScanTaskSerializer(RLSSerializer):
]
class ScanReportSerializer(serializers.Serializer):
id = serializers.CharField(source="scan")
class Meta:
resource_name = "scan-reports"
fields = ["id"]
class ResourceTagSerializer(RLSSerializer):
"""
Serializer for the ResourceTag model
@@ -1014,52 +797,7 @@ class ResourceSerializer(RLSSerializer):
}
)
def get_tags(self, obj):
return obj.get_tags(self.context.get("tenant_id"))
def get_fields(self):
"""`type` is a Python reserved keyword."""
fields = super().get_fields()
type_ = fields.pop("type_")
fields["type"] = type_
return fields
class ResourceIncludeSerializer(RLSSerializer):
"""
Serializer for the Resource model.
"""
tags = serializers.SerializerMethodField()
type_ = serializers.CharField(read_only=True)
class Meta:
model = Resource
fields = [
"id",
"inserted_at",
"updated_at",
"uid",
"name",
"region",
"service",
"type_",
"tags",
]
extra_kwargs = {
"id": {"read_only": True},
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
}
@extend_schema_field(
{
"type": "object",
"description": "Tags associated with the resource",
"example": {"env": "prod", "owner": "johndoe"},
}
)
def get_tags(self, obj):
return obj.get_tags(self.context.get("tenant_id"))
return obj.get_tags()
def get_fields(self):
"""`type` is a Python reserved keyword."""
@@ -1090,8 +828,6 @@ class FindingSerializer(RLSSerializer):
"raw_result",
"inserted_at",
"updated_at",
"first_seen_at",
"muted",
"url",
# Relationships
"scan",
@@ -1099,12 +835,11 @@ class FindingSerializer(RLSSerializer):
]
included_serializers = {
"scan": ScanIncludeSerializer,
"resources": ResourceIncludeSerializer,
"scan": ScanSerializer,
"resources": ResourceSerializer,
}
# To be removed when the related endpoint is removed as well
class FindingDynamicFilterSerializer(serializers.Serializer):
services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
@@ -1113,19 +848,6 @@ class FindingDynamicFilterSerializer(serializers.Serializer):
resource_name = "finding-dynamic-filters"
class FindingMetadataSerializer(serializers.Serializer):
services = serializers.ListField(child=serializers.CharField(), allow_empty=True)
regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
resource_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 = "findings-metadata"
# Provider secrets
class BaseWriteProviderSecretSerializer(BaseWriteSerializer):
@staticmethod
@@ -1198,7 +920,7 @@ class KubernetesProviderSecret(serializers.Serializer):
class AWSRoleAssumptionProviderSecret(serializers.Serializer):
role_arn = serializers.CharField()
external_id = serializers.CharField()
external_id = serializers.CharField(required=False)
role_session_name = serializers.CharField(required=False)
session_duration = serializers.IntegerField(
required=False, min_value=900, max_value=43200
@@ -1245,10 +967,6 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
"description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
"assumption.",
},
"external_id": {
"type": "string",
"description": "An identifier to enhance security for role assumption.",
},
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Only required if the environment lacks pre-configured "
@@ -1270,6 +988,11 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
"default": 3600,
"description": "The duration (in seconds) for the role session.",
},
"external_id": {
"type": "string",
"description": "An optional identifier to enhance security for role assumption; may be "
"required by the role administrator.",
},
"role_session_name": {
"type": "string",
"description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
@@ -1283,7 +1006,7 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
"pattern": "^[a-zA-Z0-9=,.@_-]+$",
},
},
"required": ["role_arn", "external_id"],
"required": ["role_arn"],
},
{
"type": "object",
@@ -1433,12 +1156,6 @@ class InvitationSerializer(RLSSerializer):
roles = serializers.ResourceRelatedField(many=True, queryset=Role.objects.all())
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
tenant_id = self.context.get("tenant_id")
if tenant_id is not None:
self.fields["roles"].queryset = Role.objects.filter(tenant_id=tenant_id)
class Meta:
model = Invitation
fields = [
@@ -1458,12 +1175,6 @@ class InvitationSerializer(RLSSerializer):
class InvitationBaseWriteSerializer(BaseWriteSerializer):
roles = serializers.ResourceRelatedField(many=True, queryset=Role.objects.all())
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
tenant_id = self.context.get("tenant_id")
if tenant_id is not None:
self.fields["roles"].queryset = Role.objects.filter(tenant_id=tenant_id)
def validate_email(self, value):
user = User.objects.filter(email=value).first()
tenant_id = self.context["tenant_id"]
@@ -1524,10 +1235,6 @@ class InvitationCreateSerializer(InvitationBaseWriteSerializer, RLSSerializer):
class InvitationUpdateSerializer(InvitationBaseWriteSerializer):
roles = serializers.ResourceRelatedField(
required=False, many=True, queryset=Role.objects.all()
)
class Meta:
model = Invitation
fields = ["id", "email", "expires_at", "state", "token", "roles"]
@@ -1540,19 +1247,15 @@ class InvitationUpdateSerializer(InvitationBaseWriteSerializer):
}
def update(self, instance, validated_data):
roles = validated_data.pop("roles", [])
tenant_id = self.context.get("tenant_id")
if "roles" in validated_data:
roles = validated_data.pop("roles")
instance.roles.clear()
new_relationships = [
InvitationRoleRelationship(
role=r, invitation=instance, tenant_id=tenant_id
)
for r in roles
]
InvitationRoleRelationship.objects.bulk_create(new_relationships)
invitation = super().update(instance, validated_data)
if roles:
instance.roles.clear()
for role in roles:
InvitationRoleRelationship.objects.create(
role=role, invitation=invitation, tenant_id=tenant_id
)
return invitation
@@ -1571,27 +1274,30 @@ class InvitationAcceptSerializer(RLSSerializer):
class RoleSerializer(RLSSerializer, BaseWriteSerializer):
permission_state = serializers.SerializerMethodField()
users = serializers.ResourceRelatedField(
queryset=User.objects.all(), many=True, required=False
)
provider_groups = serializers.ResourceRelatedField(
queryset=ProviderGroup.objects.all(), many=True, required=False
many=True, queryset=ProviderGroup.objects.all()
)
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
tenant_id = self.context.get("tenant_id")
if tenant_id is not None:
self.fields["users"].queryset = User.objects.filter(
membership__tenant__id=tenant_id
)
self.fields["provider_groups"].queryset = ProviderGroup.objects.filter(
tenant_id=self.context.get("tenant_id")
)
permission_state = serializers.SerializerMethodField()
def get_permission_state(self, obj) -> str:
return obj.permission_state
def get_permission_state(self, obj):
permission_fields = [
"manage_users",
"manage_account",
"manage_billing",
"manage_providers",
"manage_integrations",
"manage_scans",
]
values = [getattr(obj, field) for field in permission_fields]
if all(values):
return "unlimited"
elif not any(values):
return "none"
else:
return "limited"
def validate(self, attrs):
if Role.objects.filter(name=attrs.get("name")).exists():
@@ -1617,11 +1323,9 @@ class RoleSerializer(RLSSerializer, BaseWriteSerializer):
"name",
"manage_users",
"manage_account",
# Disable for the first release
# "manage_billing",
# /Disable for the first release
"manage_integrations",
"manage_billing",
"manage_providers",
"manage_integrations",
"manage_scans",
"permission_state",
"unlimited_visibility",
@@ -1636,18 +1340,12 @@ class RoleSerializer(RLSSerializer, BaseWriteSerializer):
"id": {"read_only": True},
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
"users": {"read_only": True},
"url": {"read_only": True},
}
class RoleCreateSerializer(RoleSerializer):
provider_groups = serializers.ResourceRelatedField(
many=True, queryset=ProviderGroup.objects.all(), required=False
)
users = serializers.ResourceRelatedField(
many=True, queryset=User.objects.all(), required=False
)
def create(self, validated_data):
provider_groups = validated_data.pop("provider_groups", [])
users = validated_data.pop("users", [])
@@ -1666,7 +1364,7 @@ class RoleCreateSerializer(RoleSerializer):
through_model_instances = [
UserRoleRelationship(
role=role,
role=user,
user=user,
tenant_id=tenant_id,
)
@@ -1678,36 +1376,19 @@ class RoleCreateSerializer(RoleSerializer):
class RoleUpdateSerializer(RoleSerializer):
def update(self, instance, validated_data):
tenant_id = self.context.get("tenant_id")
if "provider_groups" in validated_data:
provider_groups = validated_data.pop("provider_groups")
instance.provider_groups.clear()
through_model_instances = [
RoleProviderGroupRelationship(
role=instance,
provider_group=provider_group,
tenant_id=tenant_id,
)
for provider_group in provider_groups
]
RoleProviderGroupRelationship.objects.bulk_create(through_model_instances)
if "users" in validated_data:
users = validated_data.pop("users")
instance.users.clear()
through_model_instances = [
UserRoleRelationship(
role=instance,
user=user,
tenant_id=tenant_id,
)
for user in users
]
UserRoleRelationship.objects.bulk_create(through_model_instances)
return super().update(instance, validated_data)
class Meta:
model = Role
fields = [
"id",
"name",
"manage_users",
"manage_account",
"manage_billing",
"manage_providers",
"manage_integrations",
"manage_scans",
"unlimited_visibility",
]
class ProviderGroupResourceIdentifierSerializer(serializers.Serializer):
@@ -1902,13 +1583,6 @@ class ComplianceOverviewFullSerializer(ComplianceOverviewSerializer):
return obj.requirements
class ComplianceOverviewMetadataSerializer(serializers.Serializer):
regions = serializers.ListField(child=serializers.CharField(), allow_empty=True)
class Meta:
resource_name = "compliance-overviews-metadata"
# Overviews
@@ -1929,7 +1603,7 @@ class OverviewProviderSerializer(serializers.Serializer):
"properties": {
"pass": {"type": "integer"},
"fail": {"type": "integer"},
"muted": {"type": "integer"},
"manual": {"type": "integer"},
"total": {"type": "integer"},
},
}
@@ -1938,7 +1612,7 @@ class OverviewProviderSerializer(serializers.Serializer):
return {
"pass": obj["findings_passed"],
"fail": obj["findings_failed"],
"muted": obj["findings_muted"],
"manual": obj["findings_manual"],
"total": obj["total_findings"],
}
@@ -1998,24 +1672,6 @@ class OverviewSeveritySerializer(serializers.Serializer):
return {"version": "v1"}
class OverviewServiceSerializer(serializers.Serializer):
id = serializers.CharField(source="service")
total = serializers.IntegerField()
_pass = serializers.IntegerField()
fail = serializers.IntegerField()
muted = serializers.IntegerField()
class JSONAPIMeta:
resource_name = "services-overview"
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.fields["pass"] = self.fields.pop("_pass")
def get_root_meta(self, _resource, _many):
return {"version": "v1"}
# Schedules
@@ -2033,201 +1689,3 @@ class ScheduleDailyCreateSerializer(serializers.Serializer):
if unknown_keys:
raise ValidationError(f"Invalid fields: {unknown_keys}")
return data
# Integrations
class BaseWriteIntegrationSerializer(BaseWriteSerializer):
@staticmethod
def validate_integration_data(
integration_type: str,
providers: list[Provider], # noqa
configuration: dict,
credentials: dict,
):
if integration_type == Integration.IntegrationChoices.S3:
config_serializer = S3ConfigSerializer
credentials_serializers = [AWSCredentialSerializer]
# TODO: This will be required for AWS Security Hub
# if providers and not all(
# provider.provider == Provider.ProviderChoices.AWS
# for provider in providers
# ):
# raise serializers.ValidationError(
# {"providers": "All providers must be AWS for the S3 integration."}
# )
else:
raise serializers.ValidationError(
{
"integration_type": f"Integration type not supported yet: {integration_type}"
}
)
config_serializer(data=configuration).is_valid(raise_exception=True)
for cred_serializer in credentials_serializers:
try:
cred_serializer(data=credentials).is_valid(raise_exception=True)
break
except ValidationError:
continue
else:
raise ValidationError(
{"credentials": "Invalid credentials for the integration type."}
)
class IntegrationSerializer(RLSSerializer):
"""
Serializer for the Integration model.
"""
providers = serializers.ResourceRelatedField(
queryset=Provider.objects.all(), many=True
)
class Meta:
model = Integration
fields = [
"id",
"inserted_at",
"updated_at",
"enabled",
"connected",
"connection_last_checked_at",
"integration_type",
"configuration",
"providers",
"url",
]
included_serializers = {
"providers": "api.v1.serializers.ProviderIncludeSerializer",
}
def to_representation(self, instance):
representation = super().to_representation(instance)
allowed_providers = self.context.get("allowed_providers")
if allowed_providers:
allowed_provider_ids = {str(provider.id) for provider in allowed_providers}
representation["providers"] = [
provider
for provider in representation["providers"]
if provider["id"] in allowed_provider_ids
]
return representation
class IntegrationCreateSerializer(BaseWriteIntegrationSerializer):
credentials = IntegrationCredentialField(write_only=True)
configuration = IntegrationConfigField()
providers = serializers.ResourceRelatedField(
queryset=Provider.objects.all(), many=True, required=False
)
class Meta:
model = Integration
fields = [
"inserted_at",
"updated_at",
"enabled",
"connected",
"connection_last_checked_at",
"integration_type",
"configuration",
"credentials",
"providers",
]
extra_kwargs = {
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
"connected": {"read_only": True},
"enabled": {"read_only": True},
"connection_last_checked_at": {"read_only": True},
}
def validate(self, attrs):
integration_type = attrs.get("integration_type")
providers = attrs.get("providers")
configuration = attrs.get("configuration")
credentials = attrs.get("credentials")
validated_attrs = super().validate(attrs)
self.validate_integration_data(
integration_type, providers, configuration, credentials
)
return validated_attrs
def create(self, validated_data):
tenant_id = self.context.get("tenant_id")
providers = validated_data.pop("providers", [])
integration = Integration.objects.create(tenant_id=tenant_id, **validated_data)
through_model_instances = [
IntegrationProviderRelationship(
integration=integration,
provider=provider,
tenant_id=tenant_id,
)
for provider in providers
]
IntegrationProviderRelationship.objects.bulk_create(through_model_instances)
return integration
class IntegrationUpdateSerializer(BaseWriteIntegrationSerializer):
credentials = IntegrationCredentialField(write_only=True, required=False)
configuration = IntegrationConfigField(required=False)
providers = serializers.ResourceRelatedField(
queryset=Provider.objects.all(), many=True, required=False
)
class Meta:
model = Integration
fields = [
"inserted_at",
"updated_at",
"enabled",
"connected",
"connection_last_checked_at",
"integration_type",
"configuration",
"credentials",
"providers",
]
extra_kwargs = {
"inserted_at": {"read_only": True},
"updated_at": {"read_only": True},
"connected": {"read_only": True},
"connection_last_checked_at": {"read_only": True},
"integration_type": {"read_only": True},
}
def validate(self, attrs):
integration_type = self.instance.integration_type
providers = attrs.get("providers")
configuration = attrs.get("configuration") or self.instance.configuration
credentials = attrs.get("credentials") or self.instance.credentials
validated_attrs = super().validate(attrs)
self.validate_integration_data(
integration_type, providers, configuration, credentials
)
return validated_attrs
def update(self, instance, validated_data):
tenant_id = self.context.get("tenant_id")
if validated_data.get("providers") is not None:
instance.providers.clear()
new_relationships = [
IntegrationProviderRelationship(
integration=instance, provider=provider, tenant_id=tenant_id
)
for provider in validated_data["providers"]
]
IntegrationProviderRelationship.objects.bulk_create(new_relationships)
return super().update(instance, validated_data)

View File

@@ -3,32 +3,28 @@ from drf_spectacular.views import SpectacularRedocView
from rest_framework_nested import routers
from api.v1.views import (
ComplianceOverviewViewSet,
CustomTokenObtainView,
CustomTokenRefreshView,
CustomTokenSwitchTenantView,
FindingViewSet,
GithubSocialLoginView,
GoogleSocialLoginView,
IntegrationViewSet,
InvitationAcceptViewSet,
InvitationViewSet,
MembershipViewSet,
OverviewViewSet,
ProviderGroupProvidersRelationshipView,
ProviderGroupViewSet,
ProviderGroupProvidersRelationshipView,
ProviderSecretViewSet,
InvitationViewSet,
InvitationAcceptViewSet,
RoleViewSet,
RoleProviderGroupRelationshipView,
UserRoleRelationshipView,
OverviewViewSet,
ComplianceOverviewViewSet,
ProviderViewSet,
ResourceViewSet,
RoleProviderGroupRelationshipView,
RoleViewSet,
ScanViewSet,
ScheduleViewSet,
SchemaView,
TaskViewSet,
TenantMembersViewSet,
TenantViewSet,
UserRoleRelationshipView,
UserViewSet,
)
@@ -48,7 +44,6 @@ router.register(
)
router.register(r"overviews", OverviewViewSet, basename="overview")
router.register(r"schedules", ScheduleViewSet, basename="schedule")
router.register(r"integrations", IntegrationViewSet, basename="integration")
tenants_router = routers.NestedSimpleRouter(router, r"tenants", lookup="tenant")
tenants_router.register(
@@ -61,7 +56,6 @@ users_router.register(r"memberships", MembershipViewSet, basename="user-membersh
urlpatterns = [
path("tokens", CustomTokenObtainView.as_view(), name="token-obtain"),
path("tokens/refresh", CustomTokenRefreshView.as_view(), name="token-refresh"),
path("tokens/switch", CustomTokenSwitchTenantView.as_view(), name="token-switch"),
path(
"providers/secrets",
ProviderSecretViewSet.as_view({"get": "list", "post": "create"}),
@@ -112,8 +106,6 @@ urlpatterns = [
),
name="provider_group-providers-relationship",
),
path("tokens/google", GoogleSocialLoginView.as_view(), name="token-google"),
path("tokens/github", GithubSocialLoginView.as_view(), name="token-github"),
path("", include(router.urls)),
path("", include(tenants_router.urls)),
path("", include(users_router.urls)),

File diff suppressed because it is too large Load Diff

View File

@@ -1,21 +1,10 @@
from celery import Celery, Task
from config.env import env
BROKER_VISIBILITY_TIMEOUT = env.int("DJANGO_BROKER_VISIBILITY_TIMEOUT", default=86400)
celery_app = Celery("tasks")
celery_app.config_from_object("django.conf:settings", namespace="CELERY")
celery_app.conf.update(result_extended=True, result_expires=None)
celery_app.conf.broker_transport_options = {
"visibility_timeout": BROKER_VISIBILITY_TIMEOUT
}
celery_app.conf.result_backend_transport_options = {
"visibility_timeout": BROKER_VISIBILITY_TIMEOUT
}
celery_app.conf.visibility_timeout = BROKER_VISIBILITY_TIMEOUT
celery_app.autodiscover_tasks(["api"])
@@ -46,13 +35,13 @@ class RLSTask(Task):
**options,
)
task_result_instance = TaskResult.objects.get(task_id=result.task_id)
from api.db_utils import rls_transaction
from api.db_utils import tenant_transaction
tenant_id = kwargs.get("tenant_id")
with rls_transaction(tenant_id):
APITask.objects.update_or_create(
with tenant_transaction(tenant_id):
APITask.objects.create(
id=task_result_instance.task_id,
tenant_id=tenant_id,
defaults={"task_runner_task": task_result_instance},
task_runner_task=task_result_instance,
)
return result

View File

@@ -2,9 +2,10 @@ import json
import logging
from enum import StrEnum
from config.env import env
from django_guid.log_filters import CorrelationId
from config.env import env
class BackendLogger(StrEnum):
GUNICORN = "gunicorn"
@@ -38,9 +39,9 @@ class NDJSONFormatter(logging.Formatter):
"funcName": record.funcName,
"process": record.process,
"thread": record.thread,
"transaction_id": (
record.transaction_id if hasattr(record, "transaction_id") else None
),
"transaction_id": record.transaction_id
if hasattr(record, "transaction_id")
else None,
}
# Add REST API extra fields

View File

@@ -4,8 +4,6 @@ from config.custom_logging import LOGGING # noqa
from config.env import BASE_DIR, env # noqa
from config.settings.celery import * # noqa
from config.settings.partitions import * # noqa
from config.settings.sentry import * # noqa
from config.settings.social_login import * # noqa
SECRET_KEY = env("SECRET_KEY", default="secret")
DEBUG = env.bool("DJANGO_DEBUG", default=False)
@@ -31,13 +29,6 @@ INSTALLED_APPS = [
"django_celery_results",
"django_celery_beat",
"rest_framework_simplejwt.token_blacklist",
"allauth",
"allauth.account",
"allauth.socialaccount",
"allauth.socialaccount.providers.google",
"allauth.socialaccount.providers.github",
"dj_rest_auth.registration",
"rest_framework.authtoken",
]
MIDDLEWARE = [
@@ -51,11 +42,8 @@ MIDDLEWARE = [
"django.contrib.messages.middleware.MessageMiddleware",
"django.middleware.clickjacking.XFrameOptionsMiddleware",
"api.middleware.APILoggingMiddleware",
"allauth.account.middleware.AccountMiddleware",
]
SITE_ID = 1
CORS_ALLOWED_ORIGINS = ["http://localhost", "http://127.0.0.1"]
ROOT_URLCONF = "config.urls"
@@ -220,25 +208,5 @@ CACHE_STALE_WHILE_REVALIDATE = env.int("DJANGO_STALE_WHILE_REVALIDATE", 60)
TESTING = False
FINDINGS_MAX_DAYS_IN_RANGE = env.int("DJANGO_FINDINGS_MAX_DAYS_IN_RANGE", 7)
# API export settings
DJANGO_TMP_OUTPUT_DIRECTORY = env.str(
"DJANGO_TMP_OUTPUT_DIRECTORY", "/tmp/prowler_api_output"
)
DJANGO_FINDINGS_BATCH_SIZE = env.str("DJANGO_FINDINGS_BATCH_SIZE", 1000)
DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET", "")
DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = env.str("DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID", "")
DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = env.str(
"DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY", ""
)
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = env.str("DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN", "")
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION", "")
DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)
# HTTP Security Headers
SECURE_CONTENT_TYPE_NOSNIFF = True
X_FRAME_OPTIONS = "DENY"
SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
# Disable RBAC during tests/demos
DISABLE_RBAC = False

View File

@@ -1,6 +1,7 @@
from config.django.base import * # noqa
from config.env import env
DEBUG = env.bool("DJANGO_DEBUG", default=True)
ALLOWED_HOSTS = env.list("DJANGO_ALLOWED_HOSTS", default=["*"])

View File

@@ -1,6 +1,7 @@
from config.django.base import * # noqa
from config.env import env
DEBUG = env.bool("DJANGO_DEBUG", default=False)
ALLOWED_HOSTS = env.list("DJANGO_ALLOWED_HOSTS", default=["localhost", "127.0.0.1"])

View File

@@ -1,6 +1,7 @@
from config.django.base import * # noqa
from config.env import env
DEBUG = env.bool("DJANGO_DEBUG", default=False)
ALLOWED_HOSTS = env.list("DJANGO_ALLOWED_HOSTS", default=["localhost", "127.0.0.1"])
@@ -9,8 +10,8 @@ DATABASES = {
"default": {
"ENGINE": "psqlextra.backend",
"NAME": "prowler_db_test",
"USER": env("POSTGRES_USER", default="prowler_admin"),
"PASSWORD": env("POSTGRES_PASSWORD", default="postgres"),
"USER": env("POSTGRES_USER", default="prowler"),
"PASSWORD": env("POSTGRES_PASSWORD", default="S3cret"),
"HOST": env("POSTGRES_HOST", default="localhost"),
"PORT": env("POSTGRES_PORT", default="5432"),
},

View File

@@ -1,100 +0,0 @@
import sentry_sdk
from config.env import env
IGNORED_EXCEPTIONS = [
# Provider is not connected due to credentials errors
"is not connected",
# Authentication Errors from AWS
"InvalidToken",
"AccessDeniedException",
"AuthorizationErrorException",
"UnrecognizedClientException",
"UnauthorizedOperation",
"AuthFailure",
"InvalidClientTokenId",
"AWSInvalidProviderIdError",
"InternalServerErrorException",
"AccessDenied",
"No Shodan API Key", # Shodan Check
"RequestLimitExceeded", # For now we don't want to log the RequestLimitExceeded errors
"ThrottlingException",
"Rate exceeded",
"SubscriptionRequiredException",
"UnknownOperationException",
"OptInRequired",
"ReadTimeout",
"LimitExceeded",
"ConnectTimeoutError",
"ExpiredToken",
"IncompleteSignature",
"RegionDisabledException",
"TooManyRequestsException",
"SignatureDoesNotMatch",
"InvalidParameterValueException",
"InvalidInputException",
"ValidationException",
"AWSSecretAccessKeyInvalidError",
"InvalidAction",
"InvalidRequestException",
"RequestExpired",
"ConnectionClosedError",
"MaxRetryError",
"AWSAccessKeyIDInvalidError",
"AWSSessionTokenExpiredError",
"EndpointConnectionError", # AWS Service is not available in a region
"Pool is closed", # The following comes from urllib3: eu-west-1 -- HTTPClientError[126]: An HTTP Client raised an unhandled exception: AWSHTTPSConnectionPool(host='hostname.s3.eu-west-1.amazonaws.com', port=443): Pool is closed.
# Authentication Errors from GCP
"ClientAuthenticationError",
"AuthorizationFailed",
"Reauthentication is needed",
"Permission denied to get service",
"API has not been used in project",
"HttpError 404 when requesting",
"HttpError 403 when requesting",
"HttpError 400 when requesting",
"GCPNoAccesibleProjectsError",
# Authentication Errors from Azure
"ClientAuthenticationError",
"AuthorizationFailed",
"Subscription Not Registered",
"AzureNotValidClientIdError",
"AzureNotValidClientSecretError",
"AzureNotValidTenantIdError",
"AzureInvalidProviderIdError",
"AzureTenantIdAndClientSecretNotBelongingToClientIdError",
"AzureTenantIdAndClientIdNotBelongingToClientSecretError",
"AzureClientIdAndClientSecretNotBelongingToTenantIdError",
"AzureHTTPResponseError",
"Error with credentials provided",
]
def before_send(event, hint):
"""
before_send handles the Sentry events in order to sent them or not
"""
# Ignore logs with the ignored_exceptions
# https://docs.python.org/3/library/logging.html#logrecord-objects
if "log_record" in hint:
log_msg = hint["log_record"].msg
log_lvl = hint["log_record"].levelno
# Handle Error events and discard the rest
if log_lvl == 40 and any(ignored in log_msg for ignored in IGNORED_EXCEPTIONS):
return
return event
sentry_sdk.init(
dsn=env.str("DJANGO_SENTRY_DSN", ""),
# Add data like request headers and IP for users,
# see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
before_send=before_send,
send_default_pii=True,
_experiments={
# Set continuous_profiling_auto_start to True
# to automatically start the profiler on when
# possible.
"continuous_profiling_auto_start": True,
},
)

View File

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

View File

@@ -1,41 +1,38 @@
import logging
from datetime import datetime, timedelta, timezone
from unittest.mock import patch
import pytest
from django.conf import settings
from django.db import connection as django_connection
from django.db import connections as django_connections
from datetime import datetime, timezone, timedelta
from django.db import connections as django_connections, connection as django_connection
from django.urls import reverse
from django_celery_results.models import TaskResult
from prowler.lib.check.models import Severity
from prowler.lib.outputs.finding import Status
from rest_framework import status
from rest_framework.test import APIClient
from unittest.mock import patch
from api.db_utils import rls_transaction
from api.models import (
ComplianceOverview,
Finding,
Integration,
IntegrationProviderRelationship,
Invitation,
Membership,
)
from api.models import (
User,
Provider,
ProviderGroup,
ProviderSecret,
Resource,
ResourceTag,
Role,
Scan,
ScanSummary,
StateChoices,
Task,
User,
Membership,
ProviderSecret,
Invitation,
ComplianceOverview,
UserRoleRelationship,
)
from api.rls import Tenant
from api.v1.serializers import TokenSerializer
from prowler.lib.check.models import Severity
from prowler.lib.outputs.finding import Status
API_JSON_CONTENT_TYPE = "application/vnd.api+json"
NO_TENANT_HTTP_STATUS = status.HTTP_401_UNAUTHORIZED
@@ -78,6 +75,16 @@ def disable_logging():
logging.disable(logging.CRITICAL)
@pytest.fixture(scope="function")
def patch_testing_flag():
"""
Fixture to patch the TESTING flag to True during tests.
"""
with patch("api.rbac.permissions.DISABLE_RBAC", True):
with patch("api.v1.views.DISABLE_RBAC", True):
yield
@pytest.fixture(scope="session", autouse=True)
def create_test_user(django_db_setup, django_db_blocker):
with django_db_blocker.unblock():
@@ -90,14 +97,16 @@ def create_test_user(django_db_setup, django_db_blocker):
@pytest.fixture(scope="function")
def create_test_user_rbac(django_db_setup, django_db_blocker, tenants_fixture):
def create_test_user_rbac(django_db_setup, django_db_blocker):
with django_db_blocker.unblock():
user = User.objects.create_user(
name="testing",
email="rbac@rbac.com",
password=TEST_PASSWORD,
)
tenant = tenants_fixture[0]
tenant = Tenant.objects.create(
name="Tenant Test",
)
Membership.objects.create(
user=user,
tenant=tenant,
@@ -122,24 +131,6 @@ def create_test_user_rbac(django_db_setup, django_db_blocker, tenants_fixture):
return user
@pytest.fixture(scope="function")
def create_test_user_rbac_no_roles(django_db_setup, django_db_blocker, tenants_fixture):
with django_db_blocker.unblock():
user = User.objects.create_user(
name="testing",
email="rbac_noroles@rbac.com",
password=TEST_PASSWORD,
)
tenant = tenants_fixture[0]
Membership.objects.create(
user=user,
tenant=tenant,
role=Membership.RoleChoices.OWNER,
)
return user
@pytest.fixture(scope="function")
def create_test_user_rbac_limited(django_db_setup, django_db_blocker):
with django_db_blocker.unblock():
@@ -178,32 +169,8 @@ def create_test_user_rbac_limited(django_db_setup, django_db_blocker):
@pytest.fixture
def authenticated_client_rbac(create_test_user_rbac, tenants_fixture, client):
client.user = create_test_user_rbac
tenant_id = tenants_fixture[0].id
serializer = TokenSerializer(
data={
"type": "tokens",
"email": "rbac@rbac.com",
"password": TEST_PASSWORD,
"tenant_id": tenant_id,
}
)
serializer.is_valid(raise_exception=True)
access_token = serializer.validated_data["access"]
client.defaults["HTTP_AUTHORIZATION"] = f"Bearer {access_token}"
return client
@pytest.fixture
def authenticated_client_rbac_noroles(
create_test_user_rbac_no_roles, tenants_fixture, client
):
client.user = create_test_user_rbac_no_roles
serializer = TokenSerializer(
data={
"type": "tokens",
"email": "rbac_noroles@rbac.com",
"password": TEST_PASSWORD,
}
data={"type": "tokens", "email": "rbac@rbac.com", "password": TEST_PASSWORD}
)
serializer.is_valid()
access_token = serializer.validated_data["access"]
@@ -230,9 +197,7 @@ def authenticated_client_no_permissions_rbac(
@pytest.fixture
def authenticated_client(
create_test_user, tenants_fixture, set_user_admin_roles_fixture, client
):
def authenticated_client(create_test_user, tenants_fixture, client):
client.user = create_test_user
serializer = TokenSerializer(
data={"type": "tokens", "email": TEST_USER, "password": TEST_PASSWORD}
@@ -281,33 +246,10 @@ def tenants_fixture(create_test_user):
return tenant1, tenant2, tenant3
@pytest.fixture
def set_user_admin_roles_fixture(create_test_user, tenants_fixture):
user = create_test_user
for tenant in tenants_fixture[:2]:
with rls_transaction(str(tenant.id)):
role = Role.objects.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.create(
user=user,
role=role,
tenant_id=tenant.id,
)
@pytest.fixture
def invitations_fixture(create_test_user, tenants_fixture):
user = create_test_user
tenant = tenants_fixture[0]
*_, tenant = tenants_fixture
valid_invitation = Invitation.objects.create(
email="testing@prowler.com",
state=Invitation.State.PENDING,
@@ -326,20 +268,6 @@ def invitations_fixture(create_test_user, tenants_fixture):
return valid_invitation, expired_invitation
@pytest.fixture
def users_fixture(django_user_model):
user1 = User.objects.create_user(
name="user1", email="test_unit0@prowler.com", password="S3cret"
)
user2 = User.objects.create_user(
name="user2", email="test_unit1@prowler.com", password="S3cret"
)
user3 = User.objects.create_user(
name="user3", email="test_unit2@prowler.com", password="S3cret"
)
return user1, user2, user3
@pytest.fixture
def providers_fixture(tenants_fixture):
tenant, *_ = tenants_fixture
@@ -397,23 +325,6 @@ def provider_groups_fixture(tenants_fixture):
return pgroup1, pgroup2, pgroup3
@pytest.fixture
def admin_role_fixture(tenants_fixture):
tenant, *_ = tenants_fixture
return Role.objects.get_or_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,
)[0]
@pytest.fixture
def roles_fixture(tenants_fixture):
tenant, *_ = tenants_fixture
@@ -450,19 +361,8 @@ def roles_fixture(tenants_fixture):
manage_scans=True,
unlimited_visibility=True,
)
role4 = Role.objects.create(
name="Role Four",
tenant_id=tenant.id,
manage_users=False,
manage_account=False,
manage_billing=False,
manage_providers=False,
manage_integrations=False,
manage_scans=False,
unlimited_visibility=False,
)
return role1, role2, role3, role4
return role1, role2, role3
@pytest.fixture
@@ -488,7 +388,7 @@ def scans_fixture(tenants_fixture, providers_fixture):
name="Scan 1",
provider=provider,
trigger=Scan.TriggerChoices.MANUAL,
state=StateChoices.COMPLETED,
state=StateChoices.AVAILABLE,
tenant_id=tenant.id,
started_at="2024-01-02T00:00:00Z",
)
@@ -628,7 +528,6 @@ def findings_fixture(scans_fixture, resources_fixture):
"CheckId": "test_check_id",
"Description": "test description apple sauce",
},
first_seen_at="2024-01-02T00:00:00Z",
)
finding1.add_resources([resource1])
@@ -654,8 +553,6 @@ def findings_fixture(scans_fixture, resources_fixture):
"CheckId": "test_check_id",
"Description": "test description orange juice",
},
first_seen_at="2024-01-02T00:00:00Z",
muted=True,
)
finding2.add_resources([resource2])
@@ -795,147 +692,10 @@ def get_api_tokens(
data=json_body,
format="vnd.api+json",
)
return (
response.json()["data"]["attributes"]["access"],
response.json()["data"]["attributes"]["refresh"],
)
@pytest.fixture
def scan_summaries_fixture(tenants_fixture, providers_fixture):
tenant = tenants_fixture[0]
provider = providers_fixture[0]
scan = Scan.objects.create(
name="overview scan",
provider=provider,
trigger=Scan.TriggerChoices.MANUAL,
state=StateChoices.COMPLETED,
tenant=tenant,
)
ScanSummary.objects.create(
tenant=tenant,
check_id="check1",
service="service1",
severity="high",
region="region1",
_pass=1,
fail=0,
muted=0,
total=1,
new=1,
changed=0,
unchanged=0,
fail_new=0,
fail_changed=0,
pass_new=1,
pass_changed=0,
muted_new=0,
muted_changed=0,
scan=scan,
)
ScanSummary.objects.create(
tenant=tenant,
check_id="check1",
service="service1",
severity="high",
region="region2",
_pass=0,
fail=1,
muted=1,
total=2,
new=2,
changed=0,
unchanged=0,
fail_new=1,
fail_changed=0,
pass_new=0,
pass_changed=0,
muted_new=1,
muted_changed=0,
scan=scan,
)
ScanSummary.objects.create(
tenant=tenant,
check_id="check2",
service="service2",
severity="critical",
region="region1",
_pass=1,
fail=0,
muted=0,
total=1,
new=1,
changed=0,
unchanged=0,
fail_new=0,
fail_changed=0,
pass_new=1,
pass_changed=0,
muted_new=0,
muted_changed=0,
scan=scan,
)
@pytest.fixture
def integrations_fixture(providers_fixture):
provider1, provider2, *_ = providers_fixture
tenant_id = provider1.tenant_id
integration1 = Integration.objects.create(
tenant_id=tenant_id,
enabled=True,
connected=True,
integration_type="amazon_s3",
configuration={"key": "value"},
credentials={"psswd": "1234"},
)
IntegrationProviderRelationship.objects.create(
tenant_id=tenant_id,
integration=integration1,
provider=provider1,
)
integration2 = Integration.objects.create(
tenant_id=tenant_id,
enabled=True,
connected=True,
integration_type="amazon_s3",
configuration={"key": "value"},
credentials={"psswd": "1234"},
)
IntegrationProviderRelationship.objects.create(
tenant_id=tenant_id,
integration=integration2,
provider=provider1,
)
IntegrationProviderRelationship.objects.create(
tenant_id=tenant_id,
integration=integration2,
provider=provider2,
)
return integration1, integration2
return response.json()["data"]["attributes"]["access"], response.json()["data"][
"attributes"
]["refresh"]
def get_authorization_header(access_token: str) -> dict:
return {"Authorization": f"Bearer {access_token}"}
def pytest_collection_modifyitems(items):
"""Ensure test_rbac.py is executed first."""
items.sort(key=lambda item: 0 if "test_rbac.py" in item.nodeid else 1)
def pytest_configure(config):
# Apply the mock before the test session starts. This is necessary to avoid admin error when running the
# 0004_rbac_missing_admin_roles migration
patch("api.db_router.MainRouter.admin_db", new="default").start()
def pytest_unconfigure(config):
# Stop all patches after the test session ends. This is necessary to avoid admin error when running the
# 0004_rbac_missing_admin_roles migration
patch.stopall()

View File

@@ -5,14 +5,10 @@ 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.models import Provider, Scan, StateChoices
from api.models import Provider
def schedule_provider_scan(provider_instance: Provider):
tenant_id = str(provider_instance.tenant_id)
provider_id = str(provider_instance.id)
schedule, _ = IntervalSchedule.objects.get_or_create(
every=24,
period=IntervalSchedule.HOURS,
@@ -21,9 +17,23 @@ def schedule_provider_scan(provider_instance: Provider):
# Create a unique name for the periodic task
task_name = f"scan-perform-scheduled-{provider_instance.id}"
if PeriodicTask.objects.filter(
interval=schedule, name=task_name, task="scan-perform-scheduled"
).exists():
# Schedule the task
_, created = PeriodicTask.objects.get_or_create(
interval=schedule,
name=task_name,
task="scan-perform-scheduled",
kwargs=json.dumps(
{
"tenant_id": str(provider_instance.tenant_id),
"provider_id": str(provider_instance.id),
}
),
one_off=False,
defaults={
"start_time": datetime.now(timezone.utc) + timedelta(hours=24),
},
)
if not created:
raise ValidationError(
[
{
@@ -35,36 +45,9 @@ def schedule_provider_scan(provider_instance: Provider):
]
)
with rls_transaction(tenant_id):
scheduled_scan = Scan.objects.create(
tenant_id=tenant_id,
name="Daily scheduled scan",
provider_id=provider_id,
trigger=Scan.TriggerChoices.SCHEDULED,
state=StateChoices.AVAILABLE,
scheduled_at=datetime.now(timezone.utc),
)
# Schedule the task
periodic_task_instance = PeriodicTask.objects.create(
interval=schedule,
name=task_name,
task="scan-perform-scheduled",
kwargs=json.dumps(
{
"tenant_id": tenant_id,
"provider_id": provider_id,
}
),
one_off=False,
start_time=datetime.now(timezone.utc) + timedelta(hours=24),
)
scheduled_scan.scheduler_task_id = periodic_task_instance.id
scheduled_scan.save()
return perform_scheduled_scan_task.apply_async(
kwargs={
"tenant_id": str(provider_instance.tenant_id),
"provider_id": provider_id,
"provider_id": str(provider_instance.id),
},
)

View File

@@ -1,19 +1,18 @@
from celery.utils.log import get_task_logger
from django.db import DatabaseError
from django.db import transaction
from api.db_router import MainRouter
from api.db_utils import batch_delete, rls_transaction
from api.db_utils import batch_delete, tenant_transaction
from api.models import Finding, Provider, Resource, Scan, ScanSummary, Tenant
logger = get_task_logger(__name__)
def delete_provider(tenant_id: str, pk: str):
def delete_provider(pk: str):
"""
Gracefully deletes an instance of a provider along with its related data.
Args:
tenant_id (str): Tenant ID the resources belong to.
pk (str): The primary key of the Provider instance to delete.
Returns:
@@ -23,31 +22,33 @@ def delete_provider(tenant_id: str, pk: str):
Raises:
Provider.DoesNotExist: If no instance with the provided primary key exists.
"""
with rls_transaction(tenant_id):
instance = Provider.all_objects.get(pk=pk)
deletion_summary = {}
deletion_steps = [
("Scan Summaries", ScanSummary.all_objects.filter(scan__provider=instance)),
("Findings", Finding.all_objects.filter(scan__provider=instance)),
("Resources", Resource.all_objects.filter(provider=instance)),
("Scans", Scan.all_objects.filter(provider=instance)),
]
instance = Provider.all_objects.get(pk=pk)
deletion_summary = {}
for step_name, queryset in deletion_steps:
try:
_, step_summary = batch_delete(tenant_id, queryset)
deletion_summary.update(step_summary)
except DatabaseError as db_error:
logger.error(f"Error deleting {step_name}: {db_error}")
raise
with transaction.atomic():
# Delete Scan Summaries
scan_summaries_qs = ScanSummary.all_objects.filter(scan__provider=instance)
_, scans_summ_summary = batch_delete(scan_summaries_qs)
deletion_summary.update(scans_summ_summary)
try:
with rls_transaction(tenant_id):
_, provider_summary = instance.delete()
# Delete Findings
findings_qs = Finding.all_objects.filter(scan__provider=instance)
_, findings_summary = batch_delete(findings_qs)
deletion_summary.update(findings_summary)
# Delete Resources
resources_qs = Resource.all_objects.filter(provider=instance)
_, resources_summary = batch_delete(resources_qs)
deletion_summary.update(resources_summary)
# Delete Scans
scans_qs = Scan.all_objects.filter(provider=instance)
_, scans_summary = batch_delete(scans_qs)
deletion_summary.update(scans_summary)
provider_deleted_count, provider_summary = instance.delete()
deletion_summary.update(provider_summary)
except DatabaseError as db_error:
logger.error(f"Error deleting Provider: {db_error}")
raise
return deletion_summary
@@ -65,8 +66,9 @@ def delete_tenant(pk: str):
deletion_summary = {}
for provider in Provider.objects.using(MainRouter.admin_db).filter(tenant_id=pk):
summary = delete_provider(pk, provider.id)
deletion_summary.update(summary)
with tenant_transaction(pk):
summary = delete_provider(provider.id)
deletion_summary.update(summary)
Tenant.objects.using(MainRouter.admin_db).filter(id=pk).delete()

View File

@@ -1,156 +0,0 @@
import os
import zipfile
import boto3
import config.django.base as base
from botocore.exceptions import ClientError, NoCredentialsError, ParamValidationError
from celery.utils.log import get_task_logger
from django.conf import settings
from prowler.config.config import (
csv_file_suffix,
html_file_suffix,
json_ocsf_file_suffix,
output_file_timestamp,
)
from prowler.lib.outputs.csv.csv import CSV
from prowler.lib.outputs.html.html import HTML
from prowler.lib.outputs.ocsf.ocsf import OCSF
logger = get_task_logger(__name__)
# Predefined mapping for output formats and their configurations
OUTPUT_FORMATS_MAPPING = {
"csv": {
"class": CSV,
"suffix": csv_file_suffix,
"kwargs": {},
},
"json-ocsf": {"class": OCSF, "suffix": json_ocsf_file_suffix, "kwargs": {}},
"html": {"class": HTML, "suffix": html_file_suffix, "kwargs": {"stats": {}}},
}
def _compress_output_files(output_directory: str) -> str:
"""
Compress output files from all configured output formats into a ZIP archive.
Args:
output_directory (str): The directory where the output files are located.
The function looks up all known suffixes in OUTPUT_FORMATS_MAPPING
and compresses those files into a single ZIP.
Returns:
str: The full path to the newly created ZIP archive.
"""
zip_path = f"{output_directory}.zip"
with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zipf:
for suffix in [config["suffix"] for config in OUTPUT_FORMATS_MAPPING.values()]:
zipf.write(
f"{output_directory}{suffix}",
f"output/{output_directory.split('/')[-1]}{suffix}",
)
return zip_path
def get_s3_client():
"""
Create and return a boto3 S3 client using AWS credentials from environment variables.
This function attempts to initialize an S3 client by reading the AWS access key, secret key,
session token, and region from environment variables. It then validates the client by listing
available S3 buckets. If an error occurs during this process (for example, due to missing or
invalid credentials), it falls back to creating an S3 client without explicitly provided credentials,
which may rely on other configuration sources (e.g., IAM roles).
Returns:
boto3.client: A configured S3 client instance.
Raises:
ClientError, NoCredentialsError, or ParamValidationError if both attempts to create a client fail.
"""
s3_client = None
try:
s3_client = boto3.client(
"s3",
aws_access_key_id=settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID,
aws_secret_access_key=settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY,
aws_session_token=settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN,
region_name=settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION,
)
s3_client.list_buckets()
except (ClientError, NoCredentialsError, ParamValidationError, ValueError):
s3_client = boto3.client("s3")
s3_client.list_buckets()
return s3_client
def _upload_to_s3(tenant_id: str, zip_path: str, scan_id: str) -> str:
"""
Upload the specified ZIP file to an S3 bucket.
If the S3 bucket environment variables are not configured,
the function returns None without performing an upload.
Args:
tenant_id (str): The tenant identifier, used as part of the S3 key prefix.
zip_path (str): The local file system path to the ZIP file to be uploaded.
scan_id (str): The scan identifier, used as part of the S3 key prefix.
Returns:
str: The S3 URI of the uploaded file (e.g., "s3://<bucket>/<key>") if successful.
None: If the required environment variables for the S3 bucket are not set.
Raises:
botocore.exceptions.ClientError: If the upload attempt to S3 fails for any reason.
"""
if not base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET:
return
try:
s3 = get_s3_client()
s3_key = f"{tenant_id}/{scan_id}/{os.path.basename(zip_path)}"
s3.upload_file(
Filename=zip_path,
Bucket=base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET,
Key=s3_key,
)
return f"s3://{base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET}/{s3_key}"
except (ClientError, NoCredentialsError, ParamValidationError, ValueError) as e:
logger.error(f"S3 upload failed: {str(e)}")
def _generate_output_directory(
output_directory, prowler_provider: object, tenant_id: str, scan_id: str
) -> str:
"""
Generate a file system path for the output directory of a prowler scan.
This function constructs the output directory path by combining a base
temporary output directory, the tenant ID, the scan ID, and details about
the prowler provider along with a timestamp. The resulting path is used to
store the output files of a prowler scan.
Note:
This function depends on one external variable:
- `output_file_timestamp`: A timestamp (as a string) used to uniquely identify the output.
Args:
output_directory (str): The base output directory.
prowler_provider (object): An identifier or descriptor for the prowler provider.
Typically, this is a string indicating the provider (e.g., "aws").
tenant_id (str): The unique identifier for the tenant.
scan_id (str): The unique identifier for the scan.
Returns:
str: The constructed file system path for the prowler scan output directory.
Example:
>>> _generate_output_directory("/tmp", "aws", "tenant-1234", "scan-5678")
'/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56'
"""
path = (
f"{output_directory}/{tenant_id}/{scan_id}/prowler-output-"
f"{prowler_provider}-{output_file_timestamp}"
)
os.makedirs("/".join(path.split("/")[:-1]), exist_ok=True)
return path

View File

@@ -1,4 +1,3 @@
import json
import time
from copy import deepcopy
from datetime import datetime, timezone
@@ -7,13 +6,12 @@ from celery.utils.log import get_task_logger
from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
from django.db import IntegrityError, OperationalError
from django.db.models import Case, Count, IntegerField, Sum, When
from tasks.utils import CustomEncoder
from api.compliance import (
PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
generate_scan_compliance,
)
from api.db_utils import rls_transaction
from api.db_utils import tenant_transaction
from api.models import (
ComplianceOverview,
Finding,
@@ -71,7 +69,7 @@ def _store_resources(
- tuple[str, str]: A tuple containing the resource UID and region.
"""
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
resource_instance, created = Resource.objects.get_or_create(
tenant_id=tenant_id,
provider=provider_instance,
@@ -88,7 +86,7 @@ def _store_resources(
resource_instance.service = finding.service_name
resource_instance.type = finding.resource_type
resource_instance.save()
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
tags = [
ResourceTag.objects.get_or_create(
tenant_id=tenant_id, key=key, value=value
@@ -118,12 +116,13 @@ def perform_prowler_scan(
ValueError: If the provider cannot be connected.
"""
generate_compliance = False
check_status_by_region = {}
exception = None
unique_resources = set()
start_time = time.time()
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
provider_instance = Provider.objects.get(pk=provider_id)
scan_instance = Scan.objects.get(pk=scan_id)
scan_instance.state = StateChoices.EXECUTING
@@ -131,7 +130,7 @@ def perform_prowler_scan(
scan_instance.save()
try:
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
try:
prowler_provider = initialize_prowler_provider(provider_instance)
provider_instance.connected = True
@@ -146,6 +145,7 @@ def perform_prowler_scan(
)
provider_instance.save()
generate_compliance = provider_instance.provider != Provider.ProviderChoices.GCP
prowler_scan = ProwlerScan(provider=prowler_provider, checks=checks_to_execute)
resource_cache = {}
@@ -154,12 +154,9 @@ def perform_prowler_scan(
for progress, findings in prowler_scan.scan():
for finding in findings:
if finding is None:
logger.error(f"None finding detected on scan {scan_id}.")
continue
for attempt in range(CELERY_DEADLOCK_ATTEMPTS):
try:
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
# Process resource
resource_uid = finding.resource_uid
if resource_uid not in resource_cache:
@@ -181,10 +178,7 @@ def perform_prowler_scan(
# Update resource fields if necessary
updated_fields = []
if (
finding.region
and resource_instance.region != finding.region
):
if resource_instance.region != finding.region:
resource_instance.region = finding.region
updated_fields.append("region")
if resource_instance.service != finding.service_name:
@@ -193,19 +187,8 @@ def perform_prowler_scan(
if resource_instance.type != finding.resource_type:
resource_instance.type = finding.resource_type
updated_fields.append("type")
if resource_instance.metadata != finding.resource_metadata:
resource_instance.metadata = json.dumps(
finding.resource_metadata, cls=CustomEncoder
)
updated_fields.append("metadata")
if resource_instance.details != finding.resource_details:
resource_instance.details = finding.resource_details
updated_fields.append("details")
if resource_instance.partition != finding.partition:
resource_instance.partition = finding.partition
updated_fields.append("partition")
if updated_fields:
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
resource_instance.save(update_fields=updated_fields)
except (OperationalError, IntegrityError) as db_err:
if attempt < CELERY_DEADLOCK_ATTEMPTS - 1:
@@ -220,7 +203,7 @@ def perform_prowler_scan(
# Update tags
tags = []
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
for key, value in finding.resource_tags.items():
tag_key = (key, value)
if tag_key not in tag_cache:
@@ -236,35 +219,26 @@ def perform_prowler_scan(
unique_resources.add((resource_instance.uid, resource_instance.region))
# Process finding
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
finding_uid = finding.uid
last_first_seen_at = None
if finding_uid not in last_status_cache:
most_recent_finding = (
Finding.all_objects.filter(
tenant_id=tenant_id, uid=finding_uid
)
.order_by("-inserted_at")
.values("status", "first_seen_at")
Finding.objects.filter(uid=finding_uid)
.order_by("-id")
.values("status")
.first()
)
last_status = None
if most_recent_finding:
last_status = most_recent_finding["status"]
last_first_seen_at = most_recent_finding["first_seen_at"]
last_status_cache[finding_uid] = last_status, last_first_seen_at
last_status = (
most_recent_finding["status"]
if most_recent_finding
else None
)
last_status_cache[finding_uid] = last_status
else:
last_status, last_first_seen_at = last_status_cache[finding_uid]
last_status = last_status_cache[finding_uid]
status = FindingStatus[finding.status]
delta = _create_finding_delta(last_status, status)
# For the findings prior to the change, when a first finding is found with delta!="new" it will be
# assigned a current date as first_seen_at and the successive findings with the same UID will
# always get the date of the previous finding.
# For new findings, when a finding (delta="new") is found for the first time, the first_seen_at
# attribute will be assigned the current date, the following findings will get that date.
if not last_first_seen_at:
last_first_seen_at = datetime.now(tz=timezone.utc)
# Create the finding
finding_instance = Finding.objects.create(
@@ -279,14 +253,11 @@ def perform_prowler_scan(
raw_result=finding.raw,
check_id=finding.check_id,
scan=scan_instance,
first_seen_at=last_first_seen_at,
muted=finding.muted,
compliance=finding.compliance,
)
finding_instance.add_resources([resource_instance])
# Update compliance data if applicable
if finding.status.value == "MUTED":
if not generate_compliance or finding.status.value == "MUTED":
continue
region_dict = check_status_by_region.setdefault(finding.region, {})
@@ -296,7 +267,7 @@ def perform_prowler_scan(
region_dict[finding.check_id] = finding.status.value
# Update scan progress
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
scan_instance.progress = progress
scan_instance.save()
@@ -308,13 +279,13 @@ def perform_prowler_scan(
scan_instance.state = StateChoices.FAILED
finally:
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
scan_instance.duration = time.time() - start_time
scan_instance.completed_at = datetime.now(tz=timezone.utc)
scan_instance.unique_resource_count = len(unique_resources)
scan_instance.save()
if exception is None:
if exception is None and generate_compliance:
try:
regions = prowler_provider.get_regions()
except AttributeError:
@@ -359,18 +330,9 @@ def perform_prowler_scan(
total_requirements=compliance["total_requirements"],
)
)
try:
with rls_transaction(tenant_id):
ComplianceOverview.objects.bulk_create(
compliance_overview_objects, batch_size=100
)
except Exception as overview_exception:
import sentry_sdk
with tenant_transaction(tenant_id):
ComplianceOverview.objects.bulk_create(compliance_overview_objects)
sentry_sdk.capture_exception(overview_exception)
logger.error(
f"Error storing compliance overview for scan {scan_id}: {overview_exception}"
)
if exception is not None:
raise exception
@@ -406,8 +368,8 @@ def aggregate_findings(tenant_id: str, scan_id: str):
- muted_new: Muted findings with a delta of 'new'.
- muted_changed: Muted findings with a delta of 'changed'.
"""
with rls_transaction(tenant_id):
findings = Finding.objects.filter(tenant_id=tenant_id, scan_id=scan_id)
with tenant_transaction(tenant_id):
findings = Finding.objects.filter(scan_id=scan_id)
aggregation = findings.values(
"check_id",
@@ -417,21 +379,21 @@ def aggregate_findings(tenant_id: str, scan_id: str):
).annotate(
fail=Sum(
Case(
When(status="FAIL", muted=False, then=1),
When(status="FAIL", then=1),
default=0,
output_field=IntegerField(),
)
),
_pass=Sum(
Case(
When(status="PASS", muted=False, then=1),
When(status="PASS", then=1),
default=0,
output_field=IntegerField(),
)
),
muted_count=Sum(
muted=Sum(
Case(
When(muted=True, then=1),
When(status="MUTED", then=1),
default=0,
output_field=IntegerField(),
)
@@ -439,70 +401,70 @@ def aggregate_findings(tenant_id: str, scan_id: str):
total=Count("id"),
new=Sum(
Case(
When(delta="new", muted=False, then=1),
When(delta="new", then=1),
default=0,
output_field=IntegerField(),
)
),
changed=Sum(
Case(
When(delta="changed", muted=False, then=1),
When(delta="changed", then=1),
default=0,
output_field=IntegerField(),
)
),
unchanged=Sum(
Case(
When(delta__isnull=True, muted=False, then=1),
When(delta__isnull=True, then=1),
default=0,
output_field=IntegerField(),
)
),
fail_new=Sum(
Case(
When(delta="new", status="FAIL", muted=False, then=1),
When(delta="new", status="FAIL", then=1),
default=0,
output_field=IntegerField(),
)
),
fail_changed=Sum(
Case(
When(delta="changed", status="FAIL", muted=False, then=1),
When(delta="changed", status="FAIL", then=1),
default=0,
output_field=IntegerField(),
)
),
pass_new=Sum(
Case(
When(delta="new", status="PASS", muted=False, then=1),
When(delta="new", status="PASS", then=1),
default=0,
output_field=IntegerField(),
)
),
pass_changed=Sum(
Case(
When(delta="changed", status="PASS", muted=False, then=1),
When(delta="changed", status="PASS", then=1),
default=0,
output_field=IntegerField(),
)
),
muted_new=Sum(
Case(
When(delta="new", muted=True, then=1),
When(delta="new", status="MUTED", then=1),
default=0,
output_field=IntegerField(),
)
),
muted_changed=Sum(
Case(
When(delta="changed", muted=True, then=1),
When(delta="changed", status="MUTED", then=1),
default=0,
output_field=IntegerField(),
)
),
)
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
scan_aggregations = {
ScanSummary(
tenant_id=tenant_id,
@@ -513,7 +475,7 @@ def aggregate_findings(tenant_id: str, scan_id: str):
region=agg["resources__region"],
fail=agg["fail"],
_pass=agg["_pass"],
muted=agg["muted_count"],
muted=agg["muted"],
total=agg["total"],
new=agg["new"],
changed=agg["changed"],

View File

@@ -1,31 +1,15 @@
from datetime import datetime, timedelta, timezone
from pathlib import Path
from shutil import rmtree
from celery import chain, shared_task
from celery.utils.log import get_task_logger
from celery import shared_task
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.connection import check_provider_connection
from tasks.jobs.deletion import delete_provider, delete_tenant
from tasks.jobs.export import (
OUTPUT_FORMATS_MAPPING,
_compress_output_files,
_generate_output_directory,
_upload_to_s3,
)
from tasks.jobs.scan import aggregate_findings, perform_prowler_scan
from tasks.utils import batched, get_next_execution_datetime
from api.db_utils import rls_transaction
from api.db_utils import tenant_transaction
from api.decorators import set_tenant
from api.models import Finding, Provider, Scan, ScanSummary, StateChoices
from api.utils import initialize_prowler_provider
from api.v1.serializers import ScanTaskSerializer
from prowler.lib.outputs.finding import Finding as FindingOutput
logger = get_task_logger(__name__)
from api.models import Provider, Scan
@shared_task(base=RLSTask, name="provider-connection-check")
@@ -45,10 +29,9 @@ def check_provider_connection_task(provider_id: str):
return check_provider_connection(provider_id=provider_id)
@shared_task(
base=RLSTask, name="provider-deletion", queue="deletion", autoretry_for=(Exception,)
)
def delete_provider_task(provider_id: str, tenant_id: str):
@shared_task(base=RLSTask, name="provider-deletion")
@set_tenant
def delete_provider_task(provider_id: str):
"""
Task to delete a specific Provider instance.
@@ -56,7 +39,6 @@ def delete_provider_task(provider_id: str, tenant_id: str):
Args:
provider_id (str): The primary key of the `Provider` instance to be deleted.
tenant_id (str): Tenant ID the provider belongs to.
Returns:
tuple: A tuple containing:
@@ -64,7 +46,7 @@ def delete_provider_task(provider_id: str, tenant_id: str):
- A dictionary with the count of deleted instances per model,
including related models if cascading deletes were triggered.
"""
return delete_provider(tenant_id=tenant_id, pk=provider_id)
return delete_provider(pk=provider_id)
@shared_task(base=RLSTask, name="scan-perform", queue="scans")
@@ -87,22 +69,13 @@ def perform_scan_task(
Returns:
dict: The result of the scan execution, typically including the status and results of the performed checks.
"""
result = perform_prowler_scan(
return perform_prowler_scan(
tenant_id=tenant_id,
scan_id=scan_id,
provider_id=provider_id,
checks_to_execute=checks_to_execute,
)
chain(
perform_scan_summary_task.si(tenant_id, scan_id),
generate_outputs.si(
scan_id=scan_id, provider_id=provider_id, tenant_id=tenant_id
),
).apply_async()
return result
@shared_task(base=RLSTask, bind=True, name="scan-perform-scheduled", queue="scans")
def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
@@ -126,91 +99,35 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
"""
task_id = self.request.id
with rls_transaction(tenant_id):
with tenant_transaction(tenant_id):
provider_instance = Provider.objects.get(pk=provider_id)
periodic_task_instance = PeriodicTask.objects.get(
name=f"scan-perform-scheduled-{provider_id}"
)
next_scan_date = datetime.combine(
datetime.now(timezone.utc), periodic_task_instance.start_time.time()
) + timedelta(hours=24)
executed_scan = Scan.objects.filter(
scan_instance = Scan.objects.create(
tenant_id=tenant_id,
provider_id=provider_id,
task__task_runner_task__task_id=task_id,
).order_by("completed_at")
if (
Scan.objects.filter(
tenant_id=tenant_id,
provider_id=provider_id,
trigger=Scan.TriggerChoices.SCHEDULED,
state=StateChoices.EXECUTING,
scheduler_task_id=periodic_task_instance.id,
scheduled_at__date=datetime.now(timezone.utc).date(),
).exists()
or executed_scan.exists()
):
# Duplicated task execution due to visibility timeout or scan is already running
logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
try:
affected_scan = executed_scan.first()
if not affected_scan:
raise ValueError(
"Error retrieving affected scan details after detecting duplicated scheduled "
"scan."
)
# Return the affected scan details to avoid losing data
serializer = ScanTaskSerializer(instance=affected_scan)
except Exception as duplicated_scan_exception:
logger.error(
f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
f"{str(duplicated_scan_exception)}"
)
raise duplicated_scan_exception
return serializer.data
next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
scan_instance, _ = Scan.objects.get_or_create(
tenant_id=tenant_id,
provider_id=provider_id,
name="Daily scheduled scan",
provider=provider_instance,
trigger=Scan.TriggerChoices.SCHEDULED,
state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
scheduler_task_id=periodic_task_instance.id,
defaults={
"state": StateChoices.SCHEDULED,
"name": "Daily scheduled scan",
"scheduled_at": next_scan_datetime - timedelta(days=1),
},
next_scan_at=next_scan_date,
task_id=task_id,
)
scan_instance.task_id = task_id
scan_instance.save()
try:
result = perform_prowler_scan(
tenant_id=tenant_id,
scan_id=str(scan_instance.id),
provider_id=provider_id,
)
except Exception as e:
raise e
finally:
with rls_transaction(tenant_id):
Scan.objects.get_or_create(
tenant_id=tenant_id,
name="Daily scheduled scan",
provider_id=provider_id,
trigger=Scan.TriggerChoices.SCHEDULED,
state=StateChoices.SCHEDULED,
scheduled_at=next_scan_datetime,
scheduler_task_id=periodic_task_instance.id,
)
chain(
perform_scan_summary_task.si(tenant_id, scan_instance.id),
generate_outputs.si(
scan_id=str(scan_instance.id), provider_id=provider_id, tenant_id=tenant_id
),
).apply_async()
result = perform_prowler_scan(
tenant_id=tenant_id,
scan_id=str(scan_instance.id),
provider_id=provider_id,
)
perform_scan_summary_task.apply_async(
kwargs={
"tenant_id": tenant_id,
"scan_id": str(scan_instance.id),
}
)
return result
@@ -219,116 +136,6 @@ def perform_scan_summary_task(tenant_id: str, scan_id: str):
return aggregate_findings(tenant_id=tenant_id, scan_id=scan_id)
@shared_task(name="tenant-deletion", queue="deletion", autoretry_for=(Exception,))
@shared_task(name="tenant-deletion")
def delete_tenant_task(tenant_id: str):
return delete_tenant(pk=tenant_id)
@shared_task(
base=RLSTask,
name="scan-report",
queue="scan-reports",
)
@set_tenant(keep_tenant=True)
def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
"""
Process findings in batches and generate output files in multiple formats.
This function retrieves findings associated with a scan, processes them
in batches of 50, and writes each batch to the corresponding output files.
It reuses output writer instances across batches, updates them with each
batch of transformed findings, and uses a flag to indicate when the final
batch is being processed. Finally, the output files are compressed and
uploaded to S3.
Args:
tenant_id (str): The tenant identifier.
scan_id (str): The scan identifier.
provider_id (str): The provider_id id to be used in generating outputs.
"""
# Check if the scan has findings
if not ScanSummary.objects.filter(scan_id=scan_id).exists():
logger.info(f"No findings found for scan {scan_id}")
return {"upload": False}
# Initialize the prowler provider
prowler_provider = initialize_prowler_provider(Provider.objects.get(id=provider_id))
# Get the provider UID
provider_uid = Provider.objects.get(id=provider_id).uid
# Generate and ensure the output directory exists
output_directory = _generate_output_directory(
DJANGO_TMP_OUTPUT_DIRECTORY, provider_uid, tenant_id, scan_id
)
# Define auxiliary variables
output_writers = {}
scan_summary = FindingOutput._transform_findings_stats(
ScanSummary.objects.filter(scan_id=scan_id)
)
# Retrieve findings queryset
findings_qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid")
# Process findings in batches
for batch, is_last_batch in batched(
findings_qs.iterator(), DJANGO_FINDINGS_BATCH_SIZE
):
finding_outputs = [
FindingOutput.transform_api_finding(finding, prowler_provider)
for finding in batch
]
# Generate output files
for mode, config in OUTPUT_FORMATS_MAPPING.items():
kwargs = dict(config.get("kwargs", {}))
if mode == "html":
kwargs["provider"] = prowler_provider
kwargs["stats"] = scan_summary
writer_class = config["class"]
if writer_class in output_writers:
writer = output_writers[writer_class]
writer.transform(finding_outputs)
writer.close_file = is_last_batch
else:
writer = writer_class(
findings=finding_outputs,
file_path=output_directory,
file_extension=config["suffix"],
from_cli=False,
)
writer.close_file = is_last_batch
output_writers[writer_class] = writer
# Write the current batch using the writer
writer.batch_write_data_to_file(**kwargs)
# TODO: Refactor the output classes to avoid this manual reset
writer._data = []
# Compress output files
output_directory = _compress_output_files(output_directory)
# Save to configured storage
uploaded = _upload_to_s3(tenant_id, output_directory, scan_id)
if uploaded:
# Remove the local files after upload
try:
rmtree(Path(output_directory).parent, ignore_errors=True)
except FileNotFoundError as e:
logger.error(f"Error deleting output files: {e}")
output_directory = uploaded
uploaded = True
else:
uploaded = False
# Update the scan instance with the output path
Scan.all_objects.filter(id=scan_id).update(output_location=output_directory)
logger.info(f"Scan output files generated, output location: {output_directory}")
return {"upload": uploaded}

View File

@@ -6,8 +6,6 @@ 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.models import Scan
@pytest.mark.django_db
class TestScheduleProviderScan:
@@ -17,11 +15,9 @@ class TestScheduleProviderScan:
with patch(
"tasks.tasks.perform_scheduled_scan_task.apply_async"
) as mock_apply_async:
assert Scan.all_objects.count() == 0
result = schedule_provider_scan(provider_instance)
assert result is not None
assert Scan.all_objects.count() == 1
mock_apply_async.assert_called_once_with(
kwargs={

View File

@@ -1,3 +1,5 @@
from unittest.mock import patch
import pytest
from django.core.exceptions import ObjectDoesNotExist
from tasks.jobs.deletion import delete_provider, delete_tenant
@@ -9,21 +11,20 @@ from api.models import Provider, Tenant
class TestDeleteProvider:
def test_delete_provider_success(self, providers_fixture):
instance = providers_fixture[0]
tenant_id = str(instance.tenant_id)
result = delete_provider(tenant_id, instance.id)
result = delete_provider(instance.id)
assert result
with pytest.raises(ObjectDoesNotExist):
Provider.objects.get(pk=instance.id)
def test_delete_provider_does_not_exist(self, tenants_fixture):
tenant_id = str(tenants_fixture[0].id)
def test_delete_provider_does_not_exist(self):
non_existent_pk = "babf6796-cfcc-4fd3-9dcf-88d012247645"
with pytest.raises(ObjectDoesNotExist):
delete_provider(tenant_id, non_existent_pk)
delete_provider(non_existent_pk)
@patch("api.db_router.MainRouter.admin_db", new="default")
@pytest.mark.django_db
class TestDeleteTenant:
def test_delete_tenant_success(self, tenants_fixture, providers_fixture):

View File

@@ -1,5 +1,3 @@
import json
import uuid
from unittest.mock import MagicMock, patch
import pytest
@@ -8,7 +6,6 @@ from tasks.jobs.scan import (
_store_resources,
perform_prowler_scan,
)
from tasks.utils import CustomEncoder
from api.models import (
Finding,
@@ -29,7 +26,7 @@ class TestPerformScan:
providers_fixture,
):
with (
patch("api.db_utils.rls_transaction"),
patch("api.db_utils.tenant_transaction"),
patch(
"tasks.jobs.scan.initialize_prowler_provider"
) as mock_initialize_prowler_provider,
@@ -109,13 +106,7 @@ class TestPerformScan:
finding.service_name = "service_name"
finding.resource_type = "resource_type"
finding.resource_tags = {"tag1": "value1", "tag2": "value2"}
finding.muted = False
finding.raw = {}
finding.resource_metadata = {"test": "metadata"}
finding.resource_details = {"details": "test"}
finding.partition = "partition"
finding.muted = True
finding.compliance = {"compliance1": "PASS"}
# Mock the ProwlerScan instance
mock_prowler_scan_instance = MagicMock()
@@ -153,8 +144,6 @@ class TestPerformScan:
assert scan_finding.severity == finding.severity
assert scan_finding.check_id == finding.check_id
assert scan_finding.raw_result == finding.raw
assert scan_finding.muted
assert scan_finding.compliance == finding.compliance
assert scan_resource.tenant == tenant
assert scan_resource.uid == finding.resource_uid
@@ -162,11 +151,6 @@ class TestPerformScan:
assert scan_resource.service == finding.service_name
assert scan_resource.type == finding.resource_type
assert scan_resource.name == finding.resource_name
assert scan_resource.metadata == json.dumps(
finding.resource_metadata, cls=CustomEncoder
)
assert scan_resource.details == f"{finding.resource_details}"
assert scan_resource.partition == finding.partition
# Assert that the resource tags have been created and associated
tags = scan_resource.tags.all()
@@ -181,10 +165,10 @@ class TestPerformScan:
"tasks.jobs.scan.initialize_prowler_provider",
side_effect=Exception("Connection error"),
)
@patch("api.db_utils.rls_transaction")
@patch("api.db_utils.tenant_transaction")
def test_perform_prowler_scan_no_connection(
self,
mock_rls_transaction,
mock_tenant_transaction,
mock_initialize_prowler_provider,
mock_prowler_scan_class,
tenants_fixture,
@@ -221,14 +205,14 @@ class TestPerformScan:
@patch("api.models.ResourceTag.objects.get_or_create")
@patch("api.models.Resource.objects.get_or_create")
@patch("api.db_utils.rls_transaction")
@patch("api.db_utils.tenant_transaction")
def test_store_resources_new_resource(
self,
mock_rls_transaction,
mock_tenant_transaction,
mock_get_or_create_resource,
mock_get_or_create_tag,
):
tenant_id = uuid.uuid4()
tenant_id = "tenant123"
provider_instance = MagicMock()
provider_instance.id = "provider456"
@@ -269,14 +253,14 @@ class TestPerformScan:
@patch("api.models.ResourceTag.objects.get_or_create")
@patch("api.models.Resource.objects.get_or_create")
@patch("api.db_utils.rls_transaction")
@patch("api.db_utils.tenant_transaction")
def test_store_resources_existing_resource(
self,
mock_rls_transaction,
mock_tenant_transaction,
mock_get_or_create_resource,
mock_get_or_create_tag,
):
tenant_id = uuid.uuid4()
tenant_id = "tenant123"
provider_instance = MagicMock()
provider_instance.id = "provider456"
@@ -326,14 +310,14 @@ class TestPerformScan:
@patch("api.models.ResourceTag.objects.get_or_create")
@patch("api.models.Resource.objects.get_or_create")
@patch("api.db_utils.rls_transaction")
@patch("api.db_utils.tenant_transaction")
def test_store_resources_with_tags(
self,
mock_rls_transaction,
mock_tenant_transaction,
mock_get_or_create_resource,
mock_get_or_create_tag,
):
tenant_id = uuid.uuid4()
tenant_id = "tenant123"
provider_instance = MagicMock()
provider_instance.id = "provider456"

View File

@@ -1,102 +0,0 @@
from datetime import datetime, timedelta, timezone
from unittest.mock import patch
import pytest
from django_celery_beat.models import IntervalSchedule, PeriodicTask
from django_celery_results.models import TaskResult
from tasks.utils import batched, get_next_execution_datetime
@pytest.mark.django_db
class TestGetNextExecutionDatetime:
@pytest.fixture
def setup_periodic_task(self, db):
# Create a periodic task with an hourly interval
interval = IntervalSchedule.objects.create(
every=1, period=IntervalSchedule.HOURS
)
periodic_task = PeriodicTask.objects.create(
name="scan-perform-scheduled-123",
task="scan-perform-scheduled",
interval=interval,
)
return periodic_task
@pytest.fixture
def setup_task_result(self, db):
# Create a task result record
task_result = TaskResult.objects.create(
task_id="abc123",
task_name="scan-perform-scheduled",
status="SUCCESS",
date_created=datetime.now(timezone.utc) - timedelta(hours=1),
result="Success",
)
return task_result
def test_get_next_execution_datetime_success(
self, setup_task_result, setup_periodic_task
):
task_result = setup_task_result
periodic_task = setup_periodic_task
# Mock periodic_task_name on TaskResult
with patch.object(
TaskResult, "periodic_task_name", return_value=periodic_task.name
):
next_execution = get_next_execution_datetime(
task_id=task_result.task_id, provider_id="123"
)
expected_time = task_result.date_created + timedelta(hours=1)
assert next_execution == expected_time
def test_get_next_execution_datetime_fallback_to_provider_id(
self, setup_task_result, setup_periodic_task
):
task_result = setup_task_result
# Simulate the case where `periodic_task_name` is missing
with patch.object(TaskResult, "periodic_task_name", return_value=None):
next_execution = get_next_execution_datetime(
task_id=task_result.task_id, provider_id="123"
)
expected_time = task_result.date_created + timedelta(hours=1)
assert next_execution == expected_time
def test_get_next_execution_datetime_periodic_task_does_not_exist(
self, setup_task_result
):
task_result = setup_task_result
with pytest.raises(PeriodicTask.DoesNotExist):
get_next_execution_datetime(
task_id=task_result.task_id, provider_id="nonexistent"
)
class TestBatchedFunction:
def test_empty_iterable(self):
result = list(batched([], 3))
assert result == [([], True)]
def test_exact_batches(self):
result = list(batched([1, 2, 3, 4], 2))
expected = [([1, 2], False), ([3, 4], False), ([], True)]
assert result == expected
def test_inexact_batches(self):
result = list(batched([1, 2, 3, 4, 5], 2))
expected = [([1, 2], False), ([3, 4], False), ([5], True)]
assert result == expected
def test_batch_size_one(self):
result = list(batched([1, 2, 3], 1))
expected = [([1], False), ([2], False), ([3], False), ([], True)]
assert result == expected
def test_batch_size_greater_than_length(self):
result = list(batched([1, 2, 3], 5))
expected = [([1, 2, 3], True)]
assert result == expected

View File

@@ -1,73 +0,0 @@
import json
from datetime import datetime, timedelta, timezone
from enum import Enum
from django_celery_beat.models import PeriodicTask
from django_celery_results.models import TaskResult
class CustomEncoder(json.JSONEncoder):
def default(self, o):
# Enum serialization
if isinstance(o, Enum):
return o.value
# Datetime and timedelta serialization
if isinstance(o, datetime):
return o.isoformat(timespec="seconds")
if isinstance(o, timedelta):
return o.total_seconds()
# Custom object serialization
try:
return super().default(o)
except TypeError:
try:
return o.__dict__
except AttributeError:
return str(o)
def get_next_execution_datetime(task_id: int, provider_id: str) -> datetime:
task_instance = TaskResult.objects.get(task_id=task_id)
try:
periodic_task_instance = PeriodicTask.objects.get(
name=task_instance.periodic_task_name
)
except PeriodicTask.DoesNotExist:
periodic_task_instance = PeriodicTask.objects.get(
name=f"scan-perform-scheduled-{provider_id}"
)
interval = periodic_task_instance.interval
current_scheduled_time = datetime.combine(
datetime.now(timezone.utc).date(),
task_instance.date_created.time(),
tzinfo=timezone.utc,
)
return current_scheduled_time + timedelta(**{interval.period: interval.every})
def batched(iterable, batch_size):
"""
Yield successive batches from an iterable.
Args:
iterable: An iterable source of items.
batch_size (int): The number of items per batch.
Yields:
tuple: A pair (batch, is_last_batch) where:
- batch (list): A list of items (with length equal to batch_size,
except possibly for the last batch).
- is_last_batch (bool): True if this is the final batch, False otherwise.
"""
batch = []
for item in iterable:
batch.append(item)
if len(batch) == batch_size:
yield batch, False
batch = []
yield batch, True

View File

@@ -1,301 +0,0 @@
# AWS SSO to Prowler Automation Script
## Table of Contents
- [Introduction](#introduction)
- [Prerequisites](#prerequisites)
- [Setup](#setup)
- [Script Overview](#script-overview)
- [Usage](#usage)
- [Troubleshooting](#troubleshooting)
- [Customization](#customization)
- [Security Considerations](#security-considerations)
- [License](#license)
## Introduction
This repository provides a Bash script that automates the process of logging into AWS Single Sign-On (SSO), extracting temporary AWS credentials, and running **Prowler**—a security tool that performs AWS security best practices assessments—inside a Docker container using those credentials.
By following this guide, you can streamline your AWS security assessments, ensuring that you consistently apply best practices across your AWS accounts.
## Prerequisites
Before you begin, ensure that you have the following tools installed and properly configured on your system:
1. **AWS CLI v2**
- AWS SSO support is available from AWS CLI version 2 onwards.
- [Installation Guide](https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2.html)
2. **jq**
- A lightweight and flexible command-line JSON processor.
- **macOS (Homebrew):**
```bash
brew install jq
```
- **Ubuntu/Debian:**
```bash
sudo apt-get update
sudo apt-get install -y jq
```
- **Windows:**
- [Download jq](https://stedolan.github.io/jq/download/)
3. **Docker**
- Ensure Docker is installed and running on your system.
- [Docker Installation Guide](https://docs.docker.com/get-docker/)
4. **AWS SSO Profile Configuration**
- Ensure that you have configured an AWS CLI profile with SSO.
- [Configuring AWS CLI with SSO](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-sso.html)
## Setup
1. **Clone the Repository**
```bash
git clone https://github.com/your-username/aws-sso-prowler-automation.git
cd aws-sso-prowler-automation
```
2. **Create the Automation Script**
Create a new Bash script named `run_prowler_sso.sh` and make it executable.
```bash
nano run_prowler_sso.sh
chmod +x run_prowler_sso.sh
```
3. **Add the Script Content**
Paste the following content into `run_prowler_sso.sh`:
4. **Configure AWS SSO Profile**
Ensure that your AWS CLI profile (`twodragon` in this case) is correctly configured for SSO.
```bash
aws configure sso --profile twodragon
```
**Example Configuration Prompts:**
```
SSO session name (Recommended): [twodragon]
SSO start URL [None]: https://twodragon.awsapps.com/start
SSO region [None]: ap-northeast-2
SSO account ID [None]: 123456789012
SSO role name [None]: ReadOnlyAccess
CLI default client region [None]: ap-northeast-2
CLI default output format [None]: json
CLI profile name [twodragon]: twodragon
```
## Script Overview
The `run_prowler_sso.sh` script performs the following actions:
1. **AWS SSO Login:**
- Initiates AWS SSO login for the specified profile.
- Opens the SSO authorization page in the default browser for user authentication.
2. **Extract Temporary Credentials:**
- Locates the most recent SSO cache file containing the `accessToken`.
- Uses `jq` to parse and extract the `accessToken` from the cache file.
- Retrieves the `sso_role_name` and `sso_account_id` from the AWS CLI configuration.
- Obtains temporary AWS credentials (`AccessKeyId`, `SecretAccessKey`, `SessionToken`) using the extracted `accessToken`.
3. **Set Environment Variables:**
- Exports the extracted AWS credentials as environment variables to be used by the Docker container.
4. **Run Prowler:**
- Executes the **Prowler** Docker container, passing the AWS credentials as environment variables for security assessments.
## Usage
1. **Make the Script Executable**
Ensure the script has execute permissions.
```bash
chmod +x run_prowler_sso.sh
```
2. **Run the Script**
Execute the script to start the AWS SSO login process and run Prowler.
```bash
./run_prowler_sso.sh
```
3. **Follow the Prompts**
- A browser window will open prompting you to authenticate via AWS SSO.
- Complete the authentication process in the browser.
- Upon successful login, the script will extract temporary credentials and run Prowler.
4. **Review Prowler Output**
- Prowler will analyze your AWS environment based on the specified checks and output the results directly in the terminal.
## Troubleshooting
If you encounter issues during the script execution, follow these steps to diagnose and resolve them.
### 1. Verify AWS CLI Version
Ensure you are using AWS CLI version 2 or later.
```bash
aws --version
```
**Expected Output:**
```
aws-cli/2.11.10 Python/3.9.12 Darwin/20.3.0 exe/x86_64 prompt/off
```
If you are not using version 2, [install or update AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2.html).
### 2. Confirm AWS SSO Profile Configuration
Check that the `twodragon` profile is correctly configured.
```bash
aws configure list-profiles
```
**Expected Output:**
```
default
twodragon
```
Review the profile details:
```bash
aws configure get sso_start_url --profile twodragon
aws configure get sso_region --profile twodragon
aws configure get sso_account_id --profile twodragon
aws configure get sso_role_name --profile twodragon
```
Ensure all fields return the correct values.
### 3. Check SSO Cache File
Ensure that the SSO cache file contains a valid `accessToken`.
```bash
cat ~/.aws/sso/cache/*.json
```
**Example Content:**
```json
{
"accessToken": "eyJz93a...k4laUWw",
"expiresAt": "2024-12-22T14:07:55Z",
"clientId": "example-client-id",
"clientSecret": "example-client-secret",
"startUrl": "https://twodragon.awsapps.com/start#"
}
```
If `accessToken` is `null` or missing, retry the AWS SSO login:
```bash
aws sso login --profile twodragon
```
### 4. Validate `jq` Installation
Ensure that `jq` is installed and functioning correctly.
```bash
jq --version
```
**Expected Output:**
```
jq-1.6
```
If `jq` is not installed, install it using the instructions in the [Prerequisites](#prerequisites) section.
### 5. Test Docker Environment Variables
Verify that the Docker container receives the AWS credentials correctly.
```bash
docker run --platform linux/amd64 \
-e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
-e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
-e AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN \
toniblyx/prowler /bin/bash -c 'echo $AWS_ACCESS_KEY_ID; echo $AWS_SECRET_ACCESS_KEY; echo $AWS_SESSION_TOKEN'
```
**Expected Output:**
```
ASIA...
wJalrFEMI/K7MDENG/bPxRfiCY...
IQoJb3JpZ2luX2VjEHwaCXVz...
```
Ensure that none of the environment variables are empty.
### 6. Review Script Output
Run the script with debugging enabled to get detailed output.
1. **Enable Debugging in Script**
Add `set -x` for verbose output.
```bash
#!/bin/bash
set -e
set -x
# ... rest of the script ...
```
2. **Run the Script**
```bash
./run_prowler_sso.sh
```
3. **Analyze Output**
Look for any errors or unexpected values in the output to identify where the script is failing.
## Customization
You can modify the script to suit your specific needs, such as:
- **Changing the AWS Profile Name:**
Update the `PROFILE` variable at the top of the script.
```bash
PROFILE="your-profile-name"
```
- **Adding Prowler Options:**
Pass additional options to Prowler for customized checks or output formats.
```bash
docker run --platform linux/amd64 \
-e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
-e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
-e AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN \
toniblyx/prowler -c check123 -M json
```
## Security Considerations
- **Handle Credentials Securely:**
- Avoid sharing or exposing your AWS credentials.
- Do not include sensitive information in logs or version control.
- **Script Permissions:**
- Ensure the script file has appropriate permissions to prevent unauthorized access.
```bash
chmod 700 run_prowler_sso.sh
```
- **Environment Variables:**
- Be cautious when exporting credentials as environment variables.
- Consider using more secure methods for credential management if necessary.
## License
This project is licensed under the [MIT License](LICENSE).

View File

@@ -1,136 +0,0 @@
#!/bin/bash
set -e
# Set the profile name
PROFILE="twodragon"
# Set the Prowler output directory
OUTPUT_DIR=~/prowler-output
mkdir -p "$OUTPUT_DIR"
# Set the port for the local web server
WEB_SERVER_PORT=8000
# ----------------------------------------------
# Functions
# ----------------------------------------------
# Function to open the HTML report in the default browser
open_report() {
local report_path="$1"
if [[ "$OSTYPE" == "darwin"* ]]; then
open "$report_path"
elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
xdg-open "$report_path"
elif [[ "$OSTYPE" == "msys" ]]; then
start "" "$report_path"
else
echo "Automatic method to open Prowler HTML report is not supported on this OS."
echo "Please open the report manually at: $report_path"
fi
}
# Function to start a simple HTTP server to host the Prowler reports
start_web_server() {
local directory="$1"
local port="$2"
echo "Starting local web server to host Prowler reports at http://localhost:$port"
echo "Press Ctrl+C to stop the web server."
# Change to the output directory
cd "$directory"
# Start the HTTP server in the foreground
# Python 3 is required
python3 -m http.server "$port"
}
# ----------------------------------------------
# Main Script
# ----------------------------------------------
# AWS SSO Login
echo "Logging into AWS SSO..."
aws sso login --profile "$PROFILE"
# Extract temporary credentials
echo "Extracting temporary credentials..."
# Find the most recently modified SSO cache file
CACHE_FILE=$(ls -t ~/.aws/sso/cache/*.json 2>/dev/null | head -n 1)
echo "Cache File: $CACHE_FILE"
if [ -z "$CACHE_FILE" ]; then
echo "SSO cache file not found. Please ensure AWS SSO login was successful."
exit 1
fi
# Extract accessToken using jq
ACCESS_TOKEN=$(jq -r '.accessToken' "$CACHE_FILE")
echo "Access Token: $ACCESS_TOKEN"
if [ -z "$ACCESS_TOKEN" ] || [ "$ACCESS_TOKEN" == "null" ]; then
echo "Unable to extract accessToken. Please check your SSO login and cache file."
exit 1
fi
# Extract role name and account ID from AWS CLI configuration
ROLE_NAME=$(aws configure get sso_role_name --profile "$PROFILE")
ACCOUNT_ID=$(aws configure get sso_account_id --profile "$PROFILE")
echo "Role Name: $ROLE_NAME"
echo "Account ID: $ACCOUNT_ID"
if [ -z "$ROLE_NAME" ] || [ -z "$ACCOUNT_ID" ]; then
echo "Unable to extract sso_role_name or sso_account_id. Please check your profile configuration."
exit 1
fi
# Obtain temporary credentials using AWS SSO
TEMP_CREDS=$(aws sso get-role-credentials \
--role-name "$ROLE_NAME" \
--account-id "$ACCOUNT_ID" \
--access-token "$ACCESS_TOKEN" \
--profile "$PROFILE")
echo "TEMP_CREDS: $TEMP_CREDS"
# Extract credentials from the JSON response
AWS_ACCESS_KEY_ID=$(echo "$TEMP_CREDS" | jq -r '.roleCredentials.accessKeyId')
AWS_SECRET_ACCESS_KEY=$(echo "$TEMP_CREDS" | jq -r '.roleCredentials.secretAccessKey')
AWS_SESSION_TOKEN=$(echo "$TEMP_CREDS" | jq -r '.roleCredentials.sessionToken')
# Verify that all credentials were extracted successfully
if [ -z "$AWS_ACCESS_KEY_ID" ] || [ -z "$AWS_SECRET_ACCESS_KEY" ] || [ -z "$AWS_SESSION_TOKEN" ]; then
echo "Unable to extract temporary credentials."
exit 1
fi
# Export AWS credentials as environment variables
export AWS_ACCESS_KEY_ID
export AWS_SECRET_ACCESS_KEY
export AWS_SESSION_TOKEN
echo "AWS credentials have been set."
# Run Prowler in Docker container
echo "Running Prowler Docker container..."
docker run --platform linux/amd64 \
-e AWS_ACCESS_KEY_ID="$AWS_ACCESS_KEY_ID" \
-e AWS_SECRET_ACCESS_KEY="$AWS_SECRET_ACCESS_KEY" \
-e AWS_SESSION_TOKEN="$AWS_SESSION_TOKEN" \
-v "$OUTPUT_DIR":/home/prowler/output \
toniblyx/prowler -M html -M csv -M json-ocsf --output-directory /home/prowler/output --output-filename prowler-output
echo "Prowler has finished running. Reports are saved in $OUTPUT_DIR."
# Open the HTML report in the default browser
REPORT_PATH="$OUTPUT_DIR/prowler-output.html"
echo "Opening Prowler HTML report..."
open_report "$REPORT_PATH" &
# Start the local web server to host the Prowler dashboard
# This will run in the foreground. To run it in the background, append an ampersand (&) at the end of the command.
start_web_server "$OUTPUT_DIR" "$WEB_SERVER_PORT"

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