Compare commits

..

1 Commits

Author SHA1 Message Date
Pepe Fagoaga 01fd759f2a refactor(deletion): isolate steps to remove blocks 2025-03-20 19:41:54 +01:00
835 changed files with 5807 additions and 40193 deletions
+1 -1
View File
@@ -123,7 +123,7 @@ SENTRY_ENVIRONMENT=local
SENTRY_RELEASE=local
#### Prowler release version ####
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.6.0
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.5.0
# Social login credentials
SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
+46 -47
View File
@@ -9,8 +9,8 @@ updates:
- package-ecosystem: "pip"
directory: "/"
schedule:
interval: "monthly"
open-pull-requests-limit: 25
interval: "daily"
open-pull-requests-limit: 10
target-branch: master
labels:
- "dependencies"
@@ -31,8 +31,8 @@ updates:
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "monthly"
open-pull-requests-limit: 25
interval: "daily"
open-pull-requests-limit: 10
target-branch: master
labels:
- "dependencies"
@@ -53,47 +53,46 @@ updates:
- package-ecosystem: "docker"
directory: "/"
schedule:
interval: "monthly"
open-pull-requests-limit: 25
interval: "weekly"
open-pull-requests-limit: 10
target-branch: master
labels:
- "dependencies"
- "docker"
# Dependabot Updates are temporary disabled - 2025/04/15
# v4.6
# - package-ecosystem: "pip"
# directory: "/"
# schedule:
# interval: "weekly"
# open-pull-requests-limit: 10
# target-branch: v4.6
# labels:
# - "dependencies"
# - "pip"
# - "v4"
- package-ecosystem: "pip"
directory: "/"
schedule:
interval: "weekly"
open-pull-requests-limit: 10
target-branch: v4.6
labels:
- "dependencies"
- "pip"
- "v4"
# - package-ecosystem: "github-actions"
# directory: "/"
# schedule:
# interval: "weekly"
# open-pull-requests-limit: 10
# target-branch: v4.6
# labels:
# - "dependencies"
# - "github_actions"
# - "v4"
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "weekly"
open-pull-requests-limit: 10
target-branch: v4.6
labels:
- "dependencies"
- "github_actions"
- "v4"
# - package-ecosystem: "docker"
# directory: "/"
# schedule:
# interval: "weekly"
# open-pull-requests-limit: 10
# target-branch: v4.6
# labels:
# - "dependencies"
# - "docker"
# - "v4"
- package-ecosystem: "docker"
directory: "/"
schedule:
interval: "weekly"
open-pull-requests-limit: 10
target-branch: v4.6
labels:
- "dependencies"
- "docker"
- "v4"
# Dependabot Updates are temporary disabled - 2025/03/19
# v3
@@ -108,13 +107,13 @@ updates:
# - "pip"
# - "v3"
# - package-ecosystem: "github-actions"
# directory: "/"
# schedule:
# interval: "monthly"
# open-pull-requests-limit: 10
# target-branch: v3
# labels:
# - "dependencies"
# - "github_actions"
# - "v3"
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "monthly"
open-pull-requests-limit: 10
target-branch: v3
labels:
- "dependencies"
- "github_actions"
- "v3"
-1
View File
@@ -16,7 +16,6 @@ Please include a summary of the change and which issue is fixed. List any depend
- [ ] Review if code is being documented following this specification https://github.com/google/styleguide/blob/gh-pages/pyguide.md#38-comments-and-docstrings
- [ ] Review if backport is needed.
- [ ] Review if is needed to change the [Readme.md](https://github.com/prowler-cloud/prowler/blob/master/README.md)
- [ ] Ensure new entries are added to [CHANGELOG.md](https://github.com/prowler-cloud/prowler/blob/master/prowler/CHANGELOG.md), if applicable.
#### API
- [ ] Verify if API specs need to be regenerated.
@@ -81,7 +81,7 @@ jobs:
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.WORKING_DIRECTORY }}
# Set push: false for testing
@@ -94,7 +94,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.WORKING_DIRECTORY }}
push: true
+2 -2
View File
@@ -48,12 +48,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/init@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/api-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/analyze@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
category: "/language:${{matrix.language}}"
+5 -19
View File
@@ -75,7 +75,7 @@ jobs:
- 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@2f7c5bfce28377bc069a65ba478de0a74aa0ca32 # v46.0.1
with:
files: api/**
files_ignore: |
@@ -85,14 +85,6 @@ jobs:
api/README.md
api/mkdocs.yml
- name: Replace @master with current branch in pyproject.toml
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
BRANCH_NAME="${GITHUB_HEAD_REF:-${GITHUB_REF_NAME}}"
echo "Using branch: $BRANCH_NAME"
sed -i "s|@master|@$BRANCH_NAME|g" pyproject.toml
- name: Install poetry
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
@@ -100,15 +92,9 @@ jobs:
python -m pip install --upgrade pip
pipx install poetry==2.1.1
- name: Update poetry.lock after the branch name change
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry lock
- name: Set up Python ${{ matrix.python-version }}
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: ${{ matrix.python-version }}
cache: "poetry"
@@ -159,7 +145,7 @@ jobs:
working-directory: ./api
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
run: |
poetry run safety check --ignore 70612,66963,74429
poetry run safety check --ignore 70612,66963
- name: Vulture
working-directory: ./api
@@ -181,7 +167,7 @@ jobs:
- name: Upload coverage reports to Codecov
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
uses: codecov/codecov-action@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
with:
@@ -193,7 +179,7 @@ jobs:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.API_WORKING_DIR }}
push: false
+1 -1
View File
@@ -11,7 +11,7 @@ jobs:
with:
fetch-depth: 0
- name: TruffleHog OSS
uses: trufflesecurity/trufflehog@b06f6d72a3791308bb7ba59c2b8cb7a083bd17e4 # v3.88.26
uses: trufflesecurity/trufflehog@ded5f45b92c00939718787ce586b520bbe795f3b # v3.88.18
with:
path: ./
base: ${{ github.event.repository.default_branch }}
-34
View File
@@ -1,34 +0,0 @@
name: Prowler - Merged Pull Request
on:
pull_request_target:
branches: ['master']
types: ['closed']
jobs:
trigger-cloud-pull-request:
name: Trigger Cloud Pull Request
if: github.event.pull_request.merged == true && github.repository == 'prowler-cloud/prowler'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set short git commit SHA
id: vars
run: |
shortSha=$(git rev-parse --short ${{ github.sha }})
echo "SHORT_SHA=${shortSha}" >> $GITHUB_ENV
- name: Trigger pull request
uses: peter-evans/repository-dispatch@ff45666b9427631e3450c54a1bcbee4d9ff4d7c0 # v3.0.0
with:
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
repository: ${{ secrets.CLOUD_DISPATCH }}
event-type: prowler-pull-request-merged
client-payload: '{
"PROWLER_COMMIT_SHA": "${{ github.sha }}",
"PROWLER_COMMIT_SHORT_SHA": "${{ env.SHORT_SHA }}",
"PROWLER_PR_TITLE": "${{ github.event.pull_request.title }}",
"PROWLER_PR_LABELS": ${{ toJson(github.event.pull_request.labels.*.name) }},
"PROWLER_PR_BODY": ${{ toJson(github.event.pull_request.body) }}
}'
@@ -62,13 +62,13 @@ jobs:
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Setup Python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: ${{ env.PYTHON_VERSION }}
- name: Install Poetry
run: |
pipx install poetry==2.*
pipx install poetry==1.8.5
pipx inject poetry poetry-bumpversion
- name: Get Prowler version
@@ -127,7 +127,7 @@ jobs:
- name: Build and push container image (latest)
if: github.event_name == 'push'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
push: true
tags: |
@@ -140,7 +140,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
# Use local context to get changes
# https://github.com/docker/build-push-action#path-context
-94
View File
@@ -1,94 +0,0 @@
name: SDK - Bump Version
on:
release:
types: [published]
env:
PROWLER_VERSION: ${{ github.event.release.tag_name }}
BASE_BRANCH: master
jobs:
bump-version:
name: Bump Version
if: github.repository == 'prowler-cloud/prowler'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Get Prowler version
shell: bash
run: |
if [[ $PROWLER_VERSION =~ ^([0-9]+)\.([0-9]+)\.([0-9]+)$ ]]; then
MAJOR_VERSION=${BASH_REMATCH[1]}
MINOR_VERSION=${BASH_REMATCH[2]}
FIX_VERSION=${BASH_REMATCH[3]}
if (( MAJOR_VERSION == 5 )); then
if (( FIX_VERSION == 0 )); then
echo "Minor Release: $PROWLER_VERSION"
BUMP_VERSION_TO=${MAJOR_VERSION}.$((MINOR_VERSION + 1)).${FIX_VERSION}
echo "BUMP_VERSION_TO=${BUMP_VERSION_TO}" >> "${GITHUB_ENV}"
TARGET_BRANCH=${BASE_BRANCH}
echo "TARGET_BRANCH=${TARGET_BRANCH}" >> "${GITHUB_ENV}"
echo "Bumping to next minor version: ${BUMP_VERSION_TO} in branch ${TARGET_BRANCH}"
else
echo "Patch Release: $PROWLER_VERSION"
BUMP_VERSION_TO=${MAJOR_VERSION}.${MINOR_VERSION}.$((FIX_VERSION + 1))
echo "BUMP_VERSION_TO=${BUMP_VERSION_TO}" >> "${GITHUB_ENV}"
TARGET_BRANCH=v${MAJOR_VERSION}.${MINOR_VERSION}
echo "TARGET_BRANCH=${TARGET_BRANCH}" >> "${GITHUB_ENV}"
echo "Bumping to next patch version: ${BUMP_VERSION_TO} in branch ${TARGET_BRANCH}"
fi
else
echo "Releasing another Prowler major version, aborting..."
exit 1
fi
else
echo "Invalid version syntax: '$PROWLER_VERSION' (must be N.N.N)" >&2
exit 1
fi
- name: Bump versions in files
run: |
echo "Using PROWLER_VERSION=$PROWLER_VERSION"
echo "Using BUMP_VERSION_TO=$BUMP_VERSION_TO"
set -e
echo "Bumping version in pyproject.toml ..."
sed -i "s|version = \"${PROWLER_VERSION}\"|version = \"${BUMP_VERSION_TO}\"|" pyproject.toml
echo "Bumping version in prowler/config/config.py ..."
sed -i "s|prowler_version = \"${PROWLER_VERSION}\"|prowler_version = \"${BUMP_VERSION_TO}\"|" prowler/config/config.py
echo "Bumping version in .env ..."
sed -i "s|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${PROWLER_VERSION}|NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v${BUMP_VERSION_TO}|" .env
git --no-pager diff
- name: Create Pull Request
uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
with:
author: prowler-bot <179230569+prowler-bot@users.noreply.github.com>
token: ${{ secrets.PROWLER_BOT_ACCESS_TOKEN }}
base: ${{ env.TARGET_BRANCH }}
commit-message: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
branch: "version-bump-to-v${{ env.BUMP_VERSION_TO }}"
title: "chore(release): Bump version to v${{ env.BUMP_VERSION_TO }}"
body: |
### Description
Bump Prowler version to v${{ env.BUMP_VERSION_TO }}
### License
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
+2 -4
View File
@@ -21,7 +21,6 @@ on:
paths-ignore:
- 'ui/**'
- 'api/**'
- '.github/**'
pull_request:
branches:
- "master"
@@ -31,7 +30,6 @@ on:
paths-ignore:
- 'ui/**'
- 'api/**'
- '.github/**'
schedule:
- cron: '00 12 * * *'
@@ -56,12 +54,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/init@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/sdk-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/analyze@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
category: "/language:${{matrix.language}}"
+5 -104
View File
@@ -25,7 +25,7 @@ jobs:
- 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@2f7c5bfce28377bc069a65ba478de0a74aa0ca32 # v46.0.1
with:
files: ./**
files_ignore: |
@@ -34,7 +34,6 @@ jobs:
permissions/**
api/**
ui/**
prowler/CHANGELOG.md
README.md
mkdocs.yml
.backportrc.json
@@ -51,7 +50,7 @@ jobs:
- name: Set up Python ${{ matrix.python-version }}
if: steps.are-non-ignored-files-changed.outputs.any_changed == 'true'
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: ${{ matrix.python-version }}
cache: "poetry"
@@ -107,113 +106,15 @@ 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/**
.poetry.lock
- name: AWS - Test
if: steps.aws-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/aws --cov-report=xml:aws_coverage.xml tests/providers/aws
# Test Azure
- name: Azure - Check if any file has changed
id: azure-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/azure/**
./tests/providers/azure/**
.poetry.lock
- name: Azure - Test
if: steps.azure-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/azure --cov-report=xml:azure_coverage.xml tests/providers/azure
# Test GCP
- name: GCP - Check if any file has changed
id: gcp-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/gcp/**
./tests/providers/gcp/**
.poetry.lock
- name: GCP - Test
if: steps.gcp-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/gcp --cov-report=xml:gcp_coverage.xml tests/providers/gcp
# Test Kubernetes
- name: Kubernetes - Check if any file has changed
id: kubernetes-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/kubernetes/**
./tests/providers/kubernetes/**
.poetry.lock
- name: Kubernetes - Test
if: steps.kubernetes-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/kubernetes --cov-report=xml:kubernetes_coverage.xml tests/providers/kubernetes
# Test NHN
- name: NHN - Check if any file has changed
id: nhn-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/nhn/**
./tests/providers/nhn/**
.poetry.lock
- name: NHN - Test
if: steps.nhn-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/nhn --cov-report=xml:nhn_coverage.xml tests/providers/nhn
# Test M365
- name: M365 - Check if any file has changed
id: m365-changed-files
uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
with:
files: |
./prowler/providers/m365/**
./tests/providers/m365/**
.poetry.lock
- name: M365 - Test
if: steps.m365-changed-files.outputs.any_changed == 'true'
run: |
poetry run pytest -n auto --cov=./prowler/providers/m365 --cov-report=xml:m365_coverage.xml tests/providers/m365
# Common Tests
- name: Lib - Test
- 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@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
uses: codecov/codecov-action@0565863a31f2c772f9f0395002a31e3f06189574 # v5.4.0
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
+4 -4
View File
@@ -7,7 +7,7 @@ on:
env:
RELEASE_TAG: ${{ github.event.release.tag_name }}
PYTHON_VERSION: 3.11
# CACHE: "poetry"
CACHE: "poetry"
jobs:
repository-check:
@@ -68,13 +68,13 @@ jobs:
- name: Install dependencies
run: |
pipx install poetry==2.1.1
pipx install poetry==1.8.5
- name: Setup Python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: ${{ env.PYTHON_VERSION }}
# cache: ${{ env.CACHE }}
cache: ${{ env.CACHE }}
- name: Build Prowler package
run: |
@@ -4,7 +4,7 @@ name: SDK - Refresh AWS services' regions
on:
schedule:
- cron: "0 9 * * 1" # runs at 09:00 UTC every Monday
- cron: "0 9 * * *" #runs at 09:00 UTC everyday
env:
GITHUB_BRANCH: "master"
@@ -28,7 +28,7 @@ jobs:
ref: ${{ env.GITHUB_BRANCH }}
- name: setup python
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: 3.9 #install the python needed
@@ -81,7 +81,7 @@ jobs:
- name: Build and push container image (latest)
# Comment the following line for testing
if: github.event_name == 'push'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
@@ -96,7 +96,7 @@ jobs:
- name: Build and push container image (release)
if: github.event_name == 'release'
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.WORKING_DIRECTORY }}
build-args: |
+2 -2
View File
@@ -48,12 +48,12 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/init@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
languages: ${{ matrix.language }}
config-file: ./.github/codeql/ui-codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@28deaeda66b76a05916b6923827895f2b14ab387 # v3.28.16
uses: github/codeql-action/analyze@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
with:
category: "/language:${{matrix.language}}"
-80
View File
@@ -1,80 +0,0 @@
name: UI - E2E Tests
on:
pull_request:
branches:
- master
- "v5.*"
paths:
- 'ui/**'
env:
SERVICES_TO_START: "api-dev postgres valkey worker-beat worker-dev"
DOCKER_COMPOSE_FILE: "docker-compose-dev.yml"
jobs:
e2e:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Node.js
uses: actions/setup-node@v4
with:
node-version: 20
cache: 'npm'
cache-dependency-path: './ui/package-lock.json'
# - name: Cache Playwright Browsers
# uses: actions/cache@v4
# with:
# path: ~/.cache/ms-playwright
# key: playwright-${{ runner.os }}-${{ hashFiles('**/package-lock.json') }}
# restore-keys: |
# playwright-${{ runner.os }}-
- name: Install dependencies
run: npm ci
working-directory: ./ui
- name: Install Playwright Browsers
run: npx playwright install --with-deps
working-directory: ./ui
- name: Set up Docker Compose
uses: docker/setup-compose-action@364cc21a5de5b1ee4a7f5f9d3fa374ce0ccde746 #v1.2.0
- name: Start Docker Compose
run: docker compose -f ${DOCKER_COMPOSE_FILE} up -d ${SERVICES_TO_START}
- name: Wait for API to be ready
run: |
for i in {1..30}; do
if curl -s http://localhost:8000/api/v1; then
echo "API is up!"
break
fi
echo "Waiting for API..."
sleep 5
done
- name: Run Playwright tests
run: npx playwright test
working-directory: ./ui
- name: Upload Playwright report
uses: actions/upload-artifact@v4
with:
name: playwright-report
path: ./ui/playwright-report
- name: Upload Playwright videos
uses: actions/upload-artifact@v4
with:
name: test-videos
path: ./ui/test-results/**/*.webm
- name: Docker Compose Down
if: always()
run: docker compose -f ${DOCKER_COMPOSE_FILE} down
+2 -2
View File
@@ -31,7 +31,7 @@ jobs:
with:
persist-credentials: false
- name: Setup Node.js ${{ matrix.node-version }}
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
uses: actions/setup-node@cdca7365b2dadb8aad0a33bc7601856ffabcc48e # v4.3.0
with:
node-version: ${{ matrix.node-version }}
- name: Install dependencies
@@ -50,7 +50,7 @@ jobs:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Build Container
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: ${{ env.UI_WORKING_DIR }}
# Always build using `prod` target
-11
View File
@@ -42,10 +42,6 @@ junit-reports/
# VSCode files
.vscode/
# Cursor files
.cursorignore
.cursor/
# Terraform
.terraform*
*.tfstate
@@ -66,10 +62,3 @@ node_modules
# Persistent data
_data/
# Playwright
node_modules/
/test-results/
/playwright-report/
/blob-report/
/playwright/.cache/
+1 -1
View File
@@ -115,7 +115,7 @@ repos:
- id: safety
name: safety
description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
entry: bash -c 'safety check --ignore 70612,66963,74429'
entry: bash -c 'safety check --ignore 70612,66963'
language: system
- id: vulture
+10 -32
View File
@@ -1,43 +1,24 @@
FROM python:3.12.10-slim-bookworm AS build
FROM python:3.12.9-alpine3.20
LABEL maintainer="https://github.com/prowler-cloud/prowler"
LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
ARG POWERSHELL_VERSION=7.5.0
# hadolint ignore=DL3008
RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
&& rm -rf /var/lib/apt/lists/*
# Install PowerShell
RUN ARCH=$(uname -m) && \
if [ "$ARCH" = "x86_64" ]; then \
wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-x64.tar.gz -O /tmp/powershell.tar.gz ; \
elif [ "$ARCH" = "aarch64" ]; then \
wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-arm64.tar.gz -O /tmp/powershell.tar.gz ; \
else \
echo "Unsupported architecture: $ARCH" && exit 1 ; \
fi && \
mkdir -p /opt/microsoft/powershell/7 && \
tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7 && \
chmod +x /opt/microsoft/powershell/7/pwsh && \
ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh && \
rm /tmp/powershell.tar.gz
# Add prowler user
RUN addgroup --gid 1000 prowler && \
adduser --uid 1000 --gid 1000 --disabled-password --gecos "" prowler
# 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
# Create non-root user
RUN mkdir -p /home/prowler && \
echo 'prowler:x:1000:1000:prowler:/home/prowler:' > /etc/passwd && \
echo 'prowler:x:1000:' > /etc/group && \
chown -R prowler:prowler /home/prowler
USER prowler
WORKDIR /home/prowler
# Copy necessary files
WORKDIR /home/prowler
COPY prowler/ /home/prowler/prowler/
COPY dashboard/ /home/prowler/dashboard/
COPY pyproject.toml /home/prowler
COPY README.md /home/prowler/
COPY prowler/providers/m365/lib/powershell/m365_powershell.py /home/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py
# Install Python dependencies
ENV HOME='/home/prowler'
@@ -53,9 +34,6 @@ RUN pip install --no-cache-dir --upgrade pip && \
RUN poetry install --compile && \
rm -rf ~/.cache/pip
# Install PowerShell modules
RUN poetry run python prowler/providers/m365/lib/powershell/m365_powershell.py
# Remove deprecated dash dependencies
RUN pip uninstall dash-html-components -y && \
pip uninstall dash-core-components -y
+3 -4
View File
@@ -72,11 +72,10 @@ 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 | 79 | 13 | 7 | 3 |
| Azure | 140 | 18 | 8 | 3 |
| GCP | 77 | 13 | 6 | 3 |
| Azure | 140 | 18 | 7 | 3 |
| Kubernetes | 83 | 7 | 4 | 7 |
| M365 | 44 | 2 | 1 | 0 |
| NHN (Unofficial) | 6 | 2 | 1 | 0 |
| Microsoft365 | 5 | 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`.
-3
View File
@@ -53,6 +53,3 @@ 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
+1 -1
View File
@@ -80,7 +80,7 @@ repos:
- id: safety
name: safety
description: "Safety is a tool that checks your installed dependencies for known security vulnerabilities"
entry: bash -c 'poetry run safety check --ignore 70612,66963,74429'
entry: bash -c 'poetry run safety check --ignore 70612,66963'
language: system
- id: vulture
+1 -35
View File
@@ -2,48 +2,14 @@
All notable changes to the **Prowler API** are documented in this file.
## [v1.7.0] (Prowler v5.6.0)
### Added
- Added M365 as a new provider [(#7563)](https://github.com/prowler-cloud/prowler/pull/7563).
- Added a `compliance/` folder and ZIPexport functionality for all compliance reports.[(#7653)](https://github.com/prowler-cloud/prowler/pull/7653).
- Added a new API endpoint to fetch and download any specific compliance file by name [(#7653)](https://github.com/prowler-cloud/prowler/pull/7653).
---
## [v1.6.0] (Prowler v5.5.0)
## [v1.6.0] (Prowler UNRELEASED)
### 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).
---
+14 -29
View File
@@ -1,33 +1,13 @@
FROM python:3.12.10-slim-bookworm AS build
FROM python:3.12.8-alpine3.20 AS build
LABEL maintainer="https://github.com/prowler-cloud/api"
ARG POWERSHELL_VERSION=7.5.0
ENV POWERSHELL_VERSION=${POWERSHELL_VERSION}
# hadolint ignore=DL3008
RUN apt-get update && apt-get install -y --no-install-recommends wget libicu72 \
&& rm -rf /var/lib/apt/lists/*
# Install PowerShell
RUN ARCH=$(uname -m) && \
if [ "$ARCH" = "x86_64" ]; then \
wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-x64.tar.gz -O /tmp/powershell.tar.gz ; \
elif [ "$ARCH" = "aarch64" ]; then \
wget --progress=dot:giga https://github.com/PowerShell/PowerShell/releases/download/v${POWERSHELL_VERSION}/powershell-${POWERSHELL_VERSION}-linux-arm64.tar.gz -O /tmp/powershell.tar.gz ; \
else \
echo "Unsupported architecture: $ARCH" && exit 1 ; \
fi && \
mkdir -p /opt/microsoft/powershell/7 && \
tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7 && \
chmod +x /opt/microsoft/powershell/7/pwsh && \
ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh && \
rm /tmp/powershell.tar.gz
# Add prowler user
RUN addgroup --gid 1000 prowler && \
adduser --uid 1000 --gid 1000 --disabled-password --gecos "" prowler
# hadolint ignore=DL3018
RUN apk --no-cache add gcc python3-dev musl-dev linux-headers curl-dev
RUN apk --no-cache upgrade && \
addgroup -g 1000 prowler && \
adduser -D -u 1000 -G prowler prowler
USER prowler
WORKDIR /home/prowler
@@ -37,7 +17,7 @@ COPY pyproject.toml ./
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir poetry
COPY src/backend/ ./backend/
COPY src/backend/ ./backend/
ENV PATH="/home/prowler/.local/bin:$PATH"
@@ -47,13 +27,18 @@ RUN poetry install --no-root && \
COPY docker-entrypoint.sh ./docker-entrypoint.sh
RUN poetry run python "$(poetry env info --path)/src/prowler/prowler/providers/m365/lib/powershell/m365_powershell.py"
WORKDIR /home/prowler/backend
# Development image
# hadolint ignore=DL3006
FROM build AS dev
USER 0
# hadolint ignore=DL3018
RUN apk --no-cache add curl vim
USER prowler
ENTRYPOINT ["../docker-entrypoint.sh", "dev"]
# Production image
-1
View File
@@ -235,7 +235,6 @@ To view the logs for any component (e.g., Django, Celery worker), you can use th
```console
docker logs -f $(docker ps --format "{{.Names}}" | grep 'api-')
```
## Applying migrations
+914 -969
View File
File diff suppressed because it is too large Load Diff
+2 -4
View File
@@ -7,8 +7,7 @@ authors = [{name = "Prowler Engineering", email = "engineering@prowler.com"}]
dependencies = [
"celery[pytest] (>=5.4.0,<6.0.0)",
"dj-rest-auth[with_social,jwt] (==7.0.1)",
"django==5.1.8",
"django-allauth==65.4.1",
"django==5.1.7",
"django-celery-beat (>=2.7.0,<3.0.0)",
"django-celery-results (>=2.5.1,<3.0.0)",
"django-cors-headers==4.4.0",
@@ -35,7 +34,7 @@ name = "prowler-api"
package-mode = false
# Needed for the SDK compatibility
requires-python = ">=3.11,<3.13"
version = "1.7.0"
version = "1.6.0"
[project.scripts]
celery = "src.backend.config.settings.celery"
@@ -46,7 +45,6 @@ coverage = "7.5.4"
django-silk = "5.3.2"
docker = "7.1.0"
freezegun = "1.5.1"
marshmallow = ">=3.15.0,<4.0.0"
mypy = "1.10.1"
pylint = "3.2.5"
pytest = "8.2.2"
+2 -28
View File
@@ -1,38 +1,12 @@
from types import MappingProxyType
from api.models import Provider
from prowler.config.config import get_available_compliance_frameworks
from prowler.lib.check.compliance_models import Compliance
from prowler.lib.check.models import CheckMetadata
from api.models import Provider
PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE = {}
PROWLER_CHECKS = {}
AVAILABLE_COMPLIANCE_FRAMEWORKS = {}
def get_compliance_frameworks(provider_type: Provider.ProviderChoices) -> list[str]:
"""
Retrieve and cache the list of available compliance frameworks for a specific cloud provider.
This function lazily loads and caches the available compliance frameworks (e.g., CIS, MITRE, ISO)
for each provider type (AWS, Azure, GCP, etc.) on first access. Subsequent calls for the same
provider will return the cached result.
Args:
provider_type (Provider.ProviderChoices): The cloud provider type for which to retrieve
available compliance frameworks (e.g., "aws", "azure", "gcp", "m365").
Returns:
list[str]: A list of framework identifiers (e.g., "cis_1.4_aws", "mitre_attack_azure") available
for the given provider.
"""
global AVAILABLE_COMPLIANCE_FRAMEWORKS
if provider_type not in AVAILABLE_COMPLIANCE_FRAMEWORKS:
AVAILABLE_COMPLIANCE_FRAMEWORKS[provider_type] = (
get_available_compliance_frameworks(provider_type)
)
return AVAILABLE_COMPLIANCE_FRAMEWORKS[provider_type]
def get_prowler_provider_checks(provider_type: Provider.ProviderChoices):
+9 -24
View File
@@ -6,7 +6,6 @@ from datetime import datetime, timedelta, timezone
from django.conf import settings
from django.contrib.auth.models import BaseUserManager
from django.db import connection, models, transaction
from django_celery_beat.models import PeriodicTask
from psycopg2 import connect as psycopg2_connect
from psycopg2.extensions import AsIs, new_type, register_adapter, register_type
from rest_framework_json_api.serializers import ValidationError
@@ -106,12 +105,11 @@ 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.
@@ -122,16 +120,15 @@ def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_
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
# Get a batch of IDs to delete
batch_ids = set(
queryset.values_list("id", flat=True).order_by("id")[:batch_size]
)
if not batch_ids:
# No more objects to delete
break
deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
deleted_count, deleted_info = queryset.filter(id__in=batch_ids).delete()
total_deleted += deleted_count
for model_label, count in deleted_info.items():
@@ -140,18 +137,6 @@ def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_
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
+8 -3
View File
@@ -287,9 +287,6 @@ 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")
@@ -617,6 +614,12 @@ 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
@@ -627,6 +630,8 @@ class ScanSummaryFilter(FilterSet):
class ServiceOverviewFilter(ScanSummaryFilter):
muted_findings = None
def is_valid(self):
# Check if at least one of the inserted_at filters is present
inserted_at_filters = [
@@ -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")]
),
),
]
@@ -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),
),
]
@@ -1,32 +0,0 @@
# Generated by Django 5.1.7 on 2025-04-16 08:47
from django.db import migrations
import api.db_utils
class Migration(migrations.Migration):
dependencies = [
("api", "0016_finding_compliance_resource_details_and_more"),
]
operations = [
migrations.AlterField(
model_name="provider",
name="provider",
field=api.db_utils.ProviderEnumField(
choices=[
("aws", "AWS"),
("azure", "Azure"),
("gcp", "GCP"),
("kubernetes", "Kubernetes"),
("m365", "M365"),
],
default="aws",
),
),
migrations.RunSQL(
"ALTER TYPE provider ADD VALUE IF NOT EXISTS 'm365';",
reverse_sql=migrations.RunSQL.noop,
),
]
+1 -17
View File
@@ -59,6 +59,7 @@ class StatusChoices(models.TextChoices):
FAIL = "FAIL", _("Fail")
PASS = "PASS", _("Pass")
MANUAL = "MANUAL", _("Manual")
MUTED = "MUTED", _("Muted")
class StateChoices(models.TextChoices):
@@ -191,7 +192,6 @@ class Provider(RowLevelSecurityProtectedModel):
AZURE = "azure", _("Azure")
GCP = "gcp", _("GCP")
KUBERNETES = "kubernetes", _("Kubernetes")
M365 = "m365", _("M365")
@staticmethod
def validate_aws_uid(value):
@@ -215,15 +215,6 @@ class Provider(RowLevelSecurityProtectedModel):
pointer="/data/attributes/uid",
)
@staticmethod
def validate_m365_uid(value):
if not re.match(r"^[a-zA-Z0-9-]+\.onmicrosoft\.com$", value):
raise ModelValidationError(
detail="M365 tenant ID must be a valid domain.",
code="m365-uid",
pointer="/data/attributes/uid",
)
@staticmethod
def validate_gcp_uid(value):
if not re.match(r"^[a-z][a-z0-9-]{5,29}$", value):
@@ -528,11 +519,6 @@ 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",
@@ -670,8 +656,6 @@ 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)
+4 -3
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()
+17 -320
View File
@@ -1,7 +1,7 @@
openapi: 3.0.3
info:
title: Prowler API
version: 1.7.0
version: 1.6.0
description: |-
Prowler API specification.
@@ -83,13 +83,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -101,7 +99,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -109,7 +106,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -237,42 +233,6 @@ paths:
schema:
$ref: '#/components/schemas/ComplianceOverviewFullResponse'
description: ''
/api/v1/compliance-overviews/metadata:
get:
operationId: compliance_overviews_metadata_retrieve
description: Fetch unique metadata values from a set of compliance overviews.
This is useful for dynamic filtering.
summary: Retrieve metadata values from compliance overviews
parameters:
- in: query
name: fields[compliance-overviews-metadata]
schema:
type: array
items:
type: string
enum:
- regions
description: endpoint return only specific fields in the response on a per-type
basis by including a fields[TYPE] query parameter.
explode: false
- in: query
name: filter[scan_id]
schema:
type: string
format: uuid
description: Related scan ID.
required: true
tags:
- Compliance Overview
security:
- jwtAuth: []
responses:
'200':
content:
application/vnd.api+json:
schema:
$ref: '#/components/schemas/ComplianceOverviewMetadataResponse'
description: ''
/api/v1/findings:
get:
operationId: findings_list
@@ -298,7 +258,6 @@ paths:
- inserted_at
- updated_at
- first_seen_at
- muted
- url
- scan
- resources
@@ -407,12 +366,6 @@ paths:
type: string
format: date
description: Maximum date range is 7 days.
- in: query
name: filter[muted]
schema:
type: boolean
description: If this filter is not provided, muted and non-muted findings
will be returned.
- in: query
name: filter[provider]
schema:
@@ -454,13 +407,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -472,7 +423,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -480,7 +430,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -648,11 +597,13 @@ paths:
enum:
- FAIL
- MANUAL
- MUTED
- PASS
description: |-
* `FAIL` - Fail
* `PASS` - Pass
* `MANUAL` - Manual
* `MUTED` - Muted
- in: query
name: filter[status__in]
schema:
@@ -769,7 +720,6 @@ paths:
- inserted_at
- updated_at
- first_seen_at
- muted
- url
- scan
- resources
@@ -923,12 +873,6 @@ paths:
type: string
format: date
description: Maximum date range is 7 days.
- in: query
name: filter[muted]
schema:
type: boolean
description: If this filter is not provided, muted and non-muted findings
will be returned.
- in: query
name: filter[provider]
schema:
@@ -970,13 +914,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -988,7 +930,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -996,7 +937,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -1164,11 +1104,13 @@ paths:
enum:
- FAIL
- MANUAL
- MUTED
- PASS
description: |-
* `FAIL` - Fail
* `PASS` - Pass
* `MANUAL` - Manual
* `MUTED` - Muted
- in: query
name: filter[status__in]
schema:
@@ -1360,12 +1302,6 @@ paths:
type: string
format: date
description: Maximum date range is 7 days.
- in: query
name: filter[muted]
schema:
type: boolean
description: If this filter is not provided, muted and non-muted findings
will be returned.
- in: query
name: filter[provider]
schema:
@@ -1407,13 +1343,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -1425,7 +1359,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -1433,7 +1366,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -1601,11 +1533,13 @@ paths:
enum:
- FAIL
- MANUAL
- MUTED
- PASS
description: |-
* `FAIL` - Fail
* `PASS` - Pass
* `MANUAL` - Manual
* `MUTED` - Muted
- in: query
name: filter[status__in]
schema:
@@ -2049,6 +1983,10 @@ paths:
schema:
type: string
format: date-time
- in: query
name: filter[muted_findings]
schema:
type: boolean
- in: query
name: filter[provider_id]
schema:
@@ -2063,13 +2001,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -2081,7 +2017,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -2089,7 +2024,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -2210,6 +2144,10 @@ paths:
schema:
type: string
format: date-time
- in: query
name: filter[muted_findings]
schema:
type: boolean
- in: query
name: filter[provider_id]
schema:
@@ -2224,13 +2162,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -2242,7 +2178,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -2250,7 +2185,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -2401,13 +2335,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -2419,7 +2351,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -2427,7 +2358,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -2891,13 +2821,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider__in]
schema:
@@ -3471,13 +3399,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -3489,7 +3415,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -3497,7 +3422,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -3750,7 +3674,6 @@ paths:
- name
- manage_users
- manage_account
- manage_integrations
- manage_providers
- manage_scans
- permission_state
@@ -3869,8 +3792,6 @@ paths:
- -manage_users
- manage_account
- -manage_account
- manage_integrations
- -manage_integrations
- manage_providers
- -manage_providers
- manage_scans
@@ -3946,7 +3867,6 @@ paths:
- name
- manage_users
- manage_account
- manage_integrations
- manage_providers
- manage_scans
- permission_state
@@ -4201,13 +4121,11 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
- in: query
name: filter[provider_type__in]
schema:
@@ -4219,7 +4137,6 @@ paths:
- azure
- gcp
- kubernetes
- m365
description: |-
Multiple values may be separated by commas.
@@ -4227,7 +4144,6 @@ paths:
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
explode: false
style: form
- in: query
@@ -4320,17 +4236,6 @@ paths:
description: |-
* `scheduled` - Scheduled
* `manual` - Manual
- in: query
name: include
schema:
type: array
items:
type: string
enum:
- provider
description: include query parameter to allow the client to customize which
related resources should be returned.
explode: false
- name: page[number]
required: false
in: query
@@ -4445,17 +4350,6 @@ paths:
format: uuid
description: A UUID string identifying this scan.
required: true
- in: query
name: include
schema:
type: array
items:
type: string
enum:
- provider
description: include query parameter to allow the client to customize which
related resources should be returned.
explode: false
tags:
- Scan
security:
@@ -4503,47 +4397,6 @@ paths:
schema:
$ref: '#/components/schemas/ScanUpdateResponse'
description: ''
/api/v1/scans/{id}/compliance/{name}:
get:
operationId: scan_compliance_download
description: Download a specific compliance report (e.g., 'cis_1.4_aws') as
a CSV file.
summary: Retrieve compliance report as CSV
parameters:
- in: query
name: fields[scan-reports]
schema:
type: array
items:
type: string
enum:
- id
- name
description: endpoint return only specific fields in the response on a per-type
basis by including a fields[TYPE] query parameter.
explode: false
- in: path
name: id
schema:
type: string
format: uuid
description: A UUID string identifying this scan.
required: true
- in: path
name: name
schema:
type: string
description: The compliance report name, like 'cis_1.4_aws'
required: true
tags:
- Scan
security:
- jwtAuth: []
responses:
'200':
description: CSV file containing the compliance report
'404':
description: Compliance report not found
/api/v1/scans/{id}/report:
get:
operationId: scans_report_retrieve
@@ -6252,40 +6105,6 @@ components:
$ref: '#/components/schemas/ComplianceOverviewFull'
required:
- data
ComplianceOverviewMetadata:
type: object
required:
- type
- id
additionalProperties: false
properties:
type:
allOf:
- $ref: '#/components/schemas/ComplianceOverviewMetadataTypeEnum'
description: The [type](https://jsonapi.org/format/#document-resource-object-identification)
member is used to describe resource objects that share common attributes
and relationships.
id: {}
attributes:
type: object
properties:
regions:
type: array
items:
type: string
required:
- regions
ComplianceOverviewMetadataResponse:
type: object
properties:
data:
$ref: '#/components/schemas/ComplianceOverviewMetadata'
required:
- data
ComplianceOverviewMetadataTypeEnum:
type: string
enum:
- compliance-overviews-metadata
Finding:
type: object
required:
@@ -6323,11 +6142,13 @@ components:
- FAIL
- PASS
- MANUAL
- MUTED
type: string
description: |-
* `FAIL` - Fail
* `PASS` - Pass
* `MANUAL` - Manual
* `MUTED` - Muted
status_extended:
type: string
nullable: true
@@ -6363,8 +6184,6 @@ components:
format: date-time
readOnly: true
nullable: true
muted:
type: boolean
required:
- uid
- status
@@ -8426,33 +8245,6 @@ components:
- client_id
- client_secret
- tenant_id
- type: object
title: M365 Static Credentials
properties:
client_id:
type: string
description: The Azure application (client) ID for authentication
in Azure AD.
client_secret:
type: string
description: The client secret associated with the application
(client) ID, providing secure access.
tenant_id:
type: string
description: The Azure tenant ID, representing the directory
where the application is registered.
user:
type: email
description: User microsoft email address.
encrypted_password:
type: string
description: User encrypted password.
required:
- client_id
- client_secret
- tenant_id
- user
- encrypted_password
- type: object
title: GCP Static Credentials
properties:
@@ -8606,8 +8398,6 @@ components:
type: boolean
manage_account:
type: boolean
manage_integrations:
type: boolean
manage_providers:
type: boolean
manage_scans:
@@ -8920,14 +8710,12 @@ components:
- azure
- gcp
- kubernetes
- m365
type: string
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
uid:
type: string
title: Unique identifier for the provider, set by the provider
@@ -9034,14 +8822,12 @@ components:
- azure
- gcp
- kubernetes
- m365
type: string
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
uid:
type: string
title: Unique identifier for the provider, set by the provider
@@ -9079,14 +8865,12 @@ components:
- azure
- gcp
- kubernetes
- m365
type: string
description: |-
* `aws` - AWS
* `azure` - Azure
* `gcp` - GCP
* `kubernetes` - Kubernetes
* `m365` - M365
uid:
type: string
minLength: 3
@@ -9671,33 +9455,6 @@ components:
- client_id
- client_secret
- tenant_id
- type: object
title: M365 Static Credentials
properties:
client_id:
type: string
description: The Azure application (client) ID for authentication
in Azure AD.
client_secret:
type: string
description: The client secret associated with the application
(client) ID, providing secure access.
tenant_id:
type: string
description: The Azure tenant ID, representing the directory where
the application is registered.
user:
type: email
description: User microsoft email address.
encrypted_password:
type: string
description: User encrypted password.
required:
- client_id
- client_secret
- tenant_id
- user
- encrypted_password
- type: object
title: GCP Static Credentials
properties:
@@ -9880,33 +9637,6 @@ components:
- client_id
- client_secret
- tenant_id
- type: object
title: M365 Static Credentials
properties:
client_id:
type: string
description: The Azure application (client) ID for authentication
in Azure AD.
client_secret:
type: string
description: The client secret associated with the application
(client) ID, providing secure access.
tenant_id:
type: string
description: The Azure tenant ID, representing the directory
where the application is registered.
user:
type: email
description: User microsoft email address.
encrypted_password:
type: string
description: User encrypted password.
required:
- client_id
- client_secret
- tenant_id
- user
- encrypted_password
- type: object
title: GCP Static Credentials
properties:
@@ -10105,33 +9835,6 @@ components:
- client_id
- client_secret
- tenant_id
- type: object
title: M365 Static Credentials
properties:
client_id:
type: string
description: The Azure application (client) ID for authentication
in Azure AD.
client_secret:
type: string
description: The client secret associated with the application
(client) ID, providing secure access.
tenant_id:
type: string
description: The Azure tenant ID, representing the directory where
the application is registered.
user:
type: email
description: User microsoft email address.
encrypted_password:
type: string
description: User encrypted password.
required:
- client_id
- client_secret
- tenant_id
- user
- encrypted_password
- type: object
title: GCP Static Credentials
properties:
@@ -10347,8 +10050,6 @@ components:
type: boolean
manage_account:
type: boolean
manage_integrations:
type: boolean
manage_providers:
type: boolean
manage_scans:
@@ -10478,8 +10179,6 @@ components:
type: boolean
manage_account:
type: boolean
manage_integrations:
type: boolean
manage_providers:
type: boolean
manage_scans:
@@ -10614,8 +10313,6 @@ components:
type: boolean
manage_account:
type: boolean
manage_integrations:
type: boolean
manage_providers:
type: boolean
manage_scans:
+2 -3
View File
@@ -131,10 +131,9 @@ class TestBatchDelete:
return provider_count
@pytest.mark.django_db
def test_batch_delete(self, tenants_fixture, create_test_providers):
tenant_id = str(tenants_fixture[0].id)
def test_batch_delete(self, create_test_providers):
_, summary = batch_delete(
tenant_id, Provider.objects.all(), batch_size=create_test_providers // 2
Provider.objects.all(), batch_size=create_test_providers // 2
)
assert Provider.objects.all().count() == 0
assert summary == {"api.Provider": create_test_providers}
-28
View File
@@ -92,31 +92,3 @@ class TestResourceModel:
assert len(resource.tags.filter(tenant_id=tenant_id)) == 0
assert resource.get_tags(tenant_id=tenant_id) == {}
# @pytest.mark.django_db
# class TestFindingModel:
# def test_add_finding_with_long_uid(
# self, providers_fixture, scans_fixture, resources_fixture
# ):
# provider, *_ = providers_fixture
# tenant_id = provider.tenant_id
# long_uid = "1" * 500
# _ = Finding.objects.create(
# tenant_id=tenant_id,
# uid=long_uid,
# delta=Finding.DeltaChoices.NEW,
# check_metadata={},
# status=StatusChoices.PASS,
# status_extended="",
# severity="high",
# impact="high",
# raw_result={},
# check_id="test_check",
# scan=scans_fixture[0],
# first_seen_at=None,
# muted=False,
# compliance={},
# )
# assert Finding.objects.filter(uid=long_uid).exists()
-6
View File
@@ -19,7 +19,6 @@ 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 prowler.providers.m365.m365_provider import M365Provider
class TestMergeDicts:
@@ -105,7 +104,6 @@ class TestReturnProwlerProvider:
(Provider.ProviderChoices.GCP.value, GcpProvider),
(Provider.ProviderChoices.AZURE.value, AzureProvider),
(Provider.ProviderChoices.KUBERNETES.value, KubernetesProvider),
(Provider.ProviderChoices.M365.value, M365Provider),
],
)
def test_return_prowler_provider(self, provider_type, expected_provider):
@@ -178,10 +176,6 @@ class TestGetProwlerProviderKwargs:
Provider.ProviderChoices.KUBERNETES.value,
{"context": "provider_uid"},
),
(
Provider.ProviderChoices.M365.value,
{},
),
],
)
def test_get_prowler_provider_kwargs(self, provider_type, expected_extra_kwargs):
+3 -292
View File
@@ -3,19 +3,17 @@ import io
import json
import os
from datetime import datetime, timedelta, timezone
from unittest.mock import ANY, MagicMock, Mock, patch
from unittest.mock import ANY, Mock, patch
import jwt
import pytest
from botocore.exceptions import ClientError, NoCredentialsError
from botocore.exceptions import NoCredentialsError
from conftest import API_JSON_CONTENT_TYPE, TEST_PASSWORD, TEST_USER
from django.conf import settings
from django.urls import reverse
from rest_framework import status
from api.compliance import get_compliance_frameworks
from api.models import (
ComplianceOverview,
Integration,
Invitation,
Membership,
@@ -2278,8 +2276,7 @@ class TestScanViewSet:
scan.save()
monkeypatch.setattr(
"api.v1.views.env",
type("env", (), {"str": lambda self, *args, **kwargs: "test-bucket"})(),
"api.v1.views.env", type("env", (), {"str": lambda self, key: bucket})()
)
class FakeS3Client:
@@ -2348,263 +2345,6 @@ class TestScanViewSet:
assert content_disposition.startswith('attachment; filename="')
assert f'filename="{file_path.name}"' in content_disposition
def test_compliance_invalid_framework(self, authenticated_client, scans_fixture):
scan = scans_fixture[0]
scan.state = StateChoices.COMPLETED
scan.output_location = "dummy"
scan.save()
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": "invalid"})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_404_NOT_FOUND
assert resp.json()["errors"]["detail"] == "Compliance 'invalid' not found."
def test_compliance_executing(
self, authenticated_client, scans_fixture, monkeypatch
):
scan = scans_fixture[0]
scan.state = StateChoices.EXECUTING
scan.save()
task = Task.objects.create(tenant_id=scan.tenant_id)
scan.task = task
scan.save()
dummy = {"id": str(task.id), "state": StateChoices.EXECUTING}
monkeypatch.setattr(
"api.v1.views.TaskSerializer",
lambda *args, **kwargs: type("S", (), {"data": dummy}),
)
framework = get_compliance_frameworks(scan.provider.provider)[0]
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": framework})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_202_ACCEPTED
assert "Content-Location" in resp
assert dummy["id"] in resp["Content-Location"]
def test_compliance_no_output(self, authenticated_client, scans_fixture):
scan = scans_fixture[0]
scan.state = StateChoices.COMPLETED
scan.output_location = ""
scan.save()
framework = get_compliance_frameworks(scan.provider.provider)[0]
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": framework})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_404_NOT_FOUND
assert resp.json()["errors"]["detail"] == "The scan has no reports."
def test_compliance_s3_no_credentials(
self, authenticated_client, scans_fixture, monkeypatch
):
scan = scans_fixture[0]
bucket = "bucket"
key = "file.zip"
scan.output_location = f"s3://{bucket}/{key}"
scan.state = StateChoices.COMPLETED
scan.save()
monkeypatch.setattr(
"api.v1.views.get_s3_client",
lambda: (_ for _ in ()).throw(NoCredentialsError()),
)
framework = get_compliance_frameworks(scan.provider.provider)[0]
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": framework})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_403_FORBIDDEN
assert resp.json()["errors"]["detail"] == "There is a problem with credentials."
def test_compliance_s3_success(
self, authenticated_client, scans_fixture, monkeypatch
):
scan = scans_fixture[0]
bucket = "bucket"
prefix = "path/scan.zip"
scan.output_location = f"s3://{bucket}/{prefix}"
scan.state = StateChoices.COMPLETED
scan.save()
monkeypatch.setattr(
"api.v1.views.env",
type("env", (), {"str": lambda self, *args, **kwargs: "test-bucket"})(),
)
match_key = "path/compliance/mitre_attack_aws.csv"
class FakeS3Client:
def list_objects_v2(self, Bucket, Prefix):
return {"Contents": [{"Key": match_key}]}
def get_object(self, Bucket, Key):
return {"Body": io.BytesIO(b"ignored")}
monkeypatch.setattr("api.v1.views.get_s3_client", lambda: FakeS3Client())
framework = match_key.split("/")[-1].split(".")[0]
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": framework})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_200_OK
cd = resp["Content-Disposition"]
assert cd.startswith('attachment; filename="')
assert cd.endswith('filename="mitre_attack_aws.csv"')
def test_compliance_s3_not_found(
self, authenticated_client, scans_fixture, monkeypatch
):
scan = scans_fixture[0]
bucket = "bucket"
scan.output_location = f"s3://{bucket}/x/scan.zip"
scan.state = StateChoices.COMPLETED
scan.save()
monkeypatch.setattr(
"api.v1.views.env",
type("env", (), {"str": lambda self, *args, **kwargs: "test-bucket"})(),
)
class FakeS3Client:
def list_objects_v2(self, Bucket, Prefix):
return {"Contents": []}
def get_object(self, Bucket, Key):
return {"Body": io.BytesIO(b"ignored")}
monkeypatch.setattr("api.v1.views.get_s3_client", lambda: FakeS3Client())
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": "cis_1.4_aws"})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_404_NOT_FOUND
assert (
resp.json()["errors"]["detail"]
== "No compliance file found for name 'cis_1.4_aws'."
)
def test_compliance_local_file(
self, authenticated_client, scans_fixture, tmp_path, monkeypatch
):
scan = scans_fixture[0]
scan.state = StateChoices.COMPLETED
base = tmp_path / "reports"
comp_dir = base / "compliance"
comp_dir.mkdir(parents=True)
fname = comp_dir / "scan_cis.csv"
fname.write_bytes(b"ignored")
scan.output_location = str(base / "scan.zip")
scan.save()
monkeypatch.setattr(
glob,
"glob",
lambda p: [str(fname)] if p.endswith("*_cis_1.4_aws.csv") else [],
)
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": "cis_1.4_aws"})
resp = authenticated_client.get(url)
assert resp.status_code == status.HTTP_200_OK
cd = resp["Content-Disposition"]
assert cd.startswith('attachment; filename="')
assert cd.endswith(f'filename="{fname.name}"')
@patch("api.v1.views.Task.objects.get")
@patch("api.v1.views.TaskSerializer")
def test__get_task_status_returns_none_if_task_not_executing(
self, mock_task_serializer, mock_task_get, authenticated_client, scans_fixture
):
scan = scans_fixture[0]
scan.state = StateChoices.COMPLETED
scan.output_location = "dummy"
scan.save()
task = Task.objects.create(tenant_id=scan.tenant_id)
mock_task_get.return_value = task
mock_task_serializer.return_value.data = {
"id": str(task.id),
"state": StateChoices.COMPLETED,
}
url = reverse("scan-report", kwargs={"pk": scan.id})
response = authenticated_client.get(url)
assert response.status_code == status.HTTP_404_NOT_FOUND
@patch("api.v1.views.get_s3_client")
@patch("api.v1.views.sentry_sdk.capture_exception")
def test_compliance_list_objects_client_error(
self,
mock_sentry_capture,
mock_get_s3_client,
authenticated_client,
scans_fixture,
):
scan = scans_fixture[0]
scan.output_location = "s3://test-bucket/path/to/scan.zip"
scan.state = StateChoices.COMPLETED
scan.save()
fake_client = MagicMock()
fake_client.list_objects_v2.side_effect = ClientError(
{"Error": {"Code": "InternalError"}}, "ListObjectsV2"
)
mock_get_s3_client.return_value = fake_client
framework = get_compliance_frameworks(scan.provider.provider)[0]
url = reverse("scan-compliance", kwargs={"pk": scan.id, "name": framework})
response = authenticated_client.get(url)
assert response.status_code == status.HTTP_502_BAD_GATEWAY
assert (
response.json()["errors"]["detail"]
== "Unable to list compliance files in S3: encountered an AWS error."
)
mock_sentry_capture.assert_called()
@patch("api.v1.views.get_s3_client")
def test_report_s3_nosuchkey(
self, mock_get_s3_client, authenticated_client, scans_fixture
):
scan = scans_fixture[0]
scan.output_location = "s3://test-bucket/report.zip"
scan.state = StateChoices.COMPLETED
scan.save()
fake_client = MagicMock()
fake_client.get_object.side_effect = ClientError(
{"Error": {"Code": "NoSuchKey"}}, "GetObject"
)
mock_get_s3_client.return_value = fake_client
url = reverse("scan-report", kwargs={"pk": scan.id})
response = authenticated_client.get(url)
assert response.status_code == status.HTTP_404_NOT_FOUND
assert response.json()["errors"]["detail"] == "The scan has no reports."
@patch("api.v1.views.get_s3_client")
def test_report_s3_client_error_other(
self, mock_get_s3_client, authenticated_client, scans_fixture
):
scan = scans_fixture[0]
scan.output_location = "s3://test-bucket/report.zip"
scan.state = StateChoices.COMPLETED
scan.save()
fake_client = MagicMock()
fake_client.get_object.side_effect = ClientError(
{"Error": {"Code": "AccessDenied"}}, "GetObject"
)
mock_get_s3_client.return_value = fake_client
url = reverse("scan-report", kwargs={"pk": scan.id})
response = authenticated_client.get(url)
assert response.status_code == status.HTTP_403_FORBIDDEN
assert (
response.json()["errors"]["detail"]
== "There is a problem with credentials."
)
@pytest.mark.django_db
class TestTaskViewSet:
@@ -2952,8 +2692,6 @@ class TestFindingViewSet:
# ("resource_tags", "key:value", 2),
# ("resource_tags", "not:exists", 0),
# ("resource_tags", "not:exists,key:value", 2),
("muted", True, 1),
("muted", False, 1),
]
),
)
@@ -4770,33 +4508,6 @@ class TestComplianceOverviewViewSet:
assert len(response.json()["data"]) == 1
assert response.json()["data"][0]["id"] == str(compliance_overview1.id)
def test_compliance_overview_metadata(
self, authenticated_client, compliance_overviews_fixture
):
response = authenticated_client.get(
reverse("complianceoverview-metadata"),
{"filter[scan_id]": str(compliance_overviews_fixture[0].scan_id)},
)
data = response.json()
expected_regions = set(
ComplianceOverview.objects.all()
.values_list("region", flat=True)
.distinct("region")
)
assert response.status_code == status.HTTP_200_OK
assert data["data"]["type"] == "compliance-overviews-metadata"
assert data["data"]["id"] is None
assert set(data["data"]["attributes"]["regions"]) == expected_regions
def test_compliance_overview_metadata_missing_scan_id(self, authenticated_client):
# Attempt to list compliance overviews without providing filter[scan_id]
response = authenticated_client.get(reverse("complianceoverview-metadata"))
assert response.status_code == status.HTTP_400_BAD_REQUEST
assert response.json()["errors"][0]["source"]["pointer"] == "filter[scan_id]"
assert response.json()["errors"][0]["code"] == "required"
@pytest.mark.django_db
class TestOverviewViewSet:
+5 -10
View File
@@ -11,7 +11,6 @@ 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 prowler.providers.m365.m365_provider import M365Provider
class CustomOAuth2Client(OAuth2Client):
@@ -52,14 +51,14 @@ def merge_dicts(default_dict: dict, replacement_dict: dict) -> dict:
def return_prowler_provider(
provider: Provider,
) -> [AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider]:
) -> [AwsProvider | AzureProvider | GcpProvider | KubernetesProvider]:
"""Return the Prowler provider class based on the given provider type.
Args:
provider (Provider): The provider object containing the provider type and associated secrets.
Returns:
AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: The corresponding provider class.
AwsProvider | AzureProvider | GcpProvider | KubernetesProvider: The corresponding provider class.
Raises:
ValueError: If the provider type specified in `provider.provider` is not supported.
@@ -73,8 +72,6 @@ def return_prowler_provider(
prowler_provider = AzureProvider
case Provider.ProviderChoices.KUBERNETES.value:
prowler_provider = KubernetesProvider
case Provider.ProviderChoices.M365.value:
prowler_provider = M365Provider
case _:
raise ValueError(f"Provider type {provider.provider} not supported")
return prowler_provider
@@ -107,15 +104,15 @@ def get_prowler_provider_kwargs(provider: Provider) -> dict:
def initialize_prowler_provider(
provider: Provider,
) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider:
) -> AwsProvider | AzureProvider | GcpProvider | KubernetesProvider:
"""Initialize a Prowler provider instance based on the given provider type.
Args:
provider (Provider): The provider object containing the provider type and associated secrets.
Returns:
AwsProvider | AzureProvider | GcpProvider | KubernetesProvider | M365Provider: An instance of the corresponding provider class
(`AwsProvider`, `AzureProvider`, `GcpProvider`, `KubernetesProvider` or `M365Provider`) initialized with the
AwsProvider | AzureProvider | GcpProvider | KubernetesProvider: An instance of the corresponding provider class
(`AwsProvider`, `AzureProvider`, `GcpProvider`, or `KubernetesProvider`) initialized with the
provider's secrets.
"""
prowler_provider = return_prowler_provider(provider)
@@ -133,12 +130,10 @@ 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)
return prowler_provider.test_connection(
**prowler_provider_kwargs, provider_id=provider.uid, raise_on_exception=False
)
@@ -1,172 +0,0 @@
from drf_spectacular.utils import extend_schema_field
from rest_framework_json_api import serializers
@extend_schema_field(
{
"oneOf": [
{
"type": "object",
"title": "AWS Static Credentials",
"properties": {
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Required for environments where no IAM role is being "
"assumed and direct AWS access is needed.",
},
"aws_secret_access_key": {
"type": "string",
"description": "The AWS secret access key. Must accompany 'aws_access_key_id' to authorize "
"access to AWS resources.",
},
"aws_session_token": {
"type": "string",
"description": "The session token associated with temporary credentials. Only needed for "
"session-based or temporary AWS access.",
},
},
"required": ["aws_access_key_id", "aws_secret_access_key"],
},
{
"type": "object",
"title": "AWS Assume Role",
"properties": {
"role_arn": {
"type": "string",
"description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
"assumption.",
},
"external_id": {
"type": "string",
"description": "An identifier to enhance security for role assumption.",
},
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Only required if the environment lacks pre-configured "
"AWS credentials.",
},
"aws_secret_access_key": {
"type": "string",
"description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
"no AWS credentials are pre-configured.",
},
"aws_session_token": {
"type": "string",
"description": "The session token for temporary credentials, if applicable.",
},
"session_duration": {
"type": "integer",
"minimum": 900,
"maximum": 43200,
"default": 3600,
"description": "The duration (in seconds) for the role session.",
},
"role_session_name": {
"type": "string",
"description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
"The regex used to validate this parameter is a string of characters consisting of "
"upper- and lower-case alphanumeric characters with no spaces. You can also include "
"underscores or any of the following characters: =,.@-\n\n"
"Examples:\n"
"- MySession123\n"
"- User_Session-1\n"
"- Test.Session@2",
"pattern": "^[a-zA-Z0-9=,.@_-]+$",
},
},
"required": ["role_arn", "external_id"],
},
{
"type": "object",
"title": "Azure Static Credentials",
"properties": {
"client_id": {
"type": "string",
"description": "The Azure application (client) ID for authentication in Azure AD.",
},
"client_secret": {
"type": "string",
"description": "The client secret associated with the application (client) ID, providing "
"secure access.",
},
"tenant_id": {
"type": "string",
"description": "The Azure tenant ID, representing the directory where the application is "
"registered.",
},
},
"required": ["client_id", "client_secret", "tenant_id"],
},
{
"type": "object",
"title": "M365 Static Credentials",
"properties": {
"client_id": {
"type": "string",
"description": "The Azure application (client) ID for authentication in Azure AD.",
},
"client_secret": {
"type": "string",
"description": "The client secret associated with the application (client) ID, providing "
"secure access.",
},
"tenant_id": {
"type": "string",
"description": "The Azure tenant ID, representing the directory where the application is "
"registered.",
},
"user": {
"type": "email",
"description": "User microsoft email address.",
},
"encrypted_password": {
"type": "string",
"description": "User encrypted password.",
},
},
"required": [
"client_id",
"client_secret",
"tenant_id",
"user",
"encrypted_password",
],
},
{
"type": "object",
"title": "GCP Static Credentials",
"properties": {
"client_id": {
"type": "string",
"description": "The client ID from Google Cloud, used to identify the application for GCP "
"access.",
},
"client_secret": {
"type": "string",
"description": "The client secret associated with the GCP client ID, required for secure "
"access.",
},
"refresh_token": {
"type": "string",
"description": "A refresh token that allows the application to obtain new access tokens for "
"extended use.",
},
},
"required": ["client_id", "client_secret", "refresh_token"],
},
{
"type": "object",
"title": "Kubernetes Static Credentials",
"properties": {
"kubeconfig_content": {
"type": "string",
"description": "The content of the Kubernetes kubeconfig file, encoded as a string.",
}
},
"required": ["kubeconfig_content"],
},
]
}
)
class ProviderSecretField(serializers.JSONField):
pass
+135 -35
View File
@@ -42,7 +42,6 @@ from api.v1.serializer_utils.integrations import (
IntegrationCredentialField,
S3ConfigSerializer,
)
from api.v1.serializer_utils.providers import ProviderSecretField
# Tokens
@@ -852,10 +851,6 @@ class ScanSerializer(RLSSerializer):
"url",
]
included_serializers = {
"provider": "api.v1.serializers.ProviderIncludeSerializer",
}
class ScanIncludeSerializer(RLSSerializer):
trigger = serializers.ChoiceField(
@@ -960,15 +955,6 @@ class ScanReportSerializer(serializers.Serializer):
fields = ["id"]
class ScanComplianceReportSerializer(serializers.Serializer):
id = serializers.CharField(source="scan")
name = serializers.CharField()
class Meta:
resource_name = "scan-reports"
fields = ["id", "name"]
class ResourceTagSerializer(RLSSerializer):
"""
Serializer for the ResourceTag model
@@ -1101,7 +1087,6 @@ class FindingSerializer(RLSSerializer):
"inserted_at",
"updated_at",
"first_seen_at",
"muted",
"url",
# Relationships
"scan",
@@ -1151,8 +1136,6 @@ class BaseWriteProviderSecretSerializer(BaseWriteSerializer):
serializer = GCPProviderSecret(data=secret)
elif provider_type == Provider.ProviderChoices.KUBERNETES.value:
serializer = KubernetesProviderSecret(data=secret)
elif provider_type == Provider.ProviderChoices.M365.value:
serializer = M365ProviderSecret(data=secret)
else:
raise serializers.ValidationError(
{"provider": f"Provider type not supported {provider_type}"}
@@ -1192,17 +1175,6 @@ class AzureProviderSecret(serializers.Serializer):
resource_name = "provider-secrets"
class M365ProviderSecret(serializers.Serializer):
client_id = serializers.CharField()
client_secret = serializers.CharField()
tenant_id = serializers.CharField()
user = serializers.EmailField()
encrypted_password = serializers.CharField()
class Meta:
resource_name = "provider-secrets"
class GCPProviderSecret(serializers.Serializer):
client_id = serializers.CharField()
client_secret = serializers.CharField()
@@ -1234,6 +1206,141 @@ class AWSRoleAssumptionProviderSecret(serializers.Serializer):
resource_name = "provider-secrets"
@extend_schema_field(
{
"oneOf": [
{
"type": "object",
"title": "AWS Static Credentials",
"properties": {
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Required for environments where no IAM role is being "
"assumed and direct AWS access is needed.",
},
"aws_secret_access_key": {
"type": "string",
"description": "The AWS secret access key. Must accompany 'aws_access_key_id' to authorize "
"access to AWS resources.",
},
"aws_session_token": {
"type": "string",
"description": "The session token associated with temporary credentials. Only needed for "
"session-based or temporary AWS access.",
},
},
"required": ["aws_access_key_id", "aws_secret_access_key"],
},
{
"type": "object",
"title": "AWS Assume Role",
"properties": {
"role_arn": {
"type": "string",
"description": "The Amazon Resource Name (ARN) of the role to assume. Required for AWS role "
"assumption.",
},
"external_id": {
"type": "string",
"description": "An identifier to enhance security for role assumption.",
},
"aws_access_key_id": {
"type": "string",
"description": "The AWS access key ID. Only required if the environment lacks pre-configured "
"AWS credentials.",
},
"aws_secret_access_key": {
"type": "string",
"description": "The AWS secret access key. Required if 'aws_access_key_id' is provided or if "
"no AWS credentials are pre-configured.",
},
"aws_session_token": {
"type": "string",
"description": "The session token for temporary credentials, if applicable.",
},
"session_duration": {
"type": "integer",
"minimum": 900,
"maximum": 43200,
"default": 3600,
"description": "The duration (in seconds) for the role session.",
},
"role_session_name": {
"type": "string",
"description": "An identifier for the role session, useful for tracking sessions in AWS logs. "
"The regex used to validate this parameter is a string of characters consisting of "
"upper- and lower-case alphanumeric characters with no spaces. You can also include "
"underscores or any of the following characters: =,.@-\n\n"
"Examples:\n"
"- MySession123\n"
"- User_Session-1\n"
"- Test.Session@2",
"pattern": "^[a-zA-Z0-9=,.@_-]+$",
},
},
"required": ["role_arn", "external_id"],
},
{
"type": "object",
"title": "Azure Static Credentials",
"properties": {
"client_id": {
"type": "string",
"description": "The Azure application (client) ID for authentication in Azure AD.",
},
"client_secret": {
"type": "string",
"description": "The client secret associated with the application (client) ID, providing "
"secure access.",
},
"tenant_id": {
"type": "string",
"description": "The Azure tenant ID, representing the directory where the application is "
"registered.",
},
},
"required": ["client_id", "client_secret", "tenant_id"],
},
{
"type": "object",
"title": "GCP Static Credentials",
"properties": {
"client_id": {
"type": "string",
"description": "The client ID from Google Cloud, used to identify the application for GCP "
"access.",
},
"client_secret": {
"type": "string",
"description": "The client secret associated with the GCP client ID, required for secure "
"access.",
},
"refresh_token": {
"type": "string",
"description": "A refresh token that allows the application to obtain new access tokens for "
"extended use.",
},
},
"required": ["client_id", "client_secret", "refresh_token"],
},
{
"type": "object",
"title": "Kubernetes Static Credentials",
"properties": {
"kubeconfig_content": {
"type": "string",
"description": "The content of the Kubernetes kubeconfig file, encoded as a string.",
}
},
"required": ["kubeconfig_content"],
},
]
}
)
class ProviderSecretField(serializers.JSONField):
pass
class ProviderSecretSerializer(RLSSerializer):
"""
Serializer for the ProviderSecret model.
@@ -1790,13 +1897,6 @@ 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
+65 -252
View File
@@ -22,7 +22,6 @@ from django.http import HttpResponse
from django.urls import reverse
from django.utils.decorators import method_decorator
from django.views.decorators.cache import cache_control
from django_celery_beat.models import PeriodicTask
from drf_spectacular.settings import spectacular_settings
from drf_spectacular.utils import (
OpenApiParameter,
@@ -55,7 +54,6 @@ from tasks.tasks import (
)
from api.base_views import BaseRLSViewSet, BaseTenantViewset, BaseUserViewset
from api.compliance import get_compliance_frameworks
from api.db_router import MainRouter
from api.filters import (
ComplianceOverviewFilter,
@@ -103,7 +101,6 @@ from api.rls import Tenant
from api.utils import CustomOAuth2Client, validate_invitation
from api.v1.serializers import (
ComplianceOverviewFullSerializer,
ComplianceOverviewMetadataSerializer,
ComplianceOverviewSerializer,
FindingDynamicFilterSerializer,
FindingMetadataSerializer,
@@ -135,7 +132,6 @@ from api.v1.serializers import (
RoleProviderGroupRelationshipSerializer,
RoleSerializer,
RoleUpdateSerializer,
ScanComplianceReportSerializer,
ScanCreateSerializer,
ScanReportSerializer,
ScanSerializer,
@@ -249,7 +245,7 @@ class SchemaView(SpectacularAPIView):
def get(self, request, *args, **kwargs):
spectacular_settings.TITLE = "Prowler API"
spectacular_settings.VERSION = "1.7.0"
spectacular_settings.VERSION = "1.6.0"
spectacular_settings.DESCRIPTION = (
"Prowler API specification.\n\nThis file is auto-generated."
)
@@ -1091,8 +1087,6 @@ class ProviderViewSet(BaseRLSViewSet):
provider = get_object_or_404(Provider, pk=pk)
provider.is_deleted = True
provider.save()
task_name = f"scan-perform-scheduled-{pk}"
PeriodicTask.objects.filter(name=task_name).update(enabled=False)
with transaction.atomic():
task = delete_provider_task.delay(
@@ -1152,27 +1146,6 @@ class ProviderViewSet(BaseRLSViewSet):
404: OpenApiResponse(description="The scan has no reports"),
},
),
compliance=extend_schema(
tags=["Scan"],
summary="Retrieve compliance report as CSV",
description="Download a specific compliance report (e.g., 'cis_1.4_aws') as a CSV file.",
parameters=[
OpenApiParameter(
name="name",
type=str,
location=OpenApiParameter.PATH,
required=True,
description="The compliance report name, like 'cis_1.4_aws'",
),
],
responses={
200: OpenApiResponse(
description="CSV file containing the compliance report"
),
404: OpenApiResponse(description="Compliance report not found"),
},
request=None,
),
)
@method_decorator(CACHE_DECORATOR, name="list")
@method_decorator(CACHE_DECORATOR, name="retrieve")
@@ -1225,10 +1198,6 @@ class ScanViewSet(BaseRLSViewSet):
if hasattr(self, "response_serializer_class"):
return self.response_serializer_class
return ScanReportSerializer
elif self.action == "compliance":
if hasattr(self, "response_serializer_class"):
return self.response_serializer_class
return ScanComplianceReportSerializer
return super().get_serializer_class()
def partial_update(self, request, *args, **kwargs):
@@ -1246,111 +1215,70 @@ class ScanViewSet(BaseRLSViewSet):
)
return Response(data=read_serializer.data, status=status.HTTP_200_OK)
def _get_task_status(self, scan_instance):
"""
Returns task status if the scan or its associated report-generation task is still executing.
@action(detail=True, methods=["get"], url_name="report")
def report(self, request, pk=None):
scan_instance = self.get_object()
If the scan is in an EXECUTING state or if a background task related to report generation
is found and also executing, this method returns a 202 Accepted response with the task
metadata and a `Content-Location` header pointing to the task detail endpoint.
if scan_instance.state == StateChoices.EXECUTING:
# If the scan is still running, return the task
prowler_task = Task.objects.get(id=scan_instance.task.id)
self.response_serializer_class = TaskSerializer
output_serializer = self.get_serializer(prowler_task)
return Response(
data=output_serializer.data,
status=status.HTTP_202_ACCEPTED,
headers={
"Content-Location": reverse(
"task-detail", kwargs={"pk": output_serializer.data["id"]}
)
},
)
Args:
scan_instance (Scan): The scan instance for which the task status is being checked.
Returns:
Response or None:
- A `Response` with HTTP 202 status and serialized task data if the task is executing.
- `None` if no running task is found or if the task has already completed.
"""
task = None
if scan_instance.state == StateChoices.EXECUTING and scan_instance.task:
task = scan_instance.task
else:
try:
task = Task.objects.get(
task_runner_task__task_name="scan-report",
task_runner_task__task_args__contains=str(scan_instance.id),
try:
output_celery_task = Task.objects.get(
task_runner_task__task_name="scan-report",
task_runner_task__task_args__contains=pk,
)
self.response_serializer_class = TaskSerializer
output_serializer = self.get_serializer(output_celery_task)
if output_serializer.data["state"] == StateChoices.EXECUTING:
# If the task is still running, return the task
return Response(
data=output_serializer.data,
status=status.HTTP_202_ACCEPTED,
headers={
"Content-Location": reverse(
"task-detail", kwargs={"pk": output_serializer.data["id"]}
)
},
)
except Task.DoesNotExist:
return None
except Task.DoesNotExist:
# If the task does not exist, it means that the task is removed from the database
pass
self.response_serializer_class = TaskSerializer
serializer = self.get_serializer(task)
output_location = scan_instance.output_location
if not output_location:
return Response(
{"detail": "The scan has no reports."},
status=status.HTTP_404_NOT_FOUND,
)
if serializer.data.get("state") != StateChoices.EXECUTING:
return None
return Response(
data=serializer.data,
status=status.HTTP_202_ACCEPTED,
headers={
"Content-Location": reverse(
"task-detail", kwargs={"pk": serializer.data["id"]}
)
},
)
def _load_file(self, path_pattern, s3=False, bucket=None, list_objects=False):
"""
Loads a binary file (e.g., ZIP or CSV) and returns its content and filename.
Depending on the input parameters, this method supports loading:
- From S3 using a direct key.
- From S3 by listing objects under a prefix and matching suffix.
- From the local filesystem using glob pattern matching.
Args:
path_pattern (str): The key or glob pattern representing the file location.
s3 (bool, optional): Whether the file is stored in S3. Defaults to False.
bucket (str, optional): The name of the S3 bucket, required if `s3=True`. Defaults to None.
list_objects (bool, optional): If True and `s3=True`, list objects by prefix to find the file. Defaults to False.
Returns:
tuple[bytes, str]: A tuple containing the file content as bytes and the filename if successful.
Response: A DRF `Response` object with an appropriate status and error detail if an error occurs.
"""
if s3:
if scan_instance.output_location.startswith("s3://"):
try:
client = get_s3_client()
s3_client = get_s3_client()
except (ClientError, NoCredentialsError, ParamValidationError):
return Response(
{"detail": "There is a problem with credentials."},
status=status.HTTP_403_FORBIDDEN,
)
if list_objects:
# list keys under prefix then match suffix
prefix = os.path.dirname(path_pattern)
suffix = os.path.basename(path_pattern)
try:
resp = client.list_objects_v2(Bucket=bucket, Prefix=prefix)
except ClientError as e:
sentry_sdk.capture_exception(e)
return Response(
{
"detail": "Unable to list compliance files in S3: encountered an AWS error."
},
status=status.HTTP_502_BAD_GATEWAY,
)
contents = resp.get("Contents", [])
keys = [obj["Key"] for obj in contents if obj["Key"].endswith(suffix)]
if not keys:
return Response(
{
"detail": f"No compliance file found for name '{os.path.splitext(suffix)[0]}'."
},
status=status.HTTP_404_NOT_FOUND,
)
# path_pattern here is prefix, but in compliance we build correct suffix check before
key = keys[0]
else:
# path_pattern is exact key
key = path_pattern
bucket_name = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET")
key = output_location[len(f"s3://{bucket_name}/") :]
try:
s3_obj = client.get_object(Bucket=bucket, Key=key)
s3_object = s3_client.get_object(Bucket=bucket_name, Key=key)
except ClientError as e:
code = e.response.get("Error", {}).get("Code")
if code == "NoSuchKey":
error_code = e.response.get("Error", {}).get("Code")
if error_code == "NoSuchKey":
return Response(
{"detail": "The scan has no reports."},
status=status.HTTP_404_NOT_FOUND,
@@ -1359,97 +1287,28 @@ class ScanViewSet(BaseRLSViewSet):
{"detail": "There is a problem with credentials."},
status=status.HTTP_403_FORBIDDEN,
)
content = s3_obj["Body"].read()
filename = os.path.basename(key)
file_content = s3_object["Body"].read()
filename = os.path.basename(output_location.split("/")[-1])
else:
files = glob.glob(path_pattern)
if not files:
zip_files = glob.glob(output_location)
try:
file_path = zip_files[0]
except IndexError as e:
sentry_sdk.capture_exception(e)
return Response(
{"detail": "The scan has no reports."},
status=status.HTTP_404_NOT_FOUND,
)
filepath = files[0]
with open(filepath, "rb") as f:
content = f.read()
filename = os.path.basename(filepath)
with open(file_path, "rb") as f:
file_content = f.read()
filename = os.path.basename(file_path)
return content, filename
def _serve_file(self, content, filename, content_type):
response = HttpResponse(content, content_type=content_type)
response = HttpResponse(
file_content, content_type="application/x-zip-compressed"
)
response["Content-Disposition"] = f'attachment; filename="{filename}"'
return response
@action(detail=True, methods=["get"], url_name="report")
def report(self, request, pk=None):
scan = self.get_object()
# Check for executing tasks
running_resp = self._get_task_status(scan)
if running_resp:
return running_resp
if not scan.output_location:
return Response(
{"detail": "The scan has no reports."}, status=status.HTTP_404_NOT_FOUND
)
if scan.output_location.startswith("s3://"):
bucket = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET", "")
key_prefix = scan.output_location.removeprefix(f"s3://{bucket}/")
loader = self._load_file(
key_prefix, s3=True, bucket=bucket, list_objects=False
)
else:
loader = self._load_file(scan.output_location, s3=False)
if isinstance(loader, Response):
return loader
content, filename = loader
return self._serve_file(content, filename, "application/x-zip-compressed")
@action(
detail=True,
methods=["get"],
url_path="compliance/(?P<name>[^/]+)",
url_name="compliance",
)
def compliance(self, request, pk=None, name=None):
scan = self.get_object()
if name not in get_compliance_frameworks(scan.provider.provider):
return Response(
{"detail": f"Compliance '{name}' not found."},
status=status.HTTP_404_NOT_FOUND,
)
running_resp = self._get_task_status(scan)
if running_resp:
return running_resp
if not scan.output_location:
return Response(
{"detail": "The scan has no reports."}, status=status.HTTP_404_NOT_FOUND
)
if scan.output_location.startswith("s3://"):
bucket = env.str("DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET", "")
key_prefix = scan.output_location.removeprefix(f"s3://{bucket}/")
prefix = os.path.join(
os.path.dirname(key_prefix), "compliance", f"{name}.csv"
)
loader = self._load_file(prefix, s3=True, bucket=bucket, list_objects=True)
else:
base = os.path.dirname(scan.output_location)
pattern = os.path.join(base, "compliance", f"*_{name}.csv")
loader = self._load_file(pattern, s3=False)
if isinstance(loader, Response):
return loader
content, filename = loader
return self._serve_file(content, filename, "text/csv")
def create(self, request, *args, **kwargs):
input_serializer = self.get_serializer(data=request.data)
input_serializer.is_valid(raise_exception=True)
@@ -2195,21 +2054,6 @@ class RoleProviderGroupRelationshipView(RelationshipView, BaseRLSViewSet):
description="Fetch detailed information about a specific compliance overview by its ID, including detailed "
"requirement information and check's status.",
),
metadata=extend_schema(
tags=["Compliance Overview"],
summary="Retrieve metadata values from compliance overviews",
description="Fetch unique metadata values from a set of compliance overviews. This is useful for dynamic "
"filtering.",
parameters=[
OpenApiParameter(
name="filter[scan_id]",
required=True,
type=OpenApiTypes.UUID,
location=OpenApiParameter.QUERY,
description="Related scan ID.",
),
],
),
)
@method_decorator(CACHE_DECORATOR, name="list")
@method_decorator(CACHE_DECORATOR, name="retrieve")
@@ -2271,8 +2115,6 @@ class ComplianceOverviewViewSet(BaseRLSViewSet):
def get_serializer_class(self):
if self.action == "retrieve":
return ComplianceOverviewFullSerializer
elif self.action == "metadata":
return ComplianceOverviewMetadataSerializer
return super().get_serializer_class()
def list(self, request, *args, **kwargs):
@@ -2289,35 +2131,6 @@ class ComplianceOverviewViewSet(BaseRLSViewSet):
)
return super().list(request, *args, **kwargs)
@action(detail=False, methods=["get"], url_name="metadata")
def metadata(self, request):
scan_id = request.query_params.get("filter[scan_id]")
if not scan_id:
raise ValidationError(
[
{
"detail": "This query parameter is required.",
"status": 400,
"source": {"pointer": "filter[scan_id]"},
"code": "required",
}
]
)
tenant_id = self.request.tenant_id
regions = list(
ComplianceOverview.objects.filter(tenant_id=tenant_id, scan_id=scan_id)
.values_list("region", flat=True)
.order_by("region")
.distinct()
)
result = {"regions": regions}
serializer = self.get_serializer(data=result)
serializer.is_valid(raise_exception=True)
return Response(serializer.data, status=status.HTTP_200_OK)
@extend_schema(tags=["Overview"])
@extend_schema_view(
+2 -2
View File
@@ -50,9 +50,9 @@ class RLSTask(Task):
tenant_id = kwargs.get("tenant_id")
with rls_transaction(tenant_id):
APITask.objects.update_or_create(
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
-2
View File
@@ -241,5 +241,3 @@ DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGI
SECURE_CONTENT_TYPE_NOSNIFF = True
X_FRAME_OPTIONS = "DENY"
SECURE_REFERRER_POLICY = "strict-origin-when-cross-origin"
DJANGO_DELETION_BATCH_SIZE = env.int("DJANGO_DELETION_BATCH_SIZE", 5000)
-14
View File
@@ -12,8 +12,6 @@ IGNORED_EXCEPTIONS = [
"UnauthorizedOperation",
"AuthFailure",
"InvalidClientTokenId",
"AWSInvalidProviderIdError",
"InternalServerErrorException",
"AccessDenied",
"No Shodan API Key", # Shodan Check
"RequestLimitExceeded", # For now we don't want to log the RequestLimitExceeded errors
@@ -35,13 +33,6 @@ IGNORED_EXCEPTIONS = [
"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",
@@ -50,8 +41,6 @@ IGNORED_EXCEPTIONS = [
"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",
@@ -60,7 +49,6 @@ IGNORED_EXCEPTIONS = [
"AzureNotValidClientIdError",
"AzureNotValidClientSecretError",
"AzureNotValidTenantIdError",
"AzureInvalidProviderIdError",
"AzureTenantIdAndClientSecretNotBelongingToClientIdError",
"AzureTenantIdAndClientIdNotBelongingToClientSecretError",
"AzureClientIdAndClientSecretNotBelongingToTenantIdError",
@@ -97,6 +85,4 @@ sentry_sdk.init(
# possible.
"continuous_profiling_auto_start": True,
},
attach_stacktrace=True,
ignore_errors=IGNORED_EXCEPTIONS,
)
-1
View File
@@ -655,7 +655,6 @@ def findings_fixture(scans_fixture, resources_fixture):
"Description": "test description orange juice",
},
first_seen_at="2024-01-02T00:00:00Z",
muted=True,
)
finding2.add_resources([resource2])
+27 -22
View File
@@ -1,5 +1,5 @@
from celery.utils.log import get_task_logger
from django.db import DatabaseError
from django.db import DatabaseError, transaction
from api.db_router import MainRouter
from api.db_utils import batch_delete, rls_transaction
@@ -8,12 +8,11 @@ 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:
@@ -22,32 +21,37 @@ def delete_provider(tenant_id: str, pk: str):
Raises:
Provider.DoesNotExist: If no instance with the provided primary key exists.
DatabaseError: If any deletion step fails.
"""
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 = {}
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)),
]
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}")
with transaction.atomic():
_, step_summary = batch_delete(queryset)
deletion_summary.update(step_summary)
except DatabaseError as error:
logger.error(f"Error deleting {step_name}: {error}")
raise
# Delete the provider itself
try:
with rls_transaction(tenant_id):
with transaction.atomic():
_, provider_summary = instance.delete()
deletion_summary.update(provider_summary)
except DatabaseError as db_error:
logger.error(f"Error deleting Provider: {db_error}")
deletion_summary.update(provider_summary)
except DatabaseError as error:
logger.error(f"Error deleting Provider: {error}")
raise
return deletion_summary
@@ -65,8 +69,9 @@ 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 rls_transaction(pk):
summary = delete_provider(provider.id)
deletion_summary.update(summary)
Tenant.objects.using(MainRouter.admin_db).filter(id=pk).delete()
+14 -107
View File
@@ -13,38 +13,6 @@ from prowler.config.config import (
json_ocsf_file_suffix,
output_file_timestamp,
)
from prowler.lib.outputs.compliance.aws_well_architected.aws_well_architected import (
AWSWellArchitected,
)
from prowler.lib.outputs.compliance.cis.cis_aws import AWSCIS
from prowler.lib.outputs.compliance.cis.cis_azure import AzureCIS
from prowler.lib.outputs.compliance.cis.cis_gcp import GCPCIS
from prowler.lib.outputs.compliance.cis.cis_kubernetes import KubernetesCIS
from prowler.lib.outputs.compliance.cis.cis_m365 import M365CIS
from prowler.lib.outputs.compliance.ens.ens_aws import AWSENS
from prowler.lib.outputs.compliance.ens.ens_azure import AzureENS
from prowler.lib.outputs.compliance.ens.ens_gcp import GCPENS
from prowler.lib.outputs.compliance.iso27001.iso27001_aws import AWSISO27001
from prowler.lib.outputs.compliance.iso27001.iso27001_azure import AzureISO27001
from prowler.lib.outputs.compliance.iso27001.iso27001_gcp import GCPISO27001
from prowler.lib.outputs.compliance.iso27001.iso27001_kubernetes import (
KubernetesISO27001,
)
from prowler.lib.outputs.compliance.kisa_ismsp.kisa_ismsp_aws import AWSKISAISMSP
from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_aws import AWSMitreAttack
from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_azure import (
AzureMitreAttack,
)
from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_gcp import GCPMitreAttack
from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_aws import (
ProwlerThreatScoreAWS,
)
from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_azure import (
ProwlerThreatScoreAzure,
)
from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_gcp import (
ProwlerThreatScoreGCP,
)
from prowler.lib.outputs.csv.csv import CSV
from prowler.lib.outputs.html.html import HTML
from prowler.lib.outputs.ocsf.ocsf import OCSF
@@ -52,43 +20,6 @@ from prowler.lib.outputs.ocsf.ocsf import OCSF
logger = get_task_logger(__name__)
COMPLIANCE_CLASS_MAP = {
"aws": [
(lambda name: name.startswith("cis_"), AWSCIS),
(lambda name: name == "mitre_attack_aws", AWSMitreAttack),
(lambda name: name.startswith("ens_"), AWSENS),
(
lambda name: name.startswith("aws_well_architected_framework"),
AWSWellArchitected,
),
(lambda name: name.startswith("iso27001_"), AWSISO27001),
(lambda name: name.startswith("kisa"), AWSKISAISMSP),
(lambda name: name == "prowler_threatscore_aws", ProwlerThreatScoreAWS),
],
"azure": [
(lambda name: name.startswith("cis_"), AzureCIS),
(lambda name: name == "mitre_attack_azure", AzureMitreAttack),
(lambda name: name.startswith("ens_"), AzureENS),
(lambda name: name.startswith("iso27001_"), AzureISO27001),
(lambda name: name == "prowler_threatscore_azure", ProwlerThreatScoreAzure),
],
"gcp": [
(lambda name: name.startswith("cis_"), GCPCIS),
(lambda name: name == "mitre_attack_gcp", GCPMitreAttack),
(lambda name: name.startswith("ens_"), GCPENS),
(lambda name: name.startswith("iso27001_"), GCPISO27001),
(lambda name: name == "prowler_threatscore_gcp", ProwlerThreatScoreGCP),
],
"kubernetes": [
(lambda name: name.startswith("cis_"), KubernetesCIS),
(lambda name: name.startswith("iso27001_"), KubernetesISO27001),
],
"m365": [
(lambda name: name.startswith("cis_"), M365CIS),
],
}
# Predefined mapping for output formats and their configurations
OUTPUT_FORMATS_MAPPING = {
"csv": {
@@ -112,17 +43,13 @@ def _compress_output_files(output_directory: str) -> str:
str: The full path to the newly created ZIP archive.
"""
zip_path = f"{output_directory}.zip"
parent_dir = os.path.dirname(output_directory)
zip_path_abs = os.path.abspath(zip_path)
with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zipf:
for foldername, _, filenames in os.walk(parent_dir):
for filename in filenames:
file_path = os.path.join(foldername, filename)
if os.path.abspath(file_path) == zip_path_abs:
continue
arcname = os.path.relpath(file_path, start=parent_dir)
zipf.write(file_path, arcname)
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
@@ -175,38 +102,25 @@ def _upload_to_s3(tenant_id: str, zip_path: str, scan_id: str) -> str:
Raises:
botocore.exceptions.ClientError: If the upload attempt to S3 fails for any reason.
"""
bucket = base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET
if not bucket:
return None
if not base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET:
return
try:
s3 = get_s3_client()
# Upload the ZIP file (outputs) to the S3 bucket
zip_key = f"{tenant_id}/{scan_id}/{os.path.basename(zip_path)}"
s3_key = f"{tenant_id}/{scan_id}/{os.path.basename(zip_path)}"
s3.upload_file(
Filename=zip_path,
Bucket=bucket,
Key=zip_key,
Bucket=base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET,
Key=s3_key,
)
# Upload the compliance directory to the S3 bucket
compliance_dir = os.path.join(os.path.dirname(zip_path), "compliance")
for filename in os.listdir(compliance_dir):
local_path = os.path.join(compliance_dir, filename)
if not os.path.isfile(local_path):
continue
file_key = f"{tenant_id}/{scan_id}/compliance/{filename}"
s3.upload_file(Filename=local_path, Bucket=bucket, Key=file_key)
return f"s3://{base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET}/{zip_key}"
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
) -> tuple[str, str]:
) -> str:
"""
Generate a file system path for the output directory of a prowler scan.
@@ -231,8 +145,7 @@ def _generate_output_directory(
Example:
>>> _generate_output_directory("/tmp", "aws", "tenant-1234", "scan-5678")
'/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56',
'/tmp/tenant-1234/aws/scan-5678/compliance/prowler-output-2023-02-15T12:34:56'
'/tmp/tenant-1234/aws/scan-5678/prowler-output-2023-02-15T12:34:56'
"""
path = (
f"{output_directory}/{tenant_id}/{scan_id}/prowler-output-"
@@ -240,10 +153,4 @@ def _generate_output_directory(
)
os.makedirs("/".join(path.split("/")[:-1]), exist_ok=True)
compliance_path = (
f"{output_directory}/{tenant_id}/{scan_id}/compliance/prowler-output-"
f"{prowler_provider}-{output_file_timestamp}"
)
os.makedirs("/".join(compliance_path.split("/")[:-1]), exist_ok=True)
return path, compliance_path
return path
+14 -29
View File
@@ -1,4 +1,3 @@
import json
import time
from copy import deepcopy
from datetime import datetime, timezone
@@ -7,7 +6,6 @@ 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,
@@ -193,17 +191,6 @@ def perform_prowler_scan(
if resource_instance.type != finding.resource_type:
resource_instance.type = finding.resource_type
updated_fields.append("type")
if resource_instance.metadata != finding.resource_metadata:
resource_instance.metadata = json.dumps(
finding.resource_metadata, cls=CustomEncoder
)
updated_fields.append("metadata")
if resource_instance.details != finding.resource_details:
resource_instance.details = finding.resource_details
updated_fields.append("details")
if resource_instance.partition != finding.partition:
resource_instance.partition = finding.partition
updated_fields.append("partition")
if updated_fields:
with rls_transaction(tenant_id):
resource_instance.save(update_fields=updated_fields)
@@ -280,8 +267,6 @@ def perform_prowler_scan(
check_id=finding.check_id,
scan=scan_instance,
first_seen_at=last_first_seen_at,
muted=finding.muted,
compliance=finding.compliance,
)
finding_instance.add_resources([resource_instance])
@@ -417,21 +402,21 @@ 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(),
)
@@ -439,63 +424,63 @@ 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(),
)
@@ -513,7 +498,7 @@ 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"],
+65 -141
View File
@@ -1,4 +1,3 @@
from datetime import datetime, timedelta, timezone
from pathlib import Path
from shutil import rmtree
@@ -10,7 +9,6 @@ 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 (
COMPLIANCE_CLASS_MAP,
OUTPUT_FORMATS_MAPPING,
_compress_output_files,
_generate_output_directory,
@@ -19,14 +17,10 @@ from tasks.jobs.export import (
from tasks.jobs.scan import aggregate_findings, perform_prowler_scan
from tasks.utils import batched, get_next_execution_datetime
from api.compliance import get_compliance_frameworks
from api.db_utils import rls_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.check.compliance_models import Compliance
from prowler.lib.outputs.compliance.generic.generic import GenericCompliance
from prowler.lib.outputs.finding import Finding as FindingOutput
logger = get_task_logger(__name__)
@@ -49,10 +43,9 @@ 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", queue="deletion")
@set_tenant
def delete_provider_task(provider_id: str):
"""
Task to delete a specific Provider instance.
@@ -60,7 +53,6 @@ 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:
@@ -68,7 +60,7 @@ 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")
@@ -134,43 +126,6 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
periodic_task_instance = PeriodicTask.objects.get(
name=f"scan-perform-scheduled-{provider_id}"
)
executed_scan = Scan.objects.filter(
tenant_id=tenant_id,
provider_id=provider_id,
task__task_runner_task__task_id=task_id,
).order_by("completed_at")
if (
Scan.objects.filter(
tenant_id=tenant_id,
provider_id=provider_id,
trigger=Scan.TriggerChoices.SCHEDULED,
state=StateChoices.EXECUTING,
scheduler_task_id=periodic_task_instance.id,
scheduled_at__date=datetime.now(timezone.utc).date(),
).exists()
or executed_scan.exists()
):
# Duplicated task execution due to visibility timeout or scan is already running
logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
try:
affected_scan = executed_scan.first()
if not affected_scan:
raise ValueError(
"Error retrieving affected scan details after detecting duplicated scheduled "
"scan."
)
# Return the affected scan details to avoid losing data
serializer = ScanTaskSerializer(instance=affected_scan)
except Exception as duplicated_scan_exception:
logger.error(
f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
f"{str(duplicated_scan_exception)}"
)
raise duplicated_scan_exception
return serializer.data
next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
scan_instance, _ = Scan.objects.get_or_create(
tenant_id=tenant_id,
@@ -178,11 +133,7 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
trigger=Scan.TriggerChoices.SCHEDULED,
state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
scheduler_task_id=periodic_task_instance.id,
defaults={
"state": StateChoices.SCHEDULED,
"name": "Daily scheduled scan",
"scheduled_at": next_scan_datetime - timedelta(days=1),
},
defaults={"state": StateChoices.SCHEDULED},
)
scan_instance.task_id = task_id
@@ -223,7 +174,7 @@ 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", queue="deletion")
def delete_tenant_task(tenant_id: str):
return delete_tenant(pk=tenant_id)
@@ -250,111 +201,84 @@ def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
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))
provider_obj = Provider.objects.get(id=provider_id)
prowler_provider = initialize_prowler_provider(provider_obj)
provider_uid = provider_obj.uid
provider_type = provider_obj.provider
# Get the provider UID
provider_uid = Provider.objects.get(id=provider_id).uid
frameworks_bulk = Compliance.get_bulk(provider_type)
frameworks_avail = get_compliance_frameworks(provider_type)
out_dir, comp_dir = _generate_output_directory(
# Generate and ensure the output directory exists
output_directory = _generate_output_directory(
DJANGO_TMP_OUTPUT_DIRECTORY, provider_uid, tenant_id, scan_id
)
def get_writer(writer_map, name, factory, is_last):
"""
Return existing writer_map[name] or create via factory().
In both cases set `.close_file = is_last`.
"""
initialization = False
if name not in writer_map:
writer_map[name] = factory()
initialization = True
w = writer_map[name]
w.close_file = is_last
return w, initialization
# Define auxiliary variables
output_writers = {}
compliance_writers = {}
scan_summary = FindingOutput._transform_findings_stats(
ScanSummary.objects.filter(scan_id=scan_id)
)
qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid").iterator()
for batch, is_last in batched(qs, DJANGO_FINDINGS_BATCH_SIZE):
fos = [FindingOutput.transform_api_finding(f, prowler_provider) for f in batch]
# Retrieve findings queryset
findings_qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid")
# Outputs
for mode, cfg in OUTPUT_FORMATS_MAPPING.items():
cls = cfg["class"]
suffix = cfg["suffix"]
extra = cfg.get("kwargs", {}).copy()
# 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":
extra.update(provider=prowler_provider, stats=scan_summary)
kwargs["provider"] = prowler_provider
kwargs["stats"] = scan_summary
writer, initialization = get_writer(
output_writers,
cls,
lambda cls=cls, fos=fos, suffix=suffix: cls(
findings=fos,
file_path=out_dir,
file_extension=suffix,
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,
),
is_last,
)
if not initialization:
writer.transform(fos)
writer.batch_write_data_to_file(**extra)
writer._data.clear()
)
writer.close_file = is_last_batch
output_writers[writer_class] = writer
# Compliance CSVs
for name in frameworks_avail:
compliance_obj = frameworks_bulk[name]
# Write the current batch using the writer
writer.batch_write_data_to_file(**kwargs)
klass = GenericCompliance
for condition, cls in COMPLIANCE_CLASS_MAP.get(provider_type, []):
if condition(name):
klass = cls
break
# TODO: Refactor the output classes to avoid this manual reset
writer._data = []
filename = f"{comp_dir}_{name}.csv"
# Compress output files
output_directory = _compress_output_files(output_directory)
writer, initialization = get_writer(
compliance_writers,
name,
lambda klass=klass, fos=fos: klass(
findings=fos,
compliance=compliance_obj,
file_path=filename,
from_cli=False,
),
is_last,
)
if not initialization:
writer.transform(fos, compliance_obj, name)
writer.batch_write_data_to_file()
writer._data.clear()
# Save to configured storage
uploaded = _upload_to_s3(tenant_id, output_directory, scan_id)
compressed = _compress_output_files(out_dir)
upload_uri = _upload_to_s3(tenant_id, compressed, scan_id)
if upload_uri:
if uploaded:
# Remove the local files after upload
try:
rmtree(Path(compressed).parent, ignore_errors=True)
except Exception as e:
rmtree(Path(output_directory).parent, ignore_errors=True)
except FileNotFoundError as e:
logger.error(f"Error deleting output files: {e}")
final_location, did_upload = upload_uri, True
else:
final_location, did_upload = compressed, False
Scan.all_objects.filter(id=scan_id).update(output_location=final_location)
logger.info(f"Scan outputs at {final_location}")
return {"upload": did_upload}
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}
+3 -5
View File
@@ -9,19 +9,17 @@ 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)
@pytest.mark.django_db
-142
View File
@@ -1,142 +0,0 @@
import os
import zipfile
from unittest.mock import MagicMock, patch
import pytest
from botocore.exceptions import ClientError
from tasks.jobs.export import (
_compress_output_files,
_generate_output_directory,
_upload_to_s3,
get_s3_client,
)
@pytest.mark.django_db
class TestOutputs:
def test_compress_output_files_creates_zip(self, tmp_path):
output_dir = tmp_path / "output"
output_dir.mkdir()
file_path = output_dir / "result.csv"
file_path.write_text("data")
zip_path = _compress_output_files(str(output_dir))
assert zip_path.endswith(".zip")
assert os.path.exists(zip_path)
with zipfile.ZipFile(zip_path, "r") as zipf:
assert "output/result.csv" in zipf.namelist()
@patch("tasks.jobs.export.boto3.client")
@patch("tasks.jobs.export.settings")
def test_get_s3_client_success(self, mock_settings, mock_boto_client):
mock_settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID = "test"
mock_settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = "test"
mock_settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = "token"
mock_settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = "eu-west-1"
client_mock = MagicMock()
mock_boto_client.return_value = client_mock
client = get_s3_client()
assert client is not None
client_mock.list_buckets.assert_called()
@patch("tasks.jobs.export.boto3.client")
@patch("tasks.jobs.export.settings")
def test_get_s3_client_fallback(self, mock_settings, mock_boto_client):
mock_boto_client.side_effect = [
ClientError({"Error": {"Code": "403"}}, "ListBuckets"),
MagicMock(),
]
client = get_s3_client()
assert client is not None
@patch("tasks.jobs.export.get_s3_client")
@patch("tasks.jobs.export.base")
def test_upload_to_s3_success(self, mock_base, mock_get_client, tmp_path):
mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
zip_path = tmp_path / "outputs.zip"
zip_path.write_bytes(b"dummy")
compliance_dir = tmp_path / "compliance"
compliance_dir.mkdir()
compliance_file = compliance_dir / "report.csv"
compliance_file.write_text("ok")
client_mock = MagicMock()
mock_get_client.return_value = client_mock
result = _upload_to_s3("tenant-id", str(zip_path), "scan-id")
expected_uri = "s3://test-bucket/tenant-id/scan-id/outputs.zip"
assert result == expected_uri
assert client_mock.upload_file.call_count == 2
@patch("tasks.jobs.export.get_s3_client")
@patch("tasks.jobs.export.base")
def test_upload_to_s3_missing_bucket(self, mock_base, mock_get_client):
mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = ""
result = _upload_to_s3("tenant", "/tmp/fake.zip", "scan")
assert result is None
@patch("tasks.jobs.export.get_s3_client")
@patch("tasks.jobs.export.base")
def test_upload_to_s3_skips_non_files(self, mock_base, mock_get_client, tmp_path):
mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "test-bucket"
zip_path = tmp_path / "results.zip"
zip_path.write_bytes(b"zip")
compliance_dir = tmp_path / "compliance"
compliance_dir.mkdir()
(compliance_dir / "subdir").mkdir()
client_mock = MagicMock()
mock_get_client.return_value = client_mock
result = _upload_to_s3("tenant", str(zip_path), "scan")
expected_uri = "s3://test-bucket/tenant/scan/results.zip"
assert result == expected_uri
client_mock.upload_file.assert_called_once()
@patch(
"tasks.jobs.export.get_s3_client",
side_effect=ClientError({"Error": {}}, "Upload"),
)
@patch("tasks.jobs.export.base")
@patch("tasks.jobs.export.logger.error")
def test_upload_to_s3_failure_logs_error(
self, mock_logger, mock_base, mock_get_client, tmp_path
):
mock_base.DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET = "bucket"
zip_path = tmp_path / "zipfile.zip"
zip_path.write_bytes(b"zip")
compliance_dir = tmp_path / "compliance"
compliance_dir.mkdir()
(compliance_dir / "report.csv").write_text("csv")
_upload_to_s3("tenant", str(zip_path), "scan")
mock_logger.assert_called()
def test_generate_output_directory_creates_paths(self, tmp_path):
from prowler.config.config import output_file_timestamp
base_dir = str(tmp_path)
tenant_id = "t1"
scan_id = "s1"
provider = "aws"
path, compliance = _generate_output_directory(
base_dir, provider, tenant_id, scan_id
)
assert os.path.isdir(os.path.dirname(path))
assert os.path.isdir(os.path.dirname(compliance))
assert path.endswith(f"{provider}-{output_file_timestamp}")
assert compliance.endswith(f"{provider}-{output_file_timestamp}")
-15
View File
@@ -1,4 +1,3 @@
import json
import uuid
from unittest.mock import MagicMock, patch
@@ -8,7 +7,6 @@ from tasks.jobs.scan import (
_store_resources,
perform_prowler_scan,
)
from tasks.utils import CustomEncoder
from api.models import (
Finding,
@@ -109,13 +107,7 @@ 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 +145,6 @@ 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 +152,6 @@ 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()
-415
View File
@@ -1,415 +0,0 @@
import uuid
from pathlib import Path
from unittest.mock import MagicMock, patch
import pytest
from tasks.tasks import generate_outputs
@pytest.mark.django_db
class TestGenerateOutputs:
def setup_method(self):
self.scan_id = str(uuid.uuid4())
self.provider_id = str(uuid.uuid4())
self.tenant_id = str(uuid.uuid4())
def test_no_findings_returns_early(self):
with patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter:
mock_filter.return_value.exists.return_value = False
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert result == {"upload": False}
mock_filter.assert_called_once_with(scan_id=self.scan_id)
@patch("tasks.tasks.rmtree")
@patch("tasks.tasks._upload_to_s3")
@patch("tasks.tasks._compress_output_files")
@patch("tasks.tasks.get_compliance_frameworks")
@patch("tasks.tasks.Compliance.get_bulk")
@patch("tasks.tasks.initialize_prowler_provider")
@patch("tasks.tasks.Provider.objects.get")
@patch("tasks.tasks.ScanSummary.objects.filter")
@patch("tasks.tasks.Finding.all_objects.filter")
def test_generate_outputs_happy_path(
self,
mock_finding_filter,
mock_scan_summary_filter,
mock_provider_get,
mock_initialize_provider,
mock_compliance_get_bulk,
mock_get_available_frameworks,
mock_compress,
mock_upload,
mock_rmtree,
):
mock_scan_summary_filter.return_value.exists.return_value = True
mock_provider = MagicMock()
mock_provider.uid = "provider-uid"
mock_provider.provider = "aws"
mock_provider_get.return_value = mock_provider
prowler_provider = MagicMock()
mock_initialize_provider.return_value = prowler_provider
mock_compliance_get_bulk.return_value = {"cis": MagicMock()}
mock_get_available_frameworks.return_value = ["cis"]
dummy_finding = MagicMock(uid="f1")
mock_finding_filter.return_value.order_by.return_value.iterator.return_value = [
[dummy_finding],
True,
]
mock_transformed_stats = {"some": "stats"}
with (
patch(
"tasks.tasks.FindingOutput._transform_findings_stats",
return_value=mock_transformed_stats,
),
patch(
"tasks.tasks.FindingOutput.transform_api_finding",
return_value={"transformed": "f1"},
),
patch(
"tasks.tasks.OUTPUT_FORMATS_MAPPING",
{
"json": {
"class": MagicMock(name="JSONWriter"),
"suffix": ".json",
"kwargs": {},
}
},
),
patch(
"tasks.tasks.COMPLIANCE_CLASS_MAP",
{"aws": [(lambda x: True, MagicMock(name="CSVCompliance"))]},
),
patch(
"tasks.tasks._generate_output_directory",
return_value=("out-dir", "comp-dir"),
),
patch("tasks.tasks.Scan.all_objects.filter") as mock_scan_update,
):
mock_compress.return_value = "/tmp/zipped.zip"
mock_upload.return_value = "s3://bucket/zipped.zip"
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert result == {"upload": True}
mock_scan_update.return_value.update.assert_called_once_with(
output_location="s3://bucket/zipped.zip"
)
mock_rmtree.assert_called_once_with(
Path("/tmp/zipped.zip").parent, ignore_errors=True
)
def test_generate_outputs_fails_upload(self):
with (
patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
patch("tasks.tasks.Provider.objects.get"),
patch("tasks.tasks.initialize_prowler_provider"),
patch("tasks.tasks.Compliance.get_bulk"),
patch("tasks.tasks.get_compliance_frameworks"),
patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
patch(
"tasks.tasks._generate_output_directory", return_value=("out", "comp")
),
patch("tasks.tasks.FindingOutput._transform_findings_stats"),
patch("tasks.tasks.FindingOutput.transform_api_finding"),
patch(
"tasks.tasks.OUTPUT_FORMATS_MAPPING",
{
"json": {
"class": MagicMock(name="Writer"),
"suffix": ".json",
"kwargs": {},
}
},
),
patch(
"tasks.tasks.COMPLIANCE_CLASS_MAP",
{"aws": [(lambda x: True, MagicMock())]},
),
patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
patch("tasks.tasks._upload_to_s3", return_value=None),
patch("tasks.tasks.Scan.all_objects.filter") as mock_scan_update,
):
mock_filter.return_value.exists.return_value = True
mock_findings.return_value.order_by.return_value.iterator.return_value = [
[MagicMock()],
True,
]
result = generate_outputs(
scan_id="scan",
provider_id="provider",
tenant_id=self.tenant_id,
)
assert result == {"upload": False}
mock_scan_update.return_value.update.assert_called_once()
def test_generate_outputs_triggers_html_extra_update(self):
mock_finding_output = MagicMock()
mock_finding_output.compliance = {"cis": ["requirement-1", "requirement-2"]}
with (
patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
patch("tasks.tasks.Provider.objects.get"),
patch("tasks.tasks.initialize_prowler_provider"),
patch("tasks.tasks.Compliance.get_bulk", return_value={"cis": MagicMock()}),
patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
patch(
"tasks.tasks._generate_output_directory", return_value=("out", "comp")
),
patch(
"tasks.tasks.FindingOutput._transform_findings_stats",
return_value={"some": "stats"},
),
patch(
"tasks.tasks.FindingOutput.transform_api_finding",
return_value=mock_finding_output,
),
patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/f.zip"),
patch("tasks.tasks.Scan.all_objects.filter"),
):
mock_filter.return_value.exists.return_value = True
mock_findings.return_value.order_by.return_value.iterator.return_value = [
[MagicMock()],
True,
]
html_writer_mock = MagicMock()
with (
patch(
"tasks.tasks.OUTPUT_FORMATS_MAPPING",
{
"html": {
"class": lambda *args, **kwargs: html_writer_mock,
"suffix": ".html",
"kwargs": {},
}
},
),
patch(
"tasks.tasks.COMPLIANCE_CLASS_MAP",
{"aws": [(lambda x: True, MagicMock())]},
),
):
generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
html_writer_mock.batch_write_data_to_file.assert_called_once()
def test_transform_called_only_on_second_batch(self):
raw1 = MagicMock()
raw2 = MagicMock()
tf1 = MagicMock()
tf1.compliance = {}
tf2 = MagicMock()
tf2.compliance = {}
writer_instances = []
class TrackingWriter:
def __init__(self, findings, file_path, file_extension, from_cli):
self.transform_called = 0
self.batch_write_data_to_file = MagicMock()
self._data = []
self.close_file = False
writer_instances.append(self)
def transform(self, fos):
self.transform_called += 1
with (
patch("tasks.tasks.ScanSummary.objects.filter") as mock_summary,
patch("tasks.tasks.Provider.objects.get"),
patch("tasks.tasks.initialize_prowler_provider"),
patch("tasks.tasks.Compliance.get_bulk"),
patch("tasks.tasks.get_compliance_frameworks", return_value=[]),
patch("tasks.tasks.FindingOutput._transform_findings_stats"),
patch(
"tasks.tasks.FindingOutput.transform_api_finding",
side_effect=[tf1, tf2],
),
patch(
"tasks.tasks._generate_output_directory",
return_value=("outdir", "compdir"),
),
patch("tasks.tasks._compress_output_files", return_value="outdir.zip"),
patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/outdir.zip"),
patch("tasks.tasks.rmtree"),
patch("tasks.tasks.Scan.all_objects.filter"),
patch(
"tasks.tasks.batched",
return_value=[
([raw1], False),
([raw2], True),
],
),
):
mock_summary.return_value.exists.return_value = True
with patch(
"tasks.tasks.OUTPUT_FORMATS_MAPPING",
{
"json": {
"class": TrackingWriter,
"suffix": ".json",
"kwargs": {},
}
},
):
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert result == {"upload": True}
assert len(writer_instances) == 1
writer = writer_instances[0]
assert writer.transform_called == 1
def test_compliance_transform_called_on_second_batch(self):
raw1 = MagicMock()
raw2 = MagicMock()
compliance_obj = MagicMock()
writer_instances = []
class TrackingComplianceWriter:
def __init__(self, *args, **kwargs):
self.transform_calls = []
self._data = []
writer_instances.append(self)
def transform(self, fos, comp_obj, name):
self.transform_calls.append((fos, comp_obj, name))
def batch_write_data_to_file(self):
pass
two_batches = [
([raw1], False),
([raw2], True),
]
with (
patch("tasks.tasks.ScanSummary.objects.filter") as mock_summary,
patch(
"tasks.tasks.Provider.objects.get",
return_value=MagicMock(uid="UID", provider="aws"),
),
patch("tasks.tasks.initialize_prowler_provider"),
patch(
"tasks.tasks.Compliance.get_bulk", return_value={"cis": compliance_obj}
),
patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
patch(
"tasks.tasks._generate_output_directory",
return_value=("outdir", "compdir"),
),
patch("tasks.tasks.FindingOutput._transform_findings_stats"),
patch(
"tasks.tasks.FindingOutput.transform_api_finding",
side_effect=lambda f, prov: f,
),
patch("tasks.tasks._compress_output_files", return_value="outdir.zip"),
patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/outdir.zip"),
patch("tasks.tasks.rmtree"),
patch(
"tasks.tasks.Scan.all_objects.filter",
return_value=MagicMock(update=lambda **kw: None),
),
patch("tasks.tasks.batched", return_value=two_batches),
patch("tasks.tasks.OUTPUT_FORMATS_MAPPING", {}),
patch(
"tasks.tasks.COMPLIANCE_CLASS_MAP",
{"aws": [(lambda name: True, TrackingComplianceWriter)]},
),
):
mock_summary.return_value.exists.return_value = True
result = generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert len(writer_instances) == 1
writer = writer_instances[0]
assert writer.transform_calls == [([raw2], compliance_obj, "cis")]
assert result == {"upload": True}
def test_generate_outputs_logs_rmtree_exception(self, caplog):
mock_finding_output = MagicMock()
mock_finding_output.compliance = {"cis": ["requirement-1", "requirement-2"]}
with (
patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
patch("tasks.tasks.Provider.objects.get"),
patch("tasks.tasks.initialize_prowler_provider"),
patch("tasks.tasks.Compliance.get_bulk", return_value={"cis": MagicMock()}),
patch("tasks.tasks.get_compliance_frameworks", return_value=["cis"]),
patch("tasks.tasks.Finding.all_objects.filter") as mock_findings,
patch(
"tasks.tasks._generate_output_directory", return_value=("out", "comp")
),
patch(
"tasks.tasks.FindingOutput._transform_findings_stats",
return_value={"some": "stats"},
),
patch(
"tasks.tasks.FindingOutput.transform_api_finding",
return_value=mock_finding_output,
),
patch("tasks.tasks._compress_output_files", return_value="/tmp/compressed"),
patch("tasks.tasks._upload_to_s3", return_value="s3://bucket/file.zip"),
patch("tasks.tasks.Scan.all_objects.filter"),
patch("tasks.tasks.rmtree", side_effect=Exception("Test deletion error")),
):
mock_filter.return_value.exists.return_value = True
mock_findings.return_value.order_by.return_value.iterator.return_value = [
[MagicMock()],
True,
]
with (
patch(
"tasks.tasks.OUTPUT_FORMATS_MAPPING",
{
"json": {
"class": lambda *args, **kwargs: MagicMock(),
"suffix": ".json",
"kwargs": {},
}
},
),
patch(
"tasks.tasks.COMPLIANCE_CLASS_MAP",
{"aws": [(lambda x: True, MagicMock())]},
),
):
with caplog.at_level("ERROR"):
generate_outputs(
scan_id=self.scan_id,
provider_id=self.provider_id,
tenant_id=self.tenant_id,
)
assert "Error deleting output files" in caplog.text
-23
View File
@@ -1,32 +1,9 @@
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:
-156
View File
@@ -1,156 +0,0 @@
#!/usr/bin/env python3
import argparse
import re
import subprocess
import sys
from pathlib import Path
import matplotlib.pyplot as plt
import pandas as pd
plt.style.use("ggplot")
def run_locust(
locust_file: str,
host: str,
users: int,
hatch_rate: int,
run_time: str,
csv_prefix: Path,
) -> Path:
artifacts_dir = Path("artifacts")
artifacts_dir.mkdir(parents=True, exist_ok=True)
cmd = [
"locust",
"-f",
f"scenarios/{locust_file}",
"--headless",
"-u",
str(users),
"-r",
str(hatch_rate),
"-t",
run_time,
"--host",
host,
"--csv",
str(artifacts_dir / csv_prefix.name),
]
print(f"Running Locust: {' '.join(cmd)}")
process = subprocess.run(cmd)
if process.returncode:
sys.exit("Locust execution failed")
stats_file = artifacts_dir / f"{csv_prefix.stem}_stats.csv"
if not stats_file.exists():
sys.exit(f"Stats CSV not found: {stats_file}")
return stats_file
def load_percentiles(csv_path: Path) -> pd.DataFrame:
df = pd.read_csv(csv_path)
mapping = {"50%": "p50", "75%": "p75", "90%": "p90", "95%": "p95"}
available = [col for col in mapping if col in df.columns]
renamed = {col: mapping[col] for col in available}
df = df.rename(columns=renamed).set_index("Name")[renamed.values()]
return df.drop(index=["Aggregated"], errors="ignore")
def sanitize_label(label: str) -> str:
text = re.sub(r"[^\w]+", "_", label.strip().lower())
return text.strip("_")
def plot_multi_comparison(metrics: dict[str, pd.DataFrame]) -> None:
common = sorted(set.intersection(*(set(df.index) for df in metrics.values())))
percentiles = list(next(iter(metrics.values())).columns)
groups = len(metrics)
width = 0.8 / groups
for endpoint in common:
fig, ax = plt.subplots(figsize=(10, 5), dpi=100)
for idx, (label, df) in enumerate(metrics.items()):
series = df.loc[endpoint]
positions = [
i + (idx - groups / 2) * width + width / 2
for i in range(len(percentiles))
]
bars = ax.bar(positions, series.values, width, label=label)
for bar in bars:
height = bar.get_height()
ax.annotate(
f"{int(height)}",
xy=(bar.get_x() + bar.get_width() / 2, height),
xytext=(0, 3),
textcoords="offset points",
ha="center",
va="bottom",
fontsize=8,
)
ax.set_xticks(range(len(percentiles)))
ax.set_xticklabels(percentiles)
ax.set_ylabel("Latency (ms)")
ax.set_title(endpoint, fontsize=12)
ax.grid(True, axis="y", linestyle="--", alpha=0.7)
fig.tight_layout()
fig.subplots_adjust(right=0.75)
ax.legend(loc="center left", bbox_to_anchor=(1, 0.5), framealpha=0.9)
output = Path("artifacts") / f"comparison_{sanitize_label(endpoint)}.png"
plt.savefig(output)
plt.close(fig)
print(f"Saved chart: {output}")
def main() -> None:
parser = argparse.ArgumentParser(description="Run Locust and compare metrics")
parser.add_argument("--locustfile", required=True, help="Locust file in scenarios/")
parser.add_argument("--host", required=True, help="Target host URL")
parser.add_argument(
"--users", type=int, default=10, help="Number of simulated users"
)
parser.add_argument("--rate", type=int, default=1, help="Hatch rate per second")
parser.add_argument("--time", default="1m", help="Test duration (e.g. 30s, 1m)")
parser.add_argument(
"--metrics-dir", default="baselines", help="Directory with CSV baselines"
)
parser.add_argument("--version", default="current", help="Test version")
args = parser.parse_args()
metrics_dir = Path(args.metrics_dir)
if not metrics_dir.is_dir():
sys.exit(f"Metrics directory not found: {metrics_dir}")
metrics_data: dict[str, pd.DataFrame] = {}
for csv_file in sorted(metrics_dir.glob("*.csv")):
metrics_data[csv_file.stem] = load_percentiles(csv_file)
current_prefix = Path(args.version)
current_csv = run_locust(
locust_file=args.locustfile,
host=args.host,
users=args.users,
hatch_rate=args.rate,
run_time=args.time,
csv_prefix=current_prefix,
)
metrics_data[args.version] = load_percentiles(current_csv)
for endpoint in sorted(
set.intersection(*(set(df.index) for df in metrics_data.values()))
):
parts = [endpoint]
for label, df in metrics_data.items():
s = df.loc[endpoint]
parts.append(f"{label}: p50 {s.p50}, p75 {s.p75}, p90 {s.p90}, p95 {s.p95}")
print(" | ".join(parts))
plot_multi_comparison(metrics_data)
if __name__ == "__main__":
main()
-2
View File
@@ -1,2 +0,0 @@
locust==2.34.1
matplotlib==3.10.1
-202
View File
@@ -1,202 +0,0 @@
from locust import events, task
from utils.config import (
FINDINGS_UI_SORT_VALUES,
L_PROVIDER_NAME,
M_PROVIDER_NAME,
S_PROVIDER_NAME,
TARGET_INSERTED_AT,
)
from utils.helpers import (
APIUserBase,
get_api_token,
get_auth_headers,
get_next_resource_filter,
get_resource_filters_pairs,
get_scan_id_from_provider_name,
get_sort_value,
)
GLOBAL = {
"token": None,
"scan_ids": {},
"resource_filters": None,
"large_resource_filters": None,
}
@events.test_start.add_listener
def on_test_start(environment, **kwargs):
GLOBAL["token"] = get_api_token(environment.host)
GLOBAL["scan_ids"]["small"] = get_scan_id_from_provider_name(
environment.host, GLOBAL["token"], S_PROVIDER_NAME
)
GLOBAL["scan_ids"]["medium"] = get_scan_id_from_provider_name(
environment.host, GLOBAL["token"], M_PROVIDER_NAME
)
GLOBAL["scan_ids"]["large"] = get_scan_id_from_provider_name(
environment.host, GLOBAL["token"], L_PROVIDER_NAME
)
GLOBAL["resource_filters"] = get_resource_filters_pairs(
environment.host, GLOBAL["token"]
)
GLOBAL["large_resource_filters"] = get_resource_filters_pairs(
environment.host, GLOBAL["token"], GLOBAL["scan_ids"]["large"]
)
class APIUser(APIUserBase):
def on_start(self):
self.token = GLOBAL["token"]
self.s_scan_id = GLOBAL["scan_ids"]["small"]
self.m_scan_id = GLOBAL["scan_ids"]["medium"]
self.l_scan_id = GLOBAL["scan_ids"]["large"]
self.available_resource_filters = GLOBAL["resource_filters"]
self.available_resource_filters_large_scan = GLOBAL["large_resource_filters"]
@task
def findings_default(self):
name = "/findings"
page_number = self._next_page(name)
endpoint = (
f"/findings?page[number]={page_number}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[inserted_at]={TARGET_INSERTED_AT}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task(3)
def findings_default_include(self):
name = "/findings?include"
page = self._next_page(name)
endpoint = (
f"/findings?page[number]={page}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[inserted_at]={TARGET_INSERTED_AT}"
f"&include=scan.provider,resources"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task(3)
def findings_metadata(self):
endpoint = f"/findings/metadata?" f"filter[inserted_at]={TARGET_INSERTED_AT}"
self.client.get(
endpoint, headers=get_auth_headers(self.token), name="/findings/metadata"
)
@task
def findings_scan_small(self):
name = "/findings?filter[scan_id] - 50k"
page_number = self._next_page(name)
endpoint = (
f"/findings?page[number]={page_number}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[scan]={self.s_scan_id}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def findings_metadata_scan_small(self):
endpoint = f"/findings/metadata?" f"&filter[scan]={self.s_scan_id}"
self.client.get(
endpoint,
headers=get_auth_headers(self.token),
name="/findings/metadata?filter[scan_id] - 50k",
)
@task(2)
def findings_scan_medium(self):
name = "/findings?filter[scan_id] - 250k"
page_number = self._next_page(name)
endpoint = (
f"/findings?page[number]={page_number}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[scan]={self.m_scan_id}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def findings_metadata_scan_medium(self):
endpoint = f"/findings/metadata?" f"&filter[scan]={self.m_scan_id}"
self.client.get(
endpoint,
headers=get_auth_headers(self.token),
name="/findings/metadata?filter[scan_id] - 250k",
)
@task
def findings_scan_large(self):
name = "/findings?filter[scan_id] - 500k"
page_number = self._next_page(name)
endpoint = (
f"/findings?page[number]={page_number}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[scan]={self.l_scan_id}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def findings_scan_large_include(self):
name = "/findings?filter[scan_id]&include - 500k"
page_number = self._next_page(name)
endpoint = (
f"/findings?page[number]={page_number}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[scan]={self.l_scan_id}"
f"&include=scan.provider,resources"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def findings_metadata_scan_large(self):
endpoint = f"/findings/metadata?" f"&filter[scan]={self.l_scan_id}"
self.client.get(
endpoint,
headers=get_auth_headers(self.token),
name="/findings/metadata?filter[scan_id] - 500k",
)
@task(2)
def findings_resource_filter(self):
name = "/findings?filter[resource_filter]&include"
filter_name, filter_value = get_next_resource_filter(
self.available_resource_filters
)
endpoint = (
f"/findings?filter[{filter_name}]={filter_value}"
f"&filter[inserted_at]={TARGET_INSERTED_AT}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&include=scan.provider,resources"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task(3)
def findings_metadata_resource_filter(self):
name = "/findings/metadata?filter[resource_filter]"
filter_name, filter_value = get_next_resource_filter(
self.available_resource_filters
)
endpoint = (
f"/findings?filter[{filter_name}]={filter_value}"
f"&filter[inserted_at]={TARGET_INSERTED_AT}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
@task
def findings_resource_filter_large_scan_include(self):
name = "/findings?filter[resource_filter][scan]&include - 500k"
filter_name, filter_value = get_next_resource_filter(
self.available_resource_filters
)
endpoint = (
f"/findings?filter[{filter_name}]={filter_value}"
f"&{get_sort_value(FINDINGS_UI_SORT_VALUES)}"
f"&filter[scan]={self.l_scan_id}"
f"&include=scan.provider,resources"
)
self.client.get(endpoint, headers=get_auth_headers(self.token), name=name)
-19
View File
@@ -1,19 +0,0 @@
import os
USER_EMAIL = os.environ.get("USER_EMAIL")
USER_PASSWORD = os.environ.get("USER_PASSWORD")
BASE_HEADERS = {"Content-Type": "application/vnd.api+json"}
FINDINGS_UI_SORT_VALUES = ["severity", "status", "-inserted_at"]
TARGET_INSERTED_AT = os.environ.get("TARGET_INSERTED_AT", "2025-04-22")
FINDINGS_RESOURCE_METADATA = {
"regions": "region",
"resource_types": "resource_type",
"services": "service",
}
S_PROVIDER_NAME = "provider-50k"
M_PROVIDER_NAME = "provider-250k"
L_PROVIDER_NAME = "provider-500k"
-168
View File
@@ -1,168 +0,0 @@
import random
from collections import defaultdict
from threading import Lock
import requests
from locust import HttpUser, between
from utils.config import (
BASE_HEADERS,
FINDINGS_RESOURCE_METADATA,
TARGET_INSERTED_AT,
USER_EMAIL,
USER_PASSWORD,
)
_global_page_counters = defaultdict(int)
_page_lock = Lock()
class APIUserBase(HttpUser):
"""
Base class for API user simulation in Locust performance tests.
Attributes:
abstract (bool): Indicates this is an abstract user class.
wait_time: Time between task executions, randomized between 1 and 5 seconds.
"""
abstract = True
wait_time = between(1, 5)
def _next_page(self, endpoint_name: str) -> int:
"""
Returns the next page number for a given endpoint. Thread-safe.
Args:
endpoint_name (str): Name of the API endpoint being paginated.
Returns:
int: The next page number for the given endpoint.
"""
with _page_lock:
_global_page_counters[endpoint_name] += 1
return _global_page_counters[endpoint_name]
def get_next_resource_filter(available_values: dict) -> tuple:
"""
Randomly selects a filter type and value from available options.
Args:
available_values (dict): Dictionary with filter types as keys and list of possible values.
Returns:
tuple: A (filter_type, filter_value) pair randomly selected.
"""
filter_type = random.choice(list(available_values.keys()))
filter_value = random.choice(available_values[filter_type])
return filter_type, filter_value
def get_auth_headers(token: str) -> dict:
"""
Returns the headers for the API requests.
Args:
token (str): The token to be included in the headers.
Returns:
dict: The headers for the API requests.
"""
return {
"Authorization": f"Bearer {token}",
**BASE_HEADERS,
}
def get_api_token(host: str) -> str:
"""
Authenticates with the API and retrieves a bearer token.
Args:
host (str): The host URL of the API.
Returns:
str: The access token for authenticated requests.
Raises:
AssertionError: If the request fails or does not return a 200 status code.
"""
login_payload = {
"data": {
"type": "tokens",
"attributes": {"email": USER_EMAIL, "password": USER_PASSWORD},
}
}
response = requests.post(f"{host}/tokens", json=login_payload, headers=BASE_HEADERS)
assert response.status_code == 200, f"Failed to get token: {response.text}"
return response.json()["data"]["attributes"]["access"]
def get_scan_id_from_provider_name(host: str, token: str, provider_name: str) -> str:
"""
Retrieves the scan ID associated with a specific provider name.
Args:
host (str): The host URL of the API.
token (str): Bearer token for authentication.
provider_name (str): Name of the provider to filter scans by.
Returns:
str: The ID of the scan.
Raises:
AssertionError: If the request fails or does not return a 200 status code.
"""
response = requests.get(
f"{host}/scans?fields[scans]=id&filter[provider_alias]={provider_name}",
headers=get_auth_headers(token),
)
assert response.status_code == 200, f"Failed to get scan: {response.text}"
return response.json()["data"][0]["id"]
def get_resource_filters_pairs(host: str, token: str, scan_id: str = "") -> dict:
"""
Retrieves and maps resource metadata filter values from the findings endpoint.
Args:
host (str): The host URL of the API.
token (str): Bearer token for authentication.
scan_id (str, optional): Optional scan ID to filter metadata. Defaults to using inserted_at timestamp.
Returns:
dict: A dictionary of resource filter metadata.
Raises:
AssertionError: If the request fails or does not return a 200 status code.
"""
metadata_filters = (
f"filter[scan]={scan_id}"
if scan_id
else f"filter[inserted_at]={TARGET_INSERTED_AT}"
)
response = requests.get(
f"{host}/findings/metadata?{metadata_filters}", headers=get_auth_headers(token)
)
assert (
response.status_code == 200
), f"Failed to get resource filters values: {response.text}"
attributes = response.json()["data"]["attributes"]
return {
FINDINGS_RESOURCE_METADATA[key]: values
for key, values in attributes.items()
if key in FINDINGS_RESOURCE_METADATA.keys()
}
def get_sort_value(sort_values: list) -> str:
"""
Constructs a sort query string from a list of sort keys.
Args:
sort_values (list): The list of sort values to include in the query.
Returns:
str: A formatted sort query string (e.g., "sort=created_at,-severity").
"""
return f"sort={','.join(sort_values)}"
@@ -1,9 +1,6 @@
#!/bin/bash
# Run Prowler against All AWS Accounts in an AWS Organization
# Activate Poetry Environment
eval "$(poetry env activate)"
# Show Prowler Version
prowler -v
+1
View File
@@ -399,6 +399,7 @@ mainConfig:
[
"RSA-1024",
"P-192",
"SHA-1",
]
# AWS EKS Configuration
@@ -16,6 +16,7 @@ spec:
containers:
- name: prowler
image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
command: ["prowler"]
args: ["kubernetes", "-z", "-b"]
imagePullPolicy: {{ .Values.image.pullPolicy }}
volumeMounts:
Binary file not shown.

Before

Width:  |  Height:  |  Size: 68 KiB

+1 -4
View File
@@ -1361,9 +1361,6 @@ video {
.lg\:grid-cols-4 {
grid-template-columns: repeat(4, minmax(0, 1fr));
}
.lg\:grid-cols-5 {
grid-template-columns: repeat(5, minmax(0, 1fr));
}
.lg\:justify-normal {
justify-content: normal;
@@ -1406,4 +1403,4 @@ video {
.\32xl\:w-\[9\%\] {
width: 9%;
}
}
}
+2 -345
View File
@@ -2228,356 +2228,13 @@ def get_section_containers_ens(data, section_1, section_2, section_3, section_4)
return html.Div(section_containers, className="compliance-data-layout")
def get_section_containers_3_levels(data, section_1, section_2, section_3):
data["STATUS"] = data["STATUS"].apply(map_status_to_icon)
findings_counts_marco = (
data.groupby([section_1, "STATUS"]).size().unstack(fill_value=0)
)
section_containers = []
data[section_1] = data[section_1].astype(str)
data[section_2] = data[section_2].astype(str)
data[section_3] = data[section_3].astype(str)
data.sort_values(
by=section_3,
key=lambda x: x.map(extract_numeric_values),
ascending=True,
inplace=True,
)
for marco in data[section_1].unique():
success_marco = findings_counts_marco.loc[marco].get(pass_emoji, 0)
failed_marco = findings_counts_marco.loc[marco].get(fail_emoji, 0)
fig_name = go.Figure(
[
go.Bar(
name="Failed",
x=[failed_marco],
y=[""],
orientation="h",
marker=dict(color="#e77676"),
width=[0.8],
),
go.Bar(
name="Success",
x=[success_marco],
y=[""],
orientation="h",
marker=dict(color="#45cc6e"),
width=[0.8],
),
]
)
fig_name.update_layout(
barmode="stack",
margin=dict(l=10, r=10, t=10, b=10),
paper_bgcolor="rgba(0,0,0,0)",
plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
width=350,
height=30,
xaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
yaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
annotations=[
dict(
x=success_marco + failed_marco,
y=0,
xref="x",
yref="y",
text=str(success_marco),
showarrow=False,
font=dict(color="#45cc6e", size=14),
xanchor="left",
yanchor="middle",
),
dict(
x=0,
y=0,
xref="x",
yref="y",
text=str(failed_marco),
showarrow=False,
font=dict(color="#e77676", size=14),
xanchor="right",
yanchor="middle",
),
],
)
fig_name.add_annotation(
x=failed_marco,
y=0.3,
text="|",
showarrow=False,
font=dict(size=20),
xanchor="center",
yanchor="middle",
)
graph_div = html.Div(
dcc.Graph(
figure=fig_name, config={"staticPlot": True}, className="info-bar"
),
className="graph-section",
)
direct_internal_items = []
for categoria in data[data[section_1] == marco][section_2].unique():
specific_data = data[
(data[section_1] == marco) & (data[section_2] == categoria)
]
findings_counts_categoria = (
specific_data.groupby([section_2, "STATUS"])
.size()
.unstack(fill_value=0)
)
success_categoria = findings_counts_categoria.loc[categoria].get(
pass_emoji, 0
)
failed_categoria = findings_counts_categoria.loc[categoria].get(
fail_emoji, 0
)
fig_section = go.Figure(
[
go.Bar(
name="Failed",
x=[failed_categoria],
y=[""],
orientation="h",
marker=dict(color="#e77676"),
width=[0.8],
),
go.Bar(
name="Success",
x=[success_categoria],
y=[""],
orientation="h",
marker=dict(color="#45cc6e"),
width=[0.8],
),
]
)
fig_section.update_layout(
barmode="stack",
margin=dict(l=10, r=10, t=10, b=10),
paper_bgcolor="rgba(0,0,0,0)",
plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
width=350,
height=30,
xaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
yaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
annotations=[
dict(
x=success_categoria + failed_categoria,
y=0,
xref="x",
yref="y",
text=str(success_categoria),
showarrow=False,
font=dict(color="#45cc6e", size=14),
xanchor="left",
yanchor="middle",
),
dict(
x=0,
y=0,
xref="x",
yref="y",
text=str(failed_categoria),
showarrow=False,
font=dict(color="#e77676", size=14),
xanchor="right",
yanchor="middle",
),
],
)
fig_section.add_annotation(
x=failed_categoria,
y=0.3,
text="|",
showarrow=False,
font=dict(size=20),
xanchor="center",
yanchor="middle",
)
graph_div_section = html.Div(
dcc.Graph(
figure=fig_section,
config={"staticPlot": True},
className="info-bar-child",
),
className="graph-section-req",
)
direct_internal_items_idgrupocontrol = []
for idgrupocontrol in specific_data[section_3].unique():
specific_data2 = specific_data[
specific_data[section_3] == idgrupocontrol
]
findings_counts_idgrupocontrol = (
specific_data2.groupby([section_3, "STATUS"])
.size()
.unstack(fill_value=0)
)
success_idgrupocontrol = findings_counts_idgrupocontrol.loc[
idgrupocontrol
].get(pass_emoji, 0)
failed_idgrupocontrol = findings_counts_idgrupocontrol.loc[
idgrupocontrol
].get(fail_emoji, 0)
fig_idgrupocontrol = go.Figure(
[
go.Bar(
name="Failed",
x=[failed_idgrupocontrol],
y=[""],
orientation="h",
marker=dict(color="#e77676"),
width=[0.8],
),
go.Bar(
name="Success",
x=[success_idgrupocontrol],
y=[""],
orientation="h",
marker=dict(color="#45cc6e"),
width=[0.8],
),
]
)
fig_idgrupocontrol.update_layout(
barmode="stack",
margin=dict(l=10, r=10, t=10, b=10),
paper_bgcolor="rgba(0,0,0,0)",
plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
width=350,
height=30,
xaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
yaxis=dict(showticklabels=False, showgrid=False, zeroline=False),
annotations=[
dict(
x=success_idgrupocontrol + failed_idgrupocontrol,
y=0,
xref="x",
yref="y",
text=str(success_idgrupocontrol),
showarrow=False,
font=dict(color="#45cc6e", size=14),
xanchor="left",
yanchor="middle",
),
dict(
x=0,
y=0,
xref="x",
yref="y",
text=str(failed_idgrupocontrol),
showarrow=False,
font=dict(color="#e77676", size=14),
xanchor="right",
yanchor="middle",
),
],
)
fig_idgrupocontrol.add_annotation(
x=failed_idgrupocontrol,
y=0.3,
text="|",
showarrow=False,
font=dict(size=20),
xanchor="center",
yanchor="middle",
)
graph_div_idgrupocontrol = html.Div(
dcc.Graph(
figure=fig_idgrupocontrol,
config={"staticPlot": True},
className="info-bar-child",
),
className="graph-section-req",
)
data_table = dash_table.DataTable(
data=specific_data2.to_dict("records"),
columns=[
{"name": i, "id": i}
for i in [
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
],
style_table={"overflowX": "auto"},
style_as_list_view=True,
style_cell={"textAlign": "left", "padding": "5px"},
)
internal_accordion_item_2 = dbc.AccordionItem(
title=idgrupocontrol,
children=[
graph_div_idgrupocontrol,
html.Div([data_table], className="inner-accordion-content"),
],
)
direct_internal_items_idgrupocontrol.append(
html.Div(
[
graph_div_idgrupocontrol,
dbc.Accordion(
[internal_accordion_item_2],
start_collapsed=True,
flush=True,
),
],
className="accordion-inner--child",
)
)
internal_accordion_item = dbc.AccordionItem(
title=categoria,
children=direct_internal_items_idgrupocontrol,
)
internal_section_container = html.Div(
[
graph_div_section,
dbc.Accordion(
[internal_accordion_item], start_collapsed=True, flush=True
),
],
className="accordion-inner--child",
)
direct_internal_items.append(internal_section_container)
accordion_item = dbc.AccordionItem(title=marco, children=direct_internal_items)
section_container = html.Div(
[
graph_div,
dbc.Accordion([accordion_item], start_collapsed=True, flush=True),
],
className="accordion-inner",
)
section_containers.append(section_container)
return html.Div(section_containers, className="compliance-data-layout")
# This function extracts and compares up to two numeric values, ensuring correct sorting for version-like strings.
def extract_numeric_values(value):
numbers = re.findall(r"\d+", str(value))
if len(numbers) == 3:
return int(numbers[0]), int(numbers[1]), int(numbers[2])
elif len(numbers) == 2:
if len(numbers) >= 2:
return int(numbers[0]), int(numbers[1])
elif len(numbers) == 1:
return int(numbers[0])
return int(numbers[0]), 0
return 0, 0
@@ -1,6 +1,6 @@
import warnings
from dashboard.common_methods import get_section_containers_3_levels
from dashboard.common_methods import get_section_containers_format2
warnings.filterwarnings("ignore")
@@ -10,7 +10,6 @@ def get_table(data):
[
"REQUIREMENTS_ATTRIBUTES_NAME",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"CHECKID",
"STATUS",
"REGION",
@@ -18,10 +17,6 @@ def get_table(data):
"RESOURCEID",
]
]
return get_section_containers_3_levels(
aux,
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"REQUIREMENTS_ATTRIBUTES_NAME",
return get_section_containers_format2(
aux, "REQUIREMENTS_ATTRIBUTES_NAME", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
@@ -1,6 +1,6 @@
import warnings
from dashboard.common_methods import get_section_containers_3_levels
from dashboard.common_methods import get_section_containers_format2
warnings.filterwarnings("ignore")
@@ -10,7 +10,6 @@ def get_table(data):
[
"REQUIREMENTS_ATTRIBUTES_NAME",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"CHECKID",
"STATUS",
"REGION",
@@ -19,9 +18,6 @@ def get_table(data):
]
]
return get_section_containers_3_levels(
aux,
"REQUIREMENTS_ATTRIBUTES_SECTION",
"REQUIREMENTS_ATTRIBUTES_SUBSECTION",
"REQUIREMENTS_ATTRIBUTES_NAME",
return get_section_containers_format2(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ATTRIBUTES_NAME"
)
-24
View File
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_cis
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_cis(
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
+4 -7
View File
@@ -1,6 +1,6 @@
import warnings
from dashboard.common_methods import get_section_containers_3_levels
from dashboard.common_methods import get_section_containers_kisa_ismsp
warnings.filterwarnings("ignore")
@@ -8,7 +8,7 @@ warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ATTRIBUTES_DOMAIN",
"REQUIREMENTS_ID",
"REQUIREMENTS_ATTRIBUTES_SUBDOMAIN",
"REQUIREMENTS_ATTRIBUTES_SECTION",
# "REQUIREMENTS_DESCRIPTION",
@@ -20,9 +20,6 @@ def get_table(data):
]
].copy()
return get_section_containers_3_levels(
aux,
"REQUIREMENTS_ATTRIBUTES_DOMAIN",
"REQUIREMENTS_ATTRIBUTES_SUBDOMAIN",
"REQUIREMENTS_ATTRIBUTES_SECTION",
return get_section_containers_kisa_ismsp(
aux, "REQUIREMENTS_ATTRIBUTES_SUBDOMAIN", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
@@ -1,6 +1,6 @@
import warnings
from dashboard.common_methods import get_section_containers_3_levels
from dashboard.common_methods import get_section_containers_kisa_ismsp
warnings.filterwarnings("ignore")
@@ -8,7 +8,7 @@ warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ATTRIBUTES_DOMAIN",
"REQUIREMENTS_ID",
"REQUIREMENTS_ATTRIBUTES_SUBDOMAIN",
"REQUIREMENTS_ATTRIBUTES_SECTION",
# "REQUIREMENTS_DESCRIPTION",
@@ -20,9 +20,6 @@ def get_table(data):
]
].copy()
return get_section_containers_3_levels(
aux,
"REQUIREMENTS_ATTRIBUTES_DOMAIN",
"REQUIREMENTS_ATTRIBUTES_SUBDOMAIN",
"REQUIREMENTS_ATTRIBUTES_SECTION",
return get_section_containers_kisa_ismsp(
aux, "REQUIREMENTS_ATTRIBUTES_SUBDOMAIN", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_cis
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_cis(
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_cis
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_cis(
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_cis
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_cis(
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
)
-24
View File
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
-24
View File
@@ -1,24 +0,0 @@
import warnings
from dashboard.common_methods import get_section_containers_format3
warnings.filterwarnings("ignore")
def get_table(data):
aux = data[
[
"REQUIREMENTS_ID",
"REQUIREMENTS_DESCRIPTION",
"REQUIREMENTS_ATTRIBUTES_SECTION",
"CHECKID",
"STATUS",
"REGION",
"ACCOUNTID",
"RESOURCEID",
]
].copy()
return get_section_containers_format3(
aux, "REQUIREMENTS_ATTRIBUTES_SECTION", "REQUIREMENTS_ID"
)
+1 -2
View File
@@ -57,9 +57,8 @@ def create_layout_overview(
html.Div(className="flex", id="azure_card", n_clicks=0),
html.Div(className="flex", id="gcp_card", n_clicks=0),
html.Div(className="flex", id="k8s_card", n_clicks=0),
html.Div(className="flex", id="m365_card", n_clicks=0),
],
className="grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-5",
className="grid gap-x-4 mb-[30px] sm:grid-cols-2 lg:grid-cols-4",
),
html.H4(
"Count of Findings by severity",
+3 -117
View File
@@ -76,8 +76,6 @@ def load_csv_files(csv_files):
result = result.replace("_AZURE", " - AZURE")
if "KUBERNETES" in result:
result = result.replace("_KUBERNETES", " - KUBERNETES")
if "M65" in result:
result = result.replace("_M65", " - M65")
results.append(result)
unique_results = set(results)
@@ -269,15 +267,6 @@ def display_data(
data["REQUIREMENTS_ATTRIBUTES_PROFILE"] = data[
"REQUIREMENTS_ATTRIBUTES_PROFILE"
].apply(lambda x: x.split(" - ")[0])
# Add the column ACCOUNTID to the data if the provider is m65
if "m365" in analytics_input:
data.rename(columns={"TENANTID": "ACCOUNTID"}, inplace=True)
data.rename(columns={"LOCATION": "REGION"}, inplace=True)
if "REQUIREMENTS_ATTRIBUTES_PROFILE" in data.columns:
data["REQUIREMENTS_ATTRIBUTES_PROFILE"] = data[
"REQUIREMENTS_ATTRIBUTES_PROFILE"
].apply(lambda x: x.split(" - ")[0])
# Filter the chosen level of the CIS
if is_level_1:
data = data[data["REQUIREMENTS_ATTRIBUTES_PROFILE"] == "Level 1"]
@@ -408,13 +397,7 @@ def display_data(
compliance_module = importlib.import_module(
f"dashboard.compliance.{current}"
)
data = data.drop_duplicates(
subset=["CHECKID", "STATUS", "MUTED", "RESOURCEID", "STATUSEXTENDED"]
)
if "threatscore" in analytics_input:
data = get_threatscore_mean_by_pillar(data)
data.drop_duplicates(keep="first", inplace=True)
table = compliance_module.get_table(data)
except ModuleNotFoundError:
table = html.Div(
@@ -433,9 +416,6 @@ def display_data(
)
df = data.copy()
# Remove Muted rows
if "MUTED" in df.columns:
df = df[df["MUTED"] == "False"]
df = df.groupby(["STATUS"]).size().reset_index(name="counts")
df = df.sort_values(by=["counts"], ascending=False)
@@ -450,9 +430,6 @@ def display_data(
if "pci" in analytics_input:
pie_2 = get_bar_graph(df, "REQUIREMENTS_ID")
current_filter = "req_id"
elif "threatscore" in analytics_input:
pie_2 = get_table_prowler_threatscore(df)
current_filter = "threatscore"
elif (
"REQUIREMENTS_ATTRIBUTES_SECTION" in df.columns
and not df["REQUIREMENTS_ATTRIBUTES_SECTION"].isnull().values.any()
@@ -511,13 +488,6 @@ def display_data(
pie_2, f"Top 5 failed {current_filter} by requirements"
)
if "threatscore" in analytics_input:
security_level_graph = get_graph(
pie_2,
"Pillar Score by requirements (1 = Lowest Risk, 5 = Highest Risk)",
margin_top=0,
)
return (
table_output,
overall_status_result_graph,
@@ -531,7 +501,7 @@ def display_data(
)
def get_graph(pie, title, margin_top=7):
def get_graph(pie, title):
return [
html.Span(
title,
@@ -544,7 +514,7 @@ def get_graph(pie, title, margin_top=7):
"display": "flex",
"justify-content": "center",
"align-items": "center",
"margin-top": f"{margin_top}%",
"margin-top": "7%",
},
),
]
@@ -648,87 +618,3 @@ def get_table(current_compliance, table):
className="relative flex flex-col bg-white shadow-provider rounded-xl px-4 py-3 flex-wrap w-full",
),
]
def get_threatscore_mean_by_pillar(df):
modified_df = df[df["STATUS"] == "FAIL"]
modified_df["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"] = pd.to_numeric(
modified_df["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"], errors="coerce"
)
pillar_means = (
modified_df.groupby("REQUIREMENTS_ATTRIBUTES_SECTION")[
"REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"
]
.mean()
.round(2)
)
output = []
for pillar, mean in pillar_means.items():
output.append(f"{pillar} - [{mean}]")
for value in output:
if value.split(" - ")[0] in df["REQUIREMENTS_ATTRIBUTES_SECTION"].values:
df.loc[
df["REQUIREMENTS_ATTRIBUTES_SECTION"] == value.split(" - ")[0],
"REQUIREMENTS_ATTRIBUTES_SECTION",
] = value
return df
def get_table_prowler_threatscore(df):
df = df[df["STATUS"] == "FAIL"]
# Delete " - " from the column REQUIREMENTS_ATTRIBUTES_SECTION
df["REQUIREMENTS_ATTRIBUTES_SECTION"] = (
df["REQUIREMENTS_ATTRIBUTES_SECTION"].str.split(" - ").str[0]
)
df["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"] = pd.to_numeric(
df["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"], errors="coerce"
)
score_df = (
df.groupby("REQUIREMENTS_ATTRIBUTES_SECTION")[
"REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"
]
.mean()
.reset_index()
.rename(
columns={
"REQUIREMENTS_ATTRIBUTES_SECTION": "Pillar",
"REQUIREMENTS_ATTRIBUTES_LEVELOFRISK": "Score",
}
)
)
fig = px.bar(
score_df,
x="Pillar",
y="Score",
color="Score",
color_continuous_scale=[
"#45cc6e",
"#f4d44d",
"#e77676",
], # verde → amarillo → rojo
hover_data={"Score": True, "Pillar": True},
labels={"Score": "Average Risk Score", "Pillar": "Section"},
height=400,
)
fig.update_layout(
xaxis_title="Pillar",
yaxis_title="Level of Risk",
margin=dict(l=20, r=20, t=30, b=20),
plot_bgcolor="rgba(0,0,0,0)",
paper_bgcolor="rgba(0,0,0,0)",
coloraxis_colorbar=dict(title="Risk"),
)
return dcc.Graph(
figure=fig,
style={"height": "25rem", "width": "40rem"},
)
-43
View File
@@ -74,9 +74,6 @@ gcp_provider_logo = html.Img(
ks8_provider_logo = html.Img(
src="assets/images/providers/k8s_provider.png", alt="k8s provider"
)
m365_provider_logo = html.Img(
src="assets/images/providers/m365_provider.png", alt="m365 provider"
)
def load_csv_files(csv_files):
@@ -226,8 +223,6 @@ else:
accounts.append(account + " - AZURE")
if "gcp" in list(data[data["ACCOUNT_NAME"] == account]["PROVIDER"]):
accounts.append(account + " - GCP")
if "m365" in list(data[data["ACCOUNT_NAME"] == account]["PROVIDER"]):
accounts.append(account + " - M365")
if "ACCOUNT_UID" in data.columns:
for account in data["ACCOUNT_UID"].unique():
@@ -278,8 +273,6 @@ else:
services.append(service + " - AZURE")
if "gcp" in list(data[data["SERVICE_NAME"] == service]["PROVIDER"]):
services.append(service + " - GCP")
if "m365" in list(data[data["SERVICE_NAME"] == service]["PROVIDER"]):
services.append(service + " - M365")
services = ["All"] + services
services = [
@@ -492,7 +485,6 @@ else:
Output("azure_card", "children"),
Output("gcp_card", "children"),
Output("k8s_card", "children"),
Output("m365_card", "children"),
Output("subscribe_card", "children"),
Output("info-file-over", "title"),
Output("severity-filter", "value"),
@@ -507,7 +499,6 @@ else:
Output("azure_card", "n_clicks"),
Output("gcp_card", "n_clicks"),
Output("k8s_card", "n_clicks"),
Output("m365_card", "n_clicks"),
],
Input("cloud-account-filter", "value"),
Input("region-filter", "value"),
@@ -522,7 +513,6 @@ else:
Input("azure_card", "n_clicks"),
Input("gcp_card", "n_clicks"),
Input("k8s_card", "n_clicks"),
Input("m365_card", "n_clicks"),
Input("sort_button_check_name", "n_clicks"),
Input("sort_button_severity", "n_clicks"),
Input("sort_button_status", "n_clicks"),
@@ -544,7 +534,6 @@ def filter_data(
azure_clicks,
gcp_clicks,
k8s_clicks,
m365_clicks,
sort_button_check_name,
sort_button_severity,
sort_button_status,
@@ -565,7 +554,6 @@ def filter_data(
azure_clicks = 0
gcp_clicks = 0
k8s_clicks = 0
m365_clicks = 0
if azure_clicks > 0:
filtered_data = data.copy()
if azure_clicks % 2 != 0 and "azure" in list(data["PROVIDER"]):
@@ -573,7 +561,6 @@ def filter_data(
aws_clicks = 0
gcp_clicks = 0
k8s_clicks = 0
m365_clicks = 0
if gcp_clicks > 0:
filtered_data = data.copy()
if gcp_clicks % 2 != 0 and "gcp" in list(data["PROVIDER"]):
@@ -581,7 +568,6 @@ def filter_data(
aws_clicks = 0
azure_clicks = 0
k8s_clicks = 0
m365_clicks = 0
if k8s_clicks > 0:
filtered_data = data.copy()
if k8s_clicks % 2 != 0 and "kubernetes" in list(data["PROVIDER"]):
@@ -589,15 +575,6 @@ def filter_data(
aws_clicks = 0
azure_clicks = 0
gcp_clicks = 0
m365_clicks = 0
if m365_clicks > 0:
filtered_data = data.copy()
if m365_clicks % 2 != 0 and "m365" in list(data["PROVIDER"]):
filtered_data = filtered_data[filtered_data["PROVIDER"] == "m365"]
aws_clicks = 0
azure_clicks = 0
gcp_clicks = 0
k8s_clicks = 0
# For all the data, we will add to the status column the value 'MUTED (FAIL)' and 'MUTED (PASS)' depending on the value of the column 'STATUS' and 'MUTED'
if "MUTED" in filtered_data.columns:
@@ -698,8 +675,6 @@ def filter_data(
all_account_names.append(account)
if "gcp" in list(data[data["ACCOUNT_NAME"] == account]["PROVIDER"]):
all_account_names.append(account)
if "m365" in list(data[data["ACCOUNT_NAME"] == account]["PROVIDER"]):
all_account_names.append(account)
all_items = all_account_ids + all_account_names + ["All"]
@@ -717,8 +692,6 @@ def filter_data(
cloud_accounts_options.append(item + " - AZURE")
if "gcp" in list(data[data["ACCOUNT_NAME"] == item]["PROVIDER"]):
cloud_accounts_options.append(item + " - GCP")
if "m365" in list(data[data["ACCOUNT_NAME"] == item]["PROVIDER"]):
cloud_accounts_options.append(item + " - M365")
# Filter ACCOUNT
if cloud_account_values == ["All"]:
@@ -817,7 +790,6 @@ def filter_data(
service_filter_options = ["All"]
all_items = filtered_data["SERVICE_NAME"].unique()
for item in all_items:
if item not in service_filter_options and item.__class__.__name__ == "str":
if "aws" in list(
@@ -836,10 +808,6 @@ def filter_data(
filtered_data[filtered_data["SERVICE_NAME"] == item]["PROVIDER"]
):
service_filter_options.append(item + " - GCP")
if "m365" in list(
filtered_data[filtered_data["SERVICE_NAME"] == item]["PROVIDER"]
):
service_filter_options.append(item + " - M365")
# Filter Service
if service_values == ["All"]:
@@ -1267,10 +1235,6 @@ def filter_data(
filtered_data.loc[
filtered_data["ACCOUNT_UID"] == account, "ACCOUNT_UID"
] = (account + " - GCP")
if "m365" in list(data[data["ACCOUNT_UID"] == account]["PROVIDER"]):
filtered_data.loc[
filtered_data["ACCOUNT_UID"] == account, "ACCOUNT_UID"
] = (account + " - M365")
table_collapsible = []
for item in filtered_data.to_dict("records"):
@@ -1338,9 +1302,6 @@ def filter_data(
k8s_card = create_provider_card(
"kubernetes", ks8_provider_logo, "Clusters", full_filtered_data
)
m365_card = create_provider_card(
"m365", m365_provider_logo, "Accounts", full_filtered_data
)
# Subscribe to prowler SaaS card
subscribe_card = [
@@ -1385,7 +1346,6 @@ def filter_data(
azure_card,
gcp_card,
k8s_card,
m365_card,
subscribe_card,
list_files,
severity_values,
@@ -1400,7 +1360,6 @@ def filter_data(
azure_clicks,
gcp_clicks,
k8s_clicks,
m365_clicks,
)
else:
return (
@@ -1418,7 +1377,6 @@ def filter_data(
azure_card,
gcp_card,
k8s_card,
m365_card,
subscribe_card,
list_files,
severity_values,
@@ -1433,7 +1391,6 @@ def filter_data(
azure_clicks,
gcp_clicks,
k8s_clicks,
m365_clicks,
)
+1 -1
View File
@@ -175,7 +175,7 @@ Due to the complexity and differences of each provider use the rest of the provi
- [GCP](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/gcp/gcp_provider.py)
- [Azure](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/azure/azure_provider.py)
- [Kubernetes](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/kubernetes/kubernetes_provider.py)
- [M365](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/m365/m365_provider.py)
- [Microsoft365](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/microsoft365/microsoft365_provider.py)
To facilitate understanding here is a pseudocode of how the most basic provider could be with examples.
+1 -1
View File
@@ -237,4 +237,4 @@ It is really important to check if the current Prowler's permissions for each pr
- AWS: https://docs.prowler.cloud/en/latest/getting-started/requirements/#aws-authentication
- Azure: https://docs.prowler.cloud/en/latest/getting-started/requirements/#permissions
- GCP: https://docs.prowler.cloud/en/latest/getting-started/requirements/#gcp-authentication
- M365: https://docs.prowler.cloud/en/latest/getting-started/requirements/#m365-authentication
- Microsoft365: https://docs.prowler.cloud/en/latest/getting-started/requirements/#microsoft365-authentication
+12 -347
View File
@@ -40,8 +40,8 @@ If your IAM entity enforces MFA you can use `--mfa` and Prowler will ask you to
Prowler for Azure supports the following authentication types. To use each one you need to pass the proper flag to the execution:
- [Service Principal Application](https://learn.microsoft.com/en-us/entra/identity-platform/app-objects-and-service-principals?tabs=browser#service-principal-object) (recommended).
- Current AZ CLI credentials stored.
- [Service principal application](https://learn.microsoft.com/en-us/entra/identity-platform/app-objects-and-service-principals?tabs=browser#service-principal-object) (recommended).
- Current az cli credentials stored.
- Interactive browser authentication.
- [Managed identity](https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/overview) authentication.
@@ -59,7 +59,7 @@ export AZURE_CLIENT_SECRET="XXXXXXX"
```
If you try to execute Prowler with the `--sp-env-auth` flag and those variables are empty or not exported, the execution is going to fail.
Follow the instructions in the [Create Prowler Service Principal](../tutorials/azure/create-prowler-service-principal.md#how-to-create-prowler-service-principal-application) section to create a service principal.
Follow the instructions in the [Create Prowler Service Principal](../tutorials/azure/create-prowler-service-principal.md#how-to-create-prowler-service-principal) section to create a service principal.
### AZ CLI / Browser / Managed Identity authentication
@@ -79,7 +79,7 @@ Prowler for Azure needs two types of permission scopes to be set:
???+ note
Please, notice that the field `assignableScopes` in the JSON custom role file must be changed to be the subscription or management group where the role is going to be assigned. The valid formats for the field are `/subscriptions/<subscription-id>` or `/providers/Microsoft.Management/managementGroups/<management-group-id>`.
To assign the permissions, follow the instructions in the [Microsoft Entra ID permissions](../tutorials/azure/create-prowler-service-principal.md#assigning-the-proper-permissions) section and the [Azure subscriptions permissions](../tutorials/azure/subscriptions.md#assign-the-appropriate-permissions-to-the-identity-that-is-going-to-be-assumed-by-prowler) section, respectively.
To assign the permissions, follow the instructions in the [Microsoft Entra ID permissions](../tutorials/azure/create-prowler-service-principal.md#assigning-the-proper-permissions) section and the [Azure subscriptions permissions](../tutorials/azure/subscriptions.md#assigning-proper-permissions) section, respectively.
#### Checks that require ProwlerRole
@@ -98,44 +98,25 @@ Prowler will follow the same credentials search as [Google authentication librar
2. [User credentials set up by using the Google Cloud CLI](https://cloud.google.com/docs/authentication/application-default-credentials#personal)
3. [The attached service account, returned by the metadata server](https://cloud.google.com/docs/authentication/application-default-credentials#attached-sa)
### Needed permissions
Prowler for Google Cloud needs the following permissions to be set:
- **Viewer (`roles/viewer`) IAM role**: granted at the project / folder / org level in order to scan the target projects
- **Project level settings**: you need to have at least one project with the below settings:
- Identity and Access Management (IAM) API (`iam.googleapis.com`) enabled by either using the
[Google Cloud API UI](https://console.cloud.google.com/apis/api/iam.googleapis.com/metrics) or
by using the gcloud CLI `gcloud services enable iam.googleapis.com --project <your-project-id>` command
- Service Usage Consumer (`roles/serviceusage.serviceUsageConsumer`) IAM role
- Set the quota project to be this project by either running `gcloud auth application-default set-quota-project <project-id>` or by setting an environment variable:
`export GOOGLE_CLOUD_QUOTA_PROJECT=<project-id>`
The above settings must be associated to a user or service account.
Those credentials must be associated to a user or service account with proper permissions to do all checks. To make sure, add the `Viewer` role to the member associated with the credentials.
???+ note
By default, `prowler` will scan all accessible GCP Projects, use flag `--project-ids` to specify the projects to be scanned.
## Microsoft 365
## Microsoft365
Prowler for M365 currently supports the following authentication types:
Prowler for Microsoft365 currently supports the following authentication types:
- [Service Principal Application](https://learn.microsoft.com/en-us/entra/identity-platform/app-objects-and-service-principals?tabs=browser#service-principal-object).
- Service Principal Application and Microsoft User Credentials (**recommended**).
- Current AZ CLI credentials stored.
- [Service principal application](https://learn.microsoft.com/en-us/entra/identity-platform/app-objects-and-service-principals?tabs=browser#service-principal-object) (recommended).
- Current az cli credentials stored.
- Interactive browser authentication.
???+ warning
For Prowler App only the Service Principal with User Credentials authentication method is supported.
For Prowler App only the Service Principal with an application authentication method is supported.
### Service Principal authentication
Authentication flag: `--sp-env-auth`
To allow Prowler assume the service principal identity to start the scan it is needed to configure the following environment variables:
```console
@@ -145,324 +126,8 @@ export AZURE_TENANT_ID="XXXXXXXXX"
```
If you try to execute Prowler with the `--sp-env-auth` flag and those variables are empty or not exported, the execution is going to fail.
Follow the instructions in the [Create Prowler Service Principal](../tutorials/microsoft365/getting-started-m365.md#create-the-service-principal-app) section to create a service principal.
With this credentials you will only be able to run the checks that work through MS Graph, this means that you won't run all the provider. If you want to scan all the checks from M365 you will need to use the recommended authentication method.
### Service Principal and User Credentials authentication (recommended)
Authentication flag: `--env-auth`
This authentication method follows the same approach as the service principal method but introduces two additional environment variables for user credentials: `M365_USER` and `M365_ENCRYPTED_PASSWORD`.
```console
export AZURE_CLIENT_ID="XXXXXXXXX"
export AZURE_CLIENT_SECRET="XXXXXXXXX"
export AZURE_TENANT_ID="XXXXXXXXX"
export M365_USER="your_email@example.com"
export M365_ENCRYPTED_PASSWORD="6500780061006d0070006c006500700061007300730077006f0072006400" # replace this to yours
```
These two new environment variables are **required** to execute the PowerShell modules needed to retrieve information from M365 services. Prowler uses Service Principal authentication to access Microsoft Graph and user credentials to authenticate to Microsoft PowerShell modules.
- `M365_USER` should be your Microsoft account email using the default domain. This means it must look like `example@YourCompany.onmicrosoft.com`.
To ensure that you are using the default domain you can see how to verify it [here](../tutorials/microsoft365/getting-started-m365.md#step-1-obtain-your-domain).
If you don't have a user created with that domain, Prowler will not work as it will not be able to ensure both app an user belong to the same tenant. To proceed, you can either create a new user with that domain or modify the domain of an existing user.
![User Domains](../tutorials/microsoft365/img/user-domains.png)
- `M365_ENCRYPTED_PASSWORD` must be an encrypted SecureString. To convert your password into a valid encrypted string, you need to use PowerShell.
???+ warning
Passwords encrypted using ConvertTo-SecureString can only be decrypted on the same OS/user context. If you generate an encrypted password on macOS or Linux (both UNIX), it should fail on Windows and vice versa. As Prowler Cloud runs on UNIX if you generate your password using Windows it won't work so you'll need to generate a new password using any UNIX distro (example above)
If you are working from Windows and you will use your encrypted password in a different system (like for example executing Prowler in macOS or adding your password to Prowler Cloud), you will need to generate a "UNIX compatible" version of your encrypted password. This can be done using WSL which is so easy to install on Windows.
=== "UNIX"
Open a PowerShell cmd with a [supported version](requirements.md#supported-powershell-versions) and then run the following command:
```console
$securePassword = ConvertTo-SecureString "examplepassword" -AsPlainText -Force
$encryptedPassword = $securePassword | ConvertFrom-SecureString
Write-Output $encryptedPassword
6500780061006d0070006c006500700061007300730077006f0072006400
```
If everything is done correctly, you will see the encrypted string that you need to set as the `M365_ENCRYPTED_PASSWORD` environment variable.
=== "Windows"
How to install WSL and PowerShell on it to generate that password (you can use a different distro but this one will work for sure):
```console
wsl --install -d Ubuntu-22.04
```
Then, open the Ubuntu terminal and run the following commands:
```console
sudo apt update && sudo apt install -y wget apt-transport-https software-properties-common
wget -q "https://packages.microsoft.com/config/ubuntu/$(lsb_release -rs)/packages-microsoft-prod.deb"
sudo dpkg -i packages-microsoft-prod.deb
sudo apt update
sudo apt install -y powershell
pwsh
```
With this done you will see now that a prompt running PowerShell with the latest version is open so here you will be able to generate your encrypted password:
```console
$securePassword = ConvertTo-SecureString "examplepassword" -AsPlainText -Force
$encryptedPassword = $securePassword | ConvertFrom-SecureString
Write-Output $encryptedPassword
6500780061006d0070006c006500700061007300730077006f0072006400
```
If everything is done correctly, you will see the encrypted string that you need to set as the `M365_ENCRYPTED_PASSWORD` environment variable.
Follow the instructions in the [Create Prowler Service Principal](../tutorials/azure/create-prowler-service-principal.md) section to create a service principal.
### Interactive Browser authentication
Authentication flag: `--browser-auth`
This authentication method requires the user to authenticate against Azure using the default browser to start the scan, also `--tenant-id` flag is required.
With this credentials you will only be able to run the checks that work through MS Graph, this means that you won't run all the provider. If you want to scan all the checks from M365 you will need to use the recommended authentication method.
Since this is a delegated permission authentication method, necessary permissions should be given to the user, not the app.
### Needed permissions
Prowler for M365 requires two types of permission scopes to be set (if you want to run the full provider including PowerShell checks). Both must be configured using Microsoft Entra ID:
- **Service Principal Application Permissions**: These are set at the **application** level and are used to retrieve data from the identity being assessed:
- `Directory.Read.All`: Required for all services.
- `Policy.Read.All`: Required for all services.
- `User.Read` (IMPORTANT: this must be set as **delegated**): Required for the sign-in.
- `Sites.Read.All`: Required for SharePoint service.
- `SharePointTenantSettings.Read.All`: Required for SharePoint service.
- **Powershell Modules Permissions**: These are set at the `M365_USER` level, so the user used to run Prowler must have one of the following roles:
- `Global Reader` (recommended): this allows you to read all roles needed.
- `Exchange Administrator` and `Teams Administrator`: user needs both roles but with this [roles](https://learn.microsoft.com/en-us/exchange/permissions-exo/permissions-exo#microsoft-365-permissions-in-exchange-online) you can access to the same information as a Global Reader (since only read access is needed, Global Reader is recommended).
In order to know how to assign those permissions and roles follow the instructions in the Microsoft Entra ID [permissions](../tutorials/microsoft365/getting-started-m365.md#grant-required-api-permissions) and [roles](../tutorials/microsoft365/getting-started-m365.md#assign-required-roles-to-your-user) section.
### Supported PowerShell versions
You must have PowerShell installed to run certain M365 checks.
Currently, we support **PowerShell version 7.4 or higher** (7.5 is recommended).
This requirement exists because **PowerShell 5.1** (the version that comes by default on some Windows systems) does not support several cmdlets needed to run the checks properly.
Additionally, earlier [PowerShell Cross-Platform versions](https://learn.microsoft.com/en-us/powershell/scripting/install/powershell-support-lifecycle?view=powershell-7.5) are no longer under technical support, which may cause unexpected errors.
???+ note
Installing powershell will be only needed if you install prowler from pip or other sources, these means that the SDK and API containers contain PowerShell installed by default.
Installing PowerShell is different depending on your OS.
- [Windows](https://learn.microsoft.com/es-es/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.5#install-powershell-using-winget-recommended): you will need to update PowerShell to +7.4 to be able to run prowler, if not some checks will not show findings and the provider could not work as expected. This version of PowerShell is [supported](https://learn.microsoft.com/es-es/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.4#supported-versions-of-windows) on Windows 10, Windows 11, Windows Server 2016 and higher versions.
```console
winget install --id Microsoft.PowerShell --source winget
```
- [MacOS](https://learn.microsoft.com/es-es/powershell/scripting/install/installing-powershell-on-macos?view=powershell-7.5#install-the-latest-stable-release-of-powershell): installing PowerShell on MacOS needs to have installed [brew](https://brew.sh/), once you have it is just running the command above, Pwsh is only supported in macOS 15 (Sequoia) x64 and Arm64, macOS 14 (Sonoma) x64 and Arm64, macOS 13 (Ventura) x64 and Arm64
```console
brew install powershell/tap/powershell
```
Once it's installed run `pwsh` on your terminal to verify it's working.
- Linux: installing PowerShell on Linux depends on the distro you are using:
- [Ubuntu](https://learn.microsoft.com/es-es/powershell/scripting/install/install-ubuntu?view=powershell-7.5#installation-via-package-repository-the-package-repository): The required version for installing PowerShell +7.4 on Ubuntu are Ubuntu 22.04 and Ubuntu 24.04. The recommended way to install it is downloading the package available on PMC. You just need to follow the following steps:
```console
###################################
# Prerequisites
# Update the list of packages
sudo apt-get update
# Install pre-requisite packages.
sudo apt-get install -y wget apt-transport-https software-properties-common
# Get the version of Ubuntu
source /etc/os-release
# Download the Microsoft repository keys
wget -q https://packages.microsoft.com/config/ubuntu/$VERSION_ID/packages-microsoft-prod.deb
# Register the Microsoft repository keys
sudo dpkg -i packages-microsoft-prod.deb
# Delete the Microsoft repository keys file
rm packages-microsoft-prod.deb
# Update the list of packages after we added packages.microsoft.com
sudo apt-get update
###################################
# Install PowerShell
sudo apt-get install -y powershell
# Start PowerShell
pwsh
```
- [Alpine](https://learn.microsoft.com/es-es/powershell/scripting/install/install-alpine?view=powershell-7.5#installation-steps): The only supported version for installing PowerShell +7.4 on Alpine is Alpine 3.20. The unique way to install it is downloading the tar.gz package available on [PowerShell github](https://github.com/PowerShell/PowerShell/releases/download/v7.5.0/powershell-7.5.0-linux-musl-x64.tar.gz). You just need to follow the following steps:
```console
# Install the requirements
sudo apk add --no-cache \
ca-certificates \
less \
ncurses-terminfo-base \
krb5-libs \
libgcc \
libintl \
libssl3 \
libstdc++ \
tzdata \
userspace-rcu \
zlib \
icu-libs \
curl
apk -X https://dl-cdn.alpinelinux.org/alpine/edge/main add --no-cache \
lttng-ust \
openssh-client \
# Download the powershell '.tar.gz' archive
curl -L https://github.com/PowerShell/PowerShell/releases/download/v7.5.0/powershell-7.5.0-linux-musl-x64.tar.gz -o /tmp/powershell.tar.gz
# Create the target folder where powershell will be placed
sudo mkdir -p /opt/microsoft/powershell/7
# Expand powershell to the target folder
sudo tar zxf /tmp/powershell.tar.gz -C /opt/microsoft/powershell/7
# Set execute permissions
sudo chmod +x /opt/microsoft/powershell/7/pwsh
# Create the symbolic link that points to pwsh
sudo ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh
# Start PowerShell
pwsh
```
- [Debian](https://learn.microsoft.com/es-es/powershell/scripting/install/install-debian?view=powershell-7.5#installation-on-debian-11-or-12-via-the-package-repository): The required version for installing PowerShell +7.4 on Debian are Debian 11 and Debian 12. The recommended way to install it is downloading the package available on PMC. You just need to follow the following steps:
```console
###################################
# Prerequisites
# Update the list of packages
sudo apt-get update
# Install pre-requisite packages.
sudo apt-get install -y wget
# Get the version of Debian
source /etc/os-release
# Download the Microsoft repository GPG keys
wget -q https://packages.microsoft.com/config/debian/$VERSION_ID/packages-microsoft-prod.deb
# Register the Microsoft repository GPG keys
sudo dpkg -i packages-microsoft-prod.deb
# Delete the Microsoft repository GPG keys file
rm packages-microsoft-prod.deb
# Update the list of packages after we added packages.microsoft.com
sudo apt-get update
###################################
# Install PowerShell
sudo apt-get install -y powershell
# Start PowerShell
pwsh
```
- [Rhel](https://learn.microsoft.com/es-es/powershell/scripting/install/install-rhel?view=powershell-7.5#installation-via-the-package-repository): The required version for installing PowerShell +7.4 on Red Hat are RHEL 8 and RHEL 9. The recommended way to install it is downloading the package available on PMC. You just need to follow the following steps:
```console
###################################
# Prerequisites
# Get version of RHEL
source /etc/os-release
if [ ${VERSION_ID%.*} -lt 8 ]
then majorver=7
elif [ ${VERSION_ID%.*} -lt 9 ]
then majorver=8
else majorver=9
fi
# Download the Microsoft RedHat repository package
curl -sSL -O https://packages.microsoft.com/config/rhel/$majorver/packages-microsoft-prod.rpm
# Register the Microsoft RedHat repository
sudo rpm -i packages-microsoft-prod.rpm
# Delete the downloaded package after installing
rm packages-microsoft-prod.rpm
# Update package index files
sudo dnf update
# Install PowerShell
sudo dnf install powershell -y
```
- [Docker](https://learn.microsoft.com/es-es/powershell/scripting/install/powershell-in-docker?view=powershell-7.5#use-powershell-in-a-container): The following command download the latest stable versions of PowerShell:
```console
docker pull mcr.microsoft.com/dotnet/sdk:9.0
```
To start an interactive shell of Pwsh you just need to run:
```console
docker run -it mcr.microsoft.com/dotnet/sdk:9.0 pwsh
```
### Needed PowerShell modules
To obtain the required data for this provider, we use several PowerShell cmdlets.
These cmdlets come from different modules that must be installed.
The installation of these modules will be performed automatically if you run Prowler with the flag `--init-modules`. This an example way of running Prowler and installing the modules:
```console
python3 prowler-cli.py m365 --verbose --log-level ERROR --env-auth --init-modules
```
If you already have them installed, there is no problem even if you use the flag because it will automatically check if the needed modules are already installed.
???+ note
Prowler installs the modules using `-Scope CurrentUser`.
If you encounter any issues with services not working after the automatic installation, try installing the modules manually using `-Scope AllUsers` (administrator permissions are required for this).
The command needed to install a module manually is:
```powershell
Install-Module -Name "ModuleName" -Scope AllUsers -Force
```
The required modules are:
- [ExchangeOnlineManagement](https://www.powershellgallery.com/packages/ExchangeOnlineManagement/3.6.0): Minimum version 3.6.0. Required for several checks across Exchange, Defender, and Purview.
- [MicrosoftTeams](https://www.powershellgallery.com/packages/MicrosoftTeams/6.6.0): Minimum version 6.6.0. Required for all Teams checks.
To use `--browser-auth` the user needs to authenticate against Azure using the default browser to start the scan, also `--tenant-id` flag is required.
Binary file not shown.

Before

Width:  |  Height:  |  Size: 313 KiB

After

Width:  |  Height:  |  Size: 746 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 347 KiB

+15 -19
View File
@@ -53,7 +53,7 @@ Prowler App can be installed in different ways, depending on your environment:
You can change the environment variables in the `.env` file. Note that it is not recommended to use the default values in production environments.
???+ note
There is a development mode available, you can use the file https://github.com/prowler-cloud/prowler/blob/master/docker-compose-dev.yml to run the app in development mode.
There is a development mode available, you can use the file https://github.com/prowler-cloud/prowler/blob/master/docker-compose.dev.yml to run the app in development mode.
???+ warning
Google and GitHub authentication is only available in [Prowler Cloud](https://prowler.com).
@@ -136,7 +136,7 @@ Prowler App can be installed in different ways, depending on your environment:
### Prowler CLI Installation
Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/), thus can be installed as Python package with `Python >= 3.9, <= 3.12`:
Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/), thus can be installed as Python package with `Python >= 3.9`:
=== "pipx"
@@ -144,7 +144,7 @@ Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/),
_Requirements_:
* `Python >= 3.9, <= 3.12`
* `Python >= 3.9`
* `pipx` installed: [pipx installation](https://pipx.pypa.io/stable/installation/).
* AWS, GCP, Azure and/or Kubernetes credentials
@@ -168,9 +168,9 @@ Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/),
_Requirements_:
* `Python >= 3.9, <= 3.12`
* `Python >= 3.9`
* `Python pip >= 21.0.0`
* AWS, GCP, Azure, M365 and/or Kubernetes credentials
* AWS, GCP, Azure, Microsoft365 and/or Kubernetes credentials
_Commands_:
@@ -228,7 +228,7 @@ Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/),
_Requirements_:
* `Python >= 3.9, <= 3.12`
* `Python >= 3.9`
* AWS, GCP, Azure and/or Kubernetes credentials
_Commands_:
@@ -244,8 +244,8 @@ Prowler is available as a project in [PyPI](https://pypi.org/project/prowler/),
_Requirements_:
* `Ubuntu 23.04` or above, if you are using an older version of Ubuntu check [pipx installation](https://docs.prowler.com/projects/prowler-open-source/en/latest/#__tabbed_1_1) and ensure you have `Python >= 3.9, <= 3.12`.
* `Python >= 3.9, <= 3.12`
* `Ubuntu 23.04` or above, if you are using an older version of Ubuntu check [pipx installation](https://docs.prowler.com/projects/prowler-open-source/en/latest/#__tabbed_1_1) and ensure you have `Python >= 3.9`.
* `Python >= 3.9`
* AWS, GCP, Azure and/or Kubernetes credentials
_Commands_:
@@ -423,7 +423,7 @@ While the scan is running, start exploring the findings in these sections:
### Prowler CLI
To run Prowler, you will need to specify the provider (e.g `aws`, `gcp`, `azure`, `m365` or `kubernetes`):
To run Prowler, you will need to specify the provider (e.g `aws`, `gcp`, `azure`, `microsoft365` or `kubernetes`):
???+ note
If no provider specified, AWS will be used for backward compatibility with most of v2 options.
@@ -565,27 +565,23 @@ kubectl logs prowler-XXXXX --namespace prowler-ns
???+ note
By default, `prowler` will scan all namespaces in your active Kubernetes context. Use the flag `--context` to specify the context to be scanned and `--namespaces` to specify the namespaces to be scanned.
#### Microsoft 365
#### Microsoft365
With M365 you need to specify which auth method is going to be used:
With Microsoft365 you need to specify which auth method is going to be used:
```console
# To use both service principal (for MSGraph) and user credentials (for PowerShell modules)
prowler m365 --env-auth
# To use service principal authentication
prowler m365 --sp-env-auth
prowler microsoft365 --sp-env-auth
# To use az cli authentication
prowler m365 --az-cli-auth
prowler microsoft365 --az-cli-auth
# To use browser authentication
prowler m365 --browser-auth --tenant-id "XXXXXXXX"
prowler microsoft365 --browser-auth --tenant-id "XXXXXXXX"
```
See more details about M365 Authentication in [Requirements](getting-started/requirements.md#microsoft-365)
See more details about Microsoft365 Authentication in [Requirements](getting-started/requirements.md#microsoft365)
## Prowler v2 Documentation
For **Prowler v2 Documentation**, please check it out [here](https://github.com/prowler-cloud/prowler/blob/8818f47333a0c1c1a457453c87af0ea5b89a385f/README.md).
-214
View File
@@ -1,214 +0,0 @@
# Getting Started with AWS on Prowler Cloud/App
<iframe width="560" height="380" src="https://www.youtube-nocookie.com/embed/RPgIWOCERzY" title="Prowler Cloud Onboarding AWS" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen="1"></iframe>
Set up your AWS account to enable security scanning using Prowler Cloud/App.
## Requirements
To configure your AWS account, youll need:
1. Access to Prowler Cloud/App
2. Properly configured AWS credentials (either static or via an assumed IAM role)
---
## Step 1: Get Your AWS Account ID
1. Log in to the [AWS Console](https://console.aws.amazon.com)
2. Locate your AWS account ID in the top-right dropdown menu
![Account ID detail](./img/aws-account-id.png)
---
## Step 2: Access Prowler Cloud/App
1. Navigate to [Prowler Cloud](https://cloud.prowler.com/) or launch [Prowler App](../prowler-app.md)
2. Go to `Configuration` > `Cloud Providers`
![Cloud Providers Page](../img/cloud-providers-page.png)
3. Click `Add Cloud Provider`
![Add a Cloud Provider](../img/add-cloud-provider.png)
4. Select `Amazon Web Services`
![Select AWS Provider](./img/select-aws.png)
5. Enter your AWS Account ID and optionally provide a friendly alias
![Add account ID](./img/add-account-id.png)
6. Choose your preferred authentication method (next step)
![Select auth method](./img/select-auth-method.png)
---
## Step 3: Set Up AWS Authentication
Before proceeding, choose your preferred authentication mode:
Credentials
* Quick scan as current user ✅
* No extra setup ✅
* Credentials time out ❌
Assumed Role
* Preferred Setup ✅
* Permanent Credentials ✅
* Requires access to create role ❌
---
### 🔐 Assume Role (Recommended)
![Assume Role Overview](./img/assume-role-overview.png)
This method grants permanent access and is the recommended setup for production environments.
=== "CloudFormation"
1. Download the [Prowler Scan Role Template](https://raw.githubusercontent.com/prowler-cloud/prowler/refs/heads/master/permissions/templates/cloudformation/prowler-scan-role.yml)
![Prowler Scan Role Template](./img/prowler-scan-role-template.png)
![Download Role Template](./img/download-role-template.png)
2. Open the [AWS Console](https://console.aws.amazon.com), search for **CloudFormation**
![CloudFormation Search](./img/cloudformation-nav.png)
3. Go to **Stacks** and click `Create stack` > `With new resources (standard)`
![Create Stack](./img/create-stack.png)
4. In **Specify Template**, choose `Upload a template file` and select the downloaded file
![Upload a template file](./img/upload-template-file.png)
![Upload file from downloads](./img/upload-template-from-downloads.png)
5. Click `Next`, provide a stack name and the **External ID** shown in the Prowler Cloud setup screen
![External ID](./img/prowler-cloud-external-id.png)
![Stack Data](./img/fill-stack-data.png)
6. Acknowledge the IAM resource creation warning and proceed
![Stack Creation Second Step](./img/stack-creation-second-step.png)
7. Click `Submit` to deploy the stack
![Click on submit](./img/submit-third-page.png)
=== "Terraform"
To provision the scan role using Terraform:
1. Run the following commands:
```bash
terraform init
terraform plan
terraform apply
```
2. During `plan` and `apply`, you will be prompted for the **External ID**, which is available in the Prowler Cloud/App UI:
![Get External ID](./img/get-external-id-prowler-cloud.png)
> 💡 Note: Terraform will use the AWS credentials of your default profile.
---
### Finish Setup with Assume Role
8. Once the role is created, go to the **IAM Console**, click on the `ProwlerScan` role to open its details:
![ProwlerScan role info](./img/prowler-scan-pre-info.png)
9. Copy the **Role ARN**
![New Role Info](./img/get-role-arn.png)
10. Paste the ARN into the corresponding field in Prowler Cloud/App
![Input the Role ARN](./img/paste-role-arn-prowler.png)
11. Click `Next`, then `Launch Scan`
![Next button in Prowler Cloud](./img/next-button-prowler-cloud.png)
![Launch Scan](./img/launch-scan-button-prowler-cloud.png)
---
### 🔑 Credentials (Static Access Keys)
You can also configure your AWS account using static credentials (not recommended for long-term use):
![Connect via credentials](./img/connect-via-credentials.png)
=== "Long term credentials"
1. Go to the [AWS Console](https://console.aws.amazon.com), open **CloudShell**
![AWS CloudShell](./img/aws-cloudshell.png)
2. Run:
```bash
aws iam create-access-key
```
3. Copy the output containing:
- `AccessKeyId`
- `SecretAccessKey`
![CloudShell Output](./img/cloudshell-output.png)
> ⚠️ Save these credentials securely and paste them into the Prowler Cloud/App setup screen.
=== "Short term credentials (Recommended)"
You can use your [AWS Access Portal](https://docs.aws.amazon.com/singlesignon/latest/userguide/howtogetcredentials.html) or the CLI:
1. Retrieve short-term credentials for the IAM identity using this command:
```bash
aws sts get-session-token --duration-seconds 900
```
???+ note
Check the aws documentation [here](https://docs.aws.amazon.com/IAM/latest/UserGuide/sts_example_sts_GetSessionToken_section.html)
2. Copy the output containing:
- `AccessKeyId`
- `SecretAccessKey`
> Sample output:
```json
{
"Credentials": {
"AccessKeyId": "ASIAIOSFODNN7EXAMPLE",
"SecretAccessKey": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYzEXAMPLEKEY",
"SessionToken": "AQoEXAMPLEH4aoAH0gNCAPyJxz4BlCFFxWNE1OPTgk5TthT+FvwqnKwRcOIfrRh3c/LTo6UDdyJwOOvEVPvLXCrrrUtdnniCEXAMPLE/IvU1dYUg2RVAJBanLiHb4IgRmpRV3zrkuWJOgQs8IZZaIv2BXIa2R4OlgkBN9bkUDNCJiBeb/AXlzBBko7b15fjrBs2+cTQtpZ3CYWFXG8C5zqx37wnOE49mRl/+OtkIKGO7fAE",
"Expiration": "2020-05-19T18:06:10+00:00"
}
}
```
> ⚠️ Save these credentials securely and paste them into the Prowler Cloud/App setup screen.
Complete the form in Prowler Cloud/App and click `Next`
![Filled credentials page](./img/prowler-cloud-credentials-next.png)
Click `Launch Scan`
![Launch Scan](./img/launch-scan-button-prowler-cloud.png)
Binary file not shown.

Before

Width:  |  Height:  |  Size: 120 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 182 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 45 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 10 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 53 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 172 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 149 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 98 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 127 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 453 KiB

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