mirror of
https://github.com/prowler-cloud/prowler.git
synced 2026-10-04 02:04:06 +00:00
Compare commits
75
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
30ad5249d3 | ||
|
|
c2b8092461 | ||
|
|
26d9d24e5d | ||
|
|
ee59e35bc2 | ||
|
|
e0fa23b9ee | ||
|
|
4dbc3c7e74 | ||
|
|
576433d85d | ||
|
|
bf179212a5 | ||
|
|
60f936a10b | ||
|
|
15630f54d2 | ||
|
|
706603fe4d | ||
|
|
dc67fe4f37 | ||
|
|
2c233c2f6c | ||
|
|
69e1d19abe | ||
|
|
859421b0ec | ||
|
|
ea36f12a01 | ||
|
|
50a9138bea | ||
|
|
09821e6328 | ||
|
|
94899e20fd | ||
|
|
79da676c86 | ||
|
|
8b35b69731 | ||
|
|
81d90fc31e | ||
|
|
8b5f1250a9 | ||
|
|
98d2db4e13 | ||
|
|
c9068515b2 | ||
|
|
3823186914 | ||
|
|
c453b7293e | ||
|
|
03cb59c20d | ||
|
|
d819639f0e | ||
|
|
6c8d6994bb | ||
|
|
07d48ab15d | ||
|
|
5fe1a6713b | ||
|
|
61d13f078c | ||
|
|
bbb297aee7 | ||
|
|
d0d29108e0 | ||
|
|
f382400037 | ||
|
|
396ccf56bb | ||
|
|
3069486549 | ||
|
|
9f616a5d43 | ||
|
|
2198ba2d84 | ||
|
|
974f4251dd | ||
|
|
75c22df63b | ||
|
|
757cd44ecb | ||
|
|
c0fdd5bdf3 | ||
|
|
61ef44a03b | ||
|
|
682353e054 | ||
|
|
3860cd3dce | ||
|
|
1b228d590b | ||
|
|
8b265a8314 | ||
|
|
ba258a5346 | ||
|
|
282fe5b46b | ||
|
|
c08cb65d84 | ||
|
|
4727da7ca7 | ||
|
|
b378f15798 | ||
|
|
f9c02da90a | ||
|
|
865eebe7fb | ||
|
|
8270979ec8 | ||
|
|
369f852837 | ||
|
|
1e8454a3cb | ||
|
|
6f6ae88a66 | ||
|
|
c71f226e5c | ||
|
|
bbf5e1fa9f | ||
|
|
9cab9b8653 | ||
|
|
806be2d061 | ||
|
|
2769cb9876 | ||
|
|
623dc3125a | ||
|
|
2d4ab4cc25 | ||
|
|
6519927d64 | ||
|
|
234c272da0 | ||
|
|
270490e93e | ||
|
|
ea9171c77c | ||
|
|
aecac60c12 | ||
|
|
abc5bedc45 | ||
|
|
fa6eb9d5d9 | ||
|
|
9c5ed27a7a |
@@ -110,11 +110,27 @@ DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY=""
|
||||
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN=""
|
||||
|
||||
# The AWS region where your S3 bucket is located (e.g., "us-east-1")
|
||||
# Required if the bucket uses SSE-KMS: download URLs are then signed with SigV4, which
|
||||
# is scoped to this region, so it must match the bucket's
|
||||
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION=""
|
||||
|
||||
# The name of the S3 bucket where scan output should be stored
|
||||
DJANGO_OUTPUT_S3_AWS_OUTPUT_BUCKET=""
|
||||
|
||||
# The storage endpoint the API and Celery workers use to upload and list scan output
|
||||
# (e.g. "http://minio:9000"). Leave empty on AWS S3. Set it when scan output is stored on
|
||||
# S3-compatible object storage such as MinIO instead of real S3.
|
||||
# If set without DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL below, report download URLs are
|
||||
# signed against this internal host, and a browser outside the container network cannot open them.
|
||||
DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL=""
|
||||
|
||||
# The storage address the browser can reach, used only to sign report download URLs
|
||||
# (e.g. "https://storage.example.com"). Leave empty on AWS S3. Set it when storage is
|
||||
# only reachable inside the container network, such as MinIO on "http://minio:9000".
|
||||
# The reverse proxy in front of it must forward the Host header unchanged: SigV4 signs
|
||||
# Host, so rewriting it to the internal name invalidates the signature.
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL=""
|
||||
|
||||
# Django settings
|
||||
DJANGO_ALLOWED_HOSTS=localhost,127.0.0.1,prowler-api
|
||||
DJANGO_BIND_ADDRESS=0.0.0.0
|
||||
@@ -158,7 +174,7 @@ SENTRY_RELEASE=local
|
||||
# REO_DEV_CLIENT_ID=
|
||||
|
||||
#### Prowler release version ####
|
||||
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.42.0
|
||||
NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.44.0
|
||||
|
||||
# Social login credentials
|
||||
SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"
|
||||
|
||||
+13
-13
@@ -1,23 +1,23 @@
|
||||
# SDK
|
||||
/* @prowler-cloud/detection-remediation
|
||||
/prowler/ @prowler-cloud/detection-remediation
|
||||
/tests/ @prowler-cloud/detection-remediation
|
||||
/dashboard/ @prowler-cloud/detection-remediation
|
||||
/docs/ @prowler-cloud/detection-remediation
|
||||
/examples/ @prowler-cloud/detection-remediation
|
||||
/util/ @prowler-cloud/detection-remediation
|
||||
/contrib/ @prowler-cloud/detection-remediation
|
||||
/permissions/ @prowler-cloud/detection-remediation
|
||||
/codecov.yml @prowler-cloud/detection-remediation @prowler-cloud/api
|
||||
/* @prowler-cloud/engineering
|
||||
/prowler/ @prowler-cloud/engineering
|
||||
/tests/ @prowler-cloud/engineering
|
||||
/dashboard/ @prowler-cloud/engineering
|
||||
/docs/ @prowler-cloud/engineering
|
||||
/examples/ @prowler-cloud/engineering
|
||||
/util/ @prowler-cloud/engineering
|
||||
/contrib/ @prowler-cloud/engineering
|
||||
/permissions/ @prowler-cloud/engineering
|
||||
/codecov.yml @prowler-cloud/engineering
|
||||
|
||||
# API
|
||||
/api/ @prowler-cloud/api
|
||||
/api/ @prowler-cloud/engineering
|
||||
|
||||
# UI
|
||||
/ui/ @prowler-cloud/ui
|
||||
/ui/ @prowler-cloud/engineering
|
||||
|
||||
# AI
|
||||
/mcp_server/ @prowler-cloud/detection-remediation
|
||||
/mcp_server/ @prowler-cloud/engineering
|
||||
|
||||
# Platform
|
||||
/.github/ @prowler-cloud/platform
|
||||
|
||||
@@ -451,6 +451,17 @@ modules:
|
||||
e2e:
|
||||
- ui/tests/home/**
|
||||
|
||||
- name: ui-registry
|
||||
match:
|
||||
- ui/actions/registry/**
|
||||
- ui/app/**/registry/**
|
||||
- ui/components/registry/**
|
||||
- ui/lib/registry/**
|
||||
- ui/tests/registry/**
|
||||
tests: []
|
||||
e2e:
|
||||
- ui/tests/registry/**
|
||||
|
||||
- name: ui-shadcn
|
||||
match:
|
||||
- ui/components/shadcn/**
|
||||
|
||||
@@ -39,7 +39,7 @@ jobs:
|
||||
|
||||
- name: Check labels
|
||||
id: label_check
|
||||
uses: agilepathway/label-checker@c3d16ad512e7cea5961df85ff2486bb774caf3c5 # v1.6.65
|
||||
uses: agilepathway/label-checker@c324842522fbd012e4f590afe3b4e591301322ed # v1.6.66
|
||||
with:
|
||||
allow_failure: true
|
||||
prefix_mode: true
|
||||
|
||||
@@ -44,7 +44,10 @@ jobs:
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
run: pip install boto3
|
||||
# Pinned to the versions in pyproject.toml: the ISO partitions region
|
||||
# data comes from the endpoints.json bundled with botocore, so the
|
||||
# botocore version is itself a data source and must be deterministic
|
||||
run: pip install boto3==1.40.61 botocore==1.40.61
|
||||
|
||||
- name: Configure AWS credentials
|
||||
uses: aws-actions/configure-aws-credentials@d979d5b3a71173a29b74b5b88418bfda9437d885 # v6.1.1
|
||||
|
||||
@@ -10,12 +10,13 @@ on:
|
||||
- master
|
||||
- "v5.*"
|
||||
paths:
|
||||
- '.github/workflows/ui-e2e-tests-v2.yml'
|
||||
- '.github/test-impact.yml'
|
||||
- 'ui/**'
|
||||
- 'api/**' # API changes can affect UI E2E
|
||||
- '!ui/CHANGELOG.md'
|
||||
- '!api/CHANGELOG.md'
|
||||
- ".github/workflows/ui-e2e-tests-v2.yml"
|
||||
- ".github/workflows/test-impact-analysis.yml"
|
||||
- ".github/test-impact.yml"
|
||||
- "ui/**"
|
||||
- "api/**" # API changes can affect UI E2E
|
||||
- "!ui/CHANGELOG.md"
|
||||
- "!api/CHANGELOG.md"
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
@@ -40,11 +41,11 @@ jobs:
|
||||
(needs.impact-analysis.outputs.has-ui-e2e == 'true' || needs.impact-analysis.outputs.run-all == 'true')
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
AUTH_SECRET: 'fallback-ci-secret-for-testing'
|
||||
AUTH_SECRET: "fallback-ci-secret-for-testing"
|
||||
AUTH_TRUST_HOST: true
|
||||
NEXTAUTH_URL: 'http://localhost:3000'
|
||||
AUTH_URL: 'http://localhost:3000'
|
||||
UI_API_BASE_URL: 'http://localhost:8080/api/v1'
|
||||
NEXTAUTH_URL: "http://localhost:3000"
|
||||
AUTH_URL: "http://localhost:3000"
|
||||
UI_API_BASE_URL: "http://localhost:8080/api/v1"
|
||||
E2E_ADMIN_USER: ${{ secrets.E2E_ADMIN_USER }}
|
||||
E2E_ADMIN_PASSWORD: ${{ secrets.E2E_ADMIN_PASSWORD }}
|
||||
E2E_AWS_PROVIDER_ACCOUNT_ID: ${{ secrets.E2E_AWS_PROVIDER_ACCOUNT_ID }}
|
||||
@@ -60,7 +61,7 @@ jobs:
|
||||
E2E_M365_SECRET_ID: ${{ secrets.E2E_M365_SECRET_ID }}
|
||||
E2E_M365_TENANT_ID: ${{ secrets.E2E_M365_TENANT_ID }}
|
||||
E2E_M365_CERTIFICATE_CONTENT: ${{ secrets.E2E_M365_CERTIFICATE_CONTENT }}
|
||||
E2E_KUBERNETES_CONTEXT: 'kind-kind'
|
||||
E2E_KUBERNETES_CONTEXT: "kind-kind"
|
||||
E2E_KUBERNETES_KUBECONFIG_PATH: /home/runner/.kube/config
|
||||
E2E_GCP_BASE64_SERVICE_ACCOUNT_KEY: ${{ secrets.E2E_GCP_BASE64_SERVICE_ACCOUNT_KEY }}
|
||||
E2E_GCP_PROJECT_ID: ${{ secrets.E2E_GCP_PROJECT_ID }}
|
||||
@@ -237,8 +238,8 @@ jobs:
|
||||
|
||||
- name: Add AWS credentials for testing
|
||||
run: |
|
||||
echo "AWS_ACCESS_KEY_ID=${{ secrets.E2E_AWS_PROVIDER_ACCESS_KEY }}" >> .env
|
||||
echo "AWS_SECRET_ACCESS_KEY=${{ secrets.E2E_AWS_PROVIDER_SECRET_KEY }}" >> .env
|
||||
echo "AWS_ACCESS_KEY_ID=${E2E_AWS_PROVIDER_ACCESS_KEY}" >> .env
|
||||
echo "AWS_SECRET_ACCESS_KEY=${E2E_AWS_PROVIDER_SECRET_KEY}" >> .env
|
||||
|
||||
- name: Build API image from current code
|
||||
# docker-compose.yml references prowlercloud/prowler-api:latest from the registry,
|
||||
@@ -292,7 +293,7 @@ jobs:
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
|
||||
with:
|
||||
node-version-file: 'ui/.nvmrc'
|
||||
node-version-file: "ui/.nvmrc"
|
||||
|
||||
- name: Setup pnpm
|
||||
uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
|
||||
@@ -337,60 +338,59 @@ jobs:
|
||||
if: steps.playwright-cache.outputs.cache-hit != 'true'
|
||||
run: pnpm run test:e2e:install
|
||||
|
||||
- name: Run E2E tests
|
||||
- name: Run standard E2E tests
|
||||
id: standard-e2e
|
||||
working-directory: ./ui
|
||||
run: |
|
||||
if [[ "${RUN_ALL_TESTS}" == "true" ]]; then
|
||||
echo "Running ALL E2E tests..."
|
||||
echo "Running all standard E2E tests..."
|
||||
pnpm run test:e2e
|
||||
else
|
||||
echo "Running targeted E2E tests: ${E2E_TEST_PATHS}"
|
||||
# Convert glob patterns to playwright test paths
|
||||
# e.g., "ui/tests/providers/**" -> "tests/providers"
|
||||
echo "Running targeted standard E2E tests: ${E2E_TEST_PATHS}"
|
||||
TEST_PATHS="${E2E_TEST_PATHS}"
|
||||
# Remove ui/ prefix and convert ** to empty (playwright handles recursion)
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | sed 's|ui/||g' | sed 's|\*\*||g' | tr ' ' '\n' | sort -u)
|
||||
# Drop auth setup helpers (not runnable test suites)
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | grep -v '^tests/setups/')
|
||||
# Safety net: if bare "tests/" appears (from broad patterns like ui/tests/**),
|
||||
# expand to specific subdirs to avoid Playwright discovering setup files
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | grep -vE '^tests/(setups|registry)/' || true)
|
||||
|
||||
if echo "$TEST_PATHS" | grep -qx 'tests/'; then
|
||||
echo "Expanding bare 'tests/' to specific subdirs (excluding setups)..."
|
||||
SPECIFIC_DIRS=""
|
||||
for dir in tests/*/; do
|
||||
[[ "$dir" == "tests/setups/" ]] && continue
|
||||
[[ "$dir" == "tests/setups/" || "$dir" == "tests/registry/" ]] && continue
|
||||
SPECIFIC_DIRS="${SPECIFIC_DIRS}${dir}"$'\n'
|
||||
done
|
||||
# Replace "tests/" with specific dirs, keep other paths
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | grep -vx 'tests/')
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | grep -vx 'tests/' || true)
|
||||
TEST_PATHS="${TEST_PATHS}"$'\n'"${SPECIFIC_DIRS}"
|
||||
TEST_PATHS=$(echo "$TEST_PATHS" | grep -v '^$' | sort -u)
|
||||
fi
|
||||
if [[ -z "$TEST_PATHS" ]]; then
|
||||
echo "No runnable E2E test paths after filtering setups"
|
||||
exit 0
|
||||
fi
|
||||
# Filter out directories that don't contain any test files
|
||||
|
||||
VALID_PATHS=""
|
||||
while IFS= read -r p; do
|
||||
[[ -z "$p" ]] && continue
|
||||
if find "$p" -name '*.spec.ts' -o -name '*.test.ts' 2>/dev/null | head -1 | grep -q .; then
|
||||
VALID_PATHS="${VALID_PATHS}${p}"$'\n'
|
||||
while IFS= read -r path; do
|
||||
[[ -z "$path" ]] && continue
|
||||
if find "$path" -name '*.spec.ts' -o -name '*.test.ts' 2>/dev/null | head -1 | grep -q .; then
|
||||
VALID_PATHS="${VALID_PATHS}${path}"$'\n'
|
||||
else
|
||||
echo "Skipping empty test directory: $p"
|
||||
echo "Skipping empty test directory: $path"
|
||||
fi
|
||||
done <<< "$TEST_PATHS"
|
||||
VALID_PATHS=$(echo "$VALID_PATHS" | grep -v '^$' || true)
|
||||
if [[ -z "$VALID_PATHS" ]]; then
|
||||
echo "No test files found in any resolved paths — skipping E2E"
|
||||
exit 0
|
||||
|
||||
if [[ -n "$VALID_PATHS" ]]; then
|
||||
TEST_PATHS=$(echo "$VALID_PATHS" | tr '\n' ' ')
|
||||
echo "Resolved standard test paths: $TEST_PATHS"
|
||||
read -ra test_paths <<< "$TEST_PATHS"
|
||||
pnpm exec playwright test "${test_paths[@]}"
|
||||
else
|
||||
echo "No standard E2E test paths selected."
|
||||
fi
|
||||
TEST_PATHS=$(echo "$VALID_PATHS" | tr '\n' ' ')
|
||||
echo "Resolved test paths: $TEST_PATHS"
|
||||
read -ra test_paths <<< "$TEST_PATHS"
|
||||
pnpm exec playwright test "${test_paths[@]}"
|
||||
fi
|
||||
|
||||
- name: Run Registry fixture E2E tests
|
||||
if: |
|
||||
!cancelled() &&
|
||||
(steps.standard-e2e.outcome == 'success' || steps.standard-e2e.outcome == 'failure') &&
|
||||
(env.RUN_ALL_TESTS == 'true' || contains(format(' {0} ', env.E2E_TEST_PATHS), ' ui/tests/registry/'))
|
||||
working-directory: ./ui
|
||||
run: pnpm run test:e2e:registry
|
||||
|
||||
- name: Upload test reports
|
||||
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
|
||||
if: failure()
|
||||
|
||||
+22
@@ -27,6 +27,17 @@ ignore:
|
||||
package:
|
||||
name: google.golang.org/grpc
|
||||
version: v1.82.1
|
||||
# CVE-2026-84445 is the same temporary exception documented in .trivyignore.yaml:
|
||||
# Trivy 0.74.0 still embeds grpc 1.82.1, while the 1.82.2 / 1.83.2 fix is not in any
|
||||
# release. The panic needs a gRPC server built with `xds.NewGRPCServer()`; Prowler only
|
||||
# runs `trivy image` / `trivy fs`, so the image serves no gRPC at all. Pinned to the
|
||||
# embedded version so the rule stops matching on its own once Trivy bumps grpc. Remove
|
||||
# with the Trivy exception by 2026-10-15.
|
||||
# https://github.com/advisories/GHSA-2v4p-qf9q-27wj
|
||||
- vulnerability: CVE-2026-84445
|
||||
package:
|
||||
name: google.golang.org/grpc
|
||||
version: v1.82.1
|
||||
# CVE-2026-56855 / CVE-2026-78662 are the same temporary exception documented in
|
||||
# .trivyignore.yaml: Trivy 0.74.0 still embeds golang.org/x/crypto v0.55.0, while the
|
||||
# 0.56.0 fix (published 2026-09-02) hasn't reached any Trivy release, or even Trivy
|
||||
@@ -104,3 +115,14 @@ ignore:
|
||||
- vulnerability: CVE-2026-9669
|
||||
package:
|
||||
name: python
|
||||
# CVE-2026-82049 (tarfile data/tar filter bypass via a hard link to a symlink) has no
|
||||
# fixed CPython release on any branch: the fix is merged on main and 3.13 only, and the
|
||||
# 3.12 backport is still open. Grype records 3.14.0b1 as the fix, so only-fixed does not
|
||||
# drop it, yet python:3.12.14-slim-trixie reports it too. Prowler never extracts tar
|
||||
# archives to disk: the ECR image inspection reads members in memory with extractfile().
|
||||
# Remove once the base image ships a 3.12 release that includes the backport.
|
||||
# https://github.com/python/cpython/issues/157190
|
||||
# https://github.com/python/cpython/pull/157454
|
||||
- vulnerability: CVE-2026-82049
|
||||
package:
|
||||
name: python
|
||||
|
||||
+23
-30
@@ -125,41 +125,15 @@ vulnerabilities:
|
||||
purls:
|
||||
- "pkg:npm/fast-uri"
|
||||
expired_at: 2027-01-31
|
||||
- id: CVE-2026-75931
|
||||
purls:
|
||||
- "pkg:npm/fast-uri"
|
||||
expired_at: 2027-01-31
|
||||
- id: CVE-2026-69192
|
||||
purls:
|
||||
- "pkg:npm/ip-address"
|
||||
expired_at: 2027-01-31
|
||||
|
||||
# CVE-2026-62901 is a DoS in System.Net.WebSockets (unchecked input for loop condition,
|
||||
# CWE-606), fixed in .NET 9.0.19 / 10.0.11 (published 2026-08-11). The vulnerable runtime
|
||||
# ships inside the PowerShell tarball the Dockerfile pins: 7.5.9 is the latest 7.5.x and
|
||||
# bundles .NET 9.0.18; 7.6.4 bundles .NET 10.0.x < 10.0.11, so no published PowerShell
|
||||
# release contains the fix yet. Prowler only invokes pwsh locally to run M365 module
|
||||
# cmdlets; the image does not accept inbound WebSocket connections, so the DoS path is
|
||||
# not reachable from the network. Remove this temporary suppression as soon as a
|
||||
# PowerShell release shipping .NET 9.0.19+ is available.
|
||||
- id: CVE-2026-62901
|
||||
purls:
|
||||
- "pkg:nuget/Microsoft.NETCore.App.Runtime.linux-x64"
|
||||
- "pkg:nuget/Microsoft.NETCore.App.Runtime.linux-arm64"
|
||||
expired_at: 2026-09-15
|
||||
|
||||
# Modules compiled into the Trivy binary the images ship. The binary is pinned by version
|
||||
# and verified by checksum in the Dockerfile; only a rebuild by its vendor moves these.
|
||||
# CVE-2026-71556 affects go-git worktree operations that can follow symlinks outside a
|
||||
# cloned repository. Trivy 0.73.0, the latest published release and the version the
|
||||
# images ship, still pins that vulnerable version:
|
||||
# https://github.com/aquasecurity/trivy/blob/v0.73.0/go.mod#L46
|
||||
# Trivy main already contains the 5.19.2 fix, but no published release includes it yet:
|
||||
# https://github.com/aquasecurity/trivy/commit/a2edba9a03987ba0d2ebc8212c1a9a1e6979497b
|
||||
# Prowler invokes Trivy only with `fs` on an existing local path or with `image`; it does
|
||||
# not ask Trivy to clone or mutate a Git worktree, so the affected path is not reachable.
|
||||
# Remove this temporary suppression as soon as a fixed Trivy release is available.
|
||||
- id: CVE-2026-71556
|
||||
purls:
|
||||
- "pkg:golang/github.com/go-git/go-git/v5"
|
||||
expired_at: 2026-09-15
|
||||
|
||||
# CVE-2026-84304 is a DoS in grpc-go <= 1.83.0: a peer fragments a gRPC stream into
|
||||
# millions of tiny HTTP/2 DATA frames until the receiver runs out of heap. Fixed in
|
||||
# 1.83.1 (published 2026-09-01). Trivy 0.74.0, the latest published release and the
|
||||
@@ -176,6 +150,25 @@ vulnerabilities:
|
||||
- "pkg:golang/google.golang.org/grpc"
|
||||
expired_at: 2026-10-15
|
||||
|
||||
# CVE-2026-84445 is a DoS in grpc-go servers built with `xds.NewGRPCServer()`: a request
|
||||
# carrying neither `:authority` nor `Host` reaches the xDS routing interceptor, which
|
||||
# indexes an empty slice of authorities and panics. The per-RPC goroutine does not
|
||||
# recover, so the whole server process dies. Fixed in 1.82.2 and 1.83.2 (published
|
||||
# 2026-09-08). Trivy 0.74.0, the latest published release and the version the images
|
||||
# ship, pins 1.82.1 as an indirect dependency:
|
||||
# https://github.com/aquasecurity/trivy/blob/v0.74.0/go.mod
|
||||
# Trivy main already carries 1.83.2, but no published release includes it yet.
|
||||
# The reachability argument is the one made for CVE-2026-84304 above, only narrower:
|
||||
# this panic needs an xDS-managed gRPC server. Prowler invokes Trivy exclusively as
|
||||
# `trivy image` and `trivy fs` on a local path, never `trivy server`, so the image runs
|
||||
# no gRPC server at all, xDS or otherwise. Remove this temporary suppression as soon as
|
||||
# a Trivy release pins grpc >= 1.83.2.
|
||||
# https://github.com/advisories/GHSA-2v4p-qf9q-27wj
|
||||
- id: CVE-2026-84445
|
||||
purls:
|
||||
- "pkg:golang/google.golang.org/grpc@v1.82.1"
|
||||
expired_at: 2026-10-15
|
||||
|
||||
# CVE-2026-56855 and CVE-2026-78662 are DoS deadlocks in x/crypto/ssh: a malicious peer
|
||||
# can flood or misuse channel messages (RFC 4254) to block the whole connection.
|
||||
# Fixed in golang.org/x/crypto v0.56.0 (published 2026-09-02). Trivy 0.74.0, the latest
|
||||
|
||||
+13
-8
@@ -3,7 +3,7 @@ FROM python:3.12.13-slim-trixie@sha256:57cd7c3a7a273101a6485ba99423ee56815788280
|
||||
LABEL maintainer="https://github.com/prowler-cloud/prowler"
|
||||
LABEL org.opencontainers.image.source="https://github.com/prowler-cloud/prowler"
|
||||
|
||||
ARG POWERSHELL_VERSION=7.5.9
|
||||
ARG POWERSHELL_VERSION=7.5.11
|
||||
ENV POWERSHELL_VERSION=${POWERSHELL_VERSION}
|
||||
# Opt out of PowerShell telemetry (Application Insights -> dc.services.visualstudio.com)
|
||||
ENV POWERSHELL_TELEMETRY_OPTOUT=1
|
||||
@@ -17,25 +17,30 @@ ENV ZIZMOR_VERSION=${ZIZMOR_VERSION}
|
||||
# Pinned here, not fetched with the artefact: a compromised release ships its own checksum.
|
||||
ARG TRIVY_SHA256_AMD64=2ae6fe3ee734b7fdf11335663e18c75ea12dccc76062f09f164a3b0f8be4371a
|
||||
ARG TRIVY_SHA256_ARM64=b94ce1976bbf3c15b514b605ee88be7c6d94a29be2302847ff01cb794d47aad5
|
||||
ARG POWERSHELL_SHA256_AMD64=492ff26bb958336bf61e597ce19e07648b4003bd2a08659e02f0e3e0446ebfe0
|
||||
ARG POWERSHELL_SHA256_ARM64=2503b71da3e83635592b092df59a0aca4c3606b4d9b068217bb00be989cb0d56
|
||||
ARG POWERSHELL_SHA256_AMD64=82a8b13d92b0f3ae48e56cf2f3f7961679371736ca90145ca71617c2913ba9d8
|
||||
ARG POWERSHELL_SHA256_ARM64=830ebda118c731ece3fa7e6b7e8573a21346387cbbca5b2f5e3b9bfe24f96672
|
||||
ARG ZIZMOR_SHA256_AMD64=a8000f3c683319a523d3b20df0e75457ba591f049cfcbfa98966631b56733c03
|
||||
ARG ZIZMOR_SHA256_ARM64=d66e37ef8a375fb07939c630ebf9709a6e0f20242bdc3faf672a7ed97e0b768d
|
||||
|
||||
# High CVEs fixed in Debian trixie-security but not yet in the pinned base image:
|
||||
# High CVEs fixed in Debian trixie but not yet in the pinned base image:
|
||||
# openssl/libssl3t64/openssl-provider-legacy 3.5.7-1~deb13u2 CVE-2026-14456,
|
||||
# -14457, -18798, -54874, -63072, -63073, -63074, -63075, -63076, -75803
|
||||
# (image ships 3.5.6-1~deb13u2)
|
||||
# libsqlite3-0 3.46.1-7+deb13u2 CVE-2026-11822, -11824
|
||||
# gzip 1.13-1+deb13u1 CVE-2026-41992
|
||||
# perl-base 5.40.1-6+deb13u1 CVE-2026-42497, -48962, -57432
|
||||
# libssh2-1t64 1.11.1-1+deb13u2 CVE-2026-58050
|
||||
# libpcre2-8-0 10.46-1~deb13u2 CVE-2026-86145, -89161
|
||||
# Taken as a targeted --only-upgrade rather than by moving the digest: the newest
|
||||
# published python:3.12-slim-trixie carries the same vulnerable version. The three
|
||||
# packages are all built from openssl and are flagged separately, so all are named.
|
||||
# Drop them once the base image ships 3.5.7-1~deb13u2 or later.
|
||||
# published python:3.12-slim-trixie carries the same vulnerable versions. The three
|
||||
# openssl packages are flagged separately, so all are named.
|
||||
# Drop each one once the base image ships its fixed version.
|
||||
# hadolint ignore=DL3008
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
wget libicu76 libunwind8 libssl3 libcurl4 ca-certificates apt-transport-https gnupg \
|
||||
build-essential pkg-config libzstd-dev zlib1g-dev \
|
||||
&& apt-get install -y --no-install-recommends --only-upgrade \
|
||||
util-linux libssl3t64 openssl openssl-provider-legacy \
|
||||
libsqlite3-0 gzip perl-base libssh2-1t64 libpcre2-8-0 \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install PowerShell
|
||||
|
||||
@@ -126,12 +126,12 @@ Every AWS provider scan will enqueue an Attack Paths ingestion job automatically
|
||||
|
||||
| Provider | Checks | Services | [Compliance Frameworks](https://docs.prowler.com/user-guide/compliance/tutorials/compliance) | [Categories](https://docs.prowler.com/user-guide/cli/tutorials/misc#categories) | Support | Interface |
|
||||
|---|---|---|---|---|---|---|
|
||||
| AWS | 639 | 86 | 47 | 19 | Official | UI, API, CLI |
|
||||
| Azure | 191 | 22 | 21 | 16 | Official | UI, API, CLI |
|
||||
| GCP | 109 | 20 | 19 | 12 | Official | UI, API, CLI |
|
||||
| Kubernetes | 92 | 7 | 8 | 11 | Official | UI, API, CLI |
|
||||
| AWS | 662 | 86 | 50 | 19 | Official | UI, API, CLI |
|
||||
| Azure | 191 | 22 | 25 | 16 | Official | UI, API, CLI |
|
||||
| GCP | 110 | 20 | 22 | 12 | Official | UI, API, CLI |
|
||||
| Kubernetes | 92 | 7 | 11 | 11 | Official | UI, API, CLI |
|
||||
| GitHub | 24 | 3 | 2 | 5 | Official | UI, API, CLI |
|
||||
| M365 | 143 | 10 | 6 | 10 | Official | UI, API, CLI |
|
||||
| M365 | 144 | 10 | 9 | 10 | Official | UI, API, CLI |
|
||||
| OCI | 52 | 14 | 5 | 10 | Official | UI, API, CLI |
|
||||
| Alibaba Cloud | 63 | 9 | 6 | 9 | Official | UI, API, CLI |
|
||||
| Cloudflare | 29 | 3 | 2 | 5 | Official | UI, API, CLI |
|
||||
|
||||
@@ -4,6 +4,30 @@ All notable changes to the **Prowler API** are documented in this file.
|
||||
|
||||
<!-- changelog: release notes start -->
|
||||
|
||||
## [1.44.0] (Prowler v5.43.0)
|
||||
|
||||
### 🐞 Fixed
|
||||
|
||||
- Report download URLs can be signed against a browser-reachable storage host via `DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL`, so downloads complete on deployments where storage is only reachable inside the container network [(#12552)](https://github.com/prowler-cloud/prowler/pull/12552)
|
||||
- A scan report download no longer fails with a server error when `DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION` is unset, which is common on storage with no meaningful region [(#12552)](https://github.com/prowler-cloud/prowler/pull/12552)
|
||||
- Lapsed pending invitations are reported as expired and no longer block a new invitation for the same email [(#12831)](https://github.com/prowler-cloud/prowler/pull/12831)
|
||||
|
||||
### 🔐 Security
|
||||
|
||||
- `libsqlite3-0`, `gzip`, `perl-base` and `libpcre2-8-0` upgraded in the API container image, patching high Debian CVEs [(#12804)](https://github.com/prowler-cloud/prowler/pull/12804)
|
||||
- PowerShell from 7.5.9 to 7.5.11 in the API container image, bundling .NET runtime 9.0.20 and patching CVE-2026-62901 [(#12811)](https://github.com/prowler-cloud/prowler/pull/12811)
|
||||
- Bumped `anyio` to 4.14.2 to resolve CVE-2026-63374 [(#12848)](https://github.com/prowler-cloud/prowler/pull/12848)
|
||||
|
||||
---
|
||||
|
||||
## [1.43.0] (Prowler v5.42.0)
|
||||
|
||||
### 🔄 Changed
|
||||
|
||||
- Speed up compliance overview ingestion by reading ThreatScore mappings from the compliance template instead of each finding, generating time-ordered `uuid7` row ids and grouping inserted rows by framework and requirement [(#12738)](https://github.com/prowler-cloud/prowler/pull/12738)
|
||||
|
||||
---
|
||||
|
||||
## [1.42.0] (Prowler v5.41.0)
|
||||
|
||||
### 🚀 Added
|
||||
|
||||
+13
-8
@@ -2,7 +2,7 @@ FROM python:3.12.13-slim-trixie@sha256:57cd7c3a7a273101a6485ba99423ee56815788280
|
||||
|
||||
LABEL maintainer="https://github.com/prowler-cloud/api"
|
||||
|
||||
ARG POWERSHELL_VERSION=7.5.9
|
||||
ARG POWERSHELL_VERSION=7.5.11
|
||||
ENV POWERSHELL_VERSION=${POWERSHELL_VERSION}
|
||||
# Opt out of PowerShell telemetry (Application Insights -> dc.services.visualstudio.com)
|
||||
ENV POWERSHELL_TELEMETRY_OPTOUT=1
|
||||
@@ -16,19 +16,23 @@ ENV ZIZMOR_VERSION=${ZIZMOR_VERSION}
|
||||
# Pinned here, not fetched with the artefact: a compromised release ships its own checksum.
|
||||
ARG TRIVY_SHA256_AMD64=2ae6fe3ee734b7fdf11335663e18c75ea12dccc76062f09f164a3b0f8be4371a
|
||||
ARG TRIVY_SHA256_ARM64=b94ce1976bbf3c15b514b605ee88be7c6d94a29be2302847ff01cb794d47aad5
|
||||
ARG POWERSHELL_SHA256_AMD64=492ff26bb958336bf61e597ce19e07648b4003bd2a08659e02f0e3e0446ebfe0
|
||||
ARG POWERSHELL_SHA256_ARM64=2503b71da3e83635592b092df59a0aca4c3606b4d9b068217bb00be989cb0d56
|
||||
ARG POWERSHELL_SHA256_AMD64=82a8b13d92b0f3ae48e56cf2f3f7961679371736ca90145ca71617c2913ba9d8
|
||||
ARG POWERSHELL_SHA256_ARM64=830ebda118c731ece3fa7e6b7e8573a21346387cbbca5b2f5e3b9bfe24f96672
|
||||
ARG ZIZMOR_SHA256_AMD64=a8000f3c683319a523d3b20df0e75457ba591f049cfcbfa98966631b56733c03
|
||||
ARG ZIZMOR_SHA256_ARM64=d66e37ef8a375fb07939c630ebf9709a6e0f20242bdc3faf672a7ed97e0b768d
|
||||
|
||||
# High CVEs fixed in Debian trixie-security but not yet in the pinned base image:
|
||||
# High CVEs fixed in Debian trixie but not yet in the pinned base image:
|
||||
# openssl/libssl3t64/openssl-provider-legacy 3.5.7-1~deb13u2 CVE-2026-14456,
|
||||
# -14457, -18798, -54874, -63072, -63073, -63074, -63075, -63076, -75803
|
||||
# (image ships 3.5.6-1~deb13u2)
|
||||
# libsqlite3-0 3.46.1-7+deb13u2 CVE-2026-11822, -11824
|
||||
# gzip 1.13-1+deb13u1 CVE-2026-41992
|
||||
# perl-base 5.40.1-6+deb13u1 CVE-2026-42497, -48962, -57432
|
||||
# libssh2-1t64 1.11.1-1+deb13u2 CVE-2026-58050
|
||||
# libpcre2-8-0 10.46-1~deb13u2 CVE-2026-86145, -89161
|
||||
# Taken as a targeted --only-upgrade rather than by moving the digest: the newest
|
||||
# published python:3.12-slim-trixie carries the same vulnerable version. The three
|
||||
# packages are all built from openssl and are flagged separately, so all are named.
|
||||
# Drop them once the base image ships 3.5.7-1~deb13u2 or later.
|
||||
# published python:3.12-slim-trixie carries the same vulnerable versions. The three
|
||||
# openssl packages are flagged separately, so all are named.
|
||||
# Drop each one once the base image ships its fixed version.
|
||||
# hadolint ignore=DL3008
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
wget \
|
||||
@@ -46,6 +50,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
python3-dev \
|
||||
&& apt-get install -y --no-install-recommends --only-upgrade \
|
||||
util-linux libssl3t64 openssl openssl-provider-legacy \
|
||||
libsqlite3-0 gzip perl-base libssh2-1t64 libpcre2-8-0 \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install PowerShell
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
Adds a periodic sweep that drops orphaned Attack Paths temp Neo4j scan databases left behind when a worker or Neo4j crashes mid-scan, before they accumulate unbounded
|
||||
@@ -1 +0,0 @@
|
||||
Speed up compliance overview ingestion by reading ThreatScore mappings from the compliance template instead of each finding, generating time-ordered `uuid7` row ids and grouping inserted rows by framework and requirement
|
||||
@@ -0,0 +1 @@
|
||||
Resources no longer keep a stale failed findings count forever when a scoped or imported scan for the same provider completes after a full scan, which used to make the full scan skip its own cleanup
|
||||
@@ -0,0 +1 @@
|
||||
Providers whose most recent completed scan has no `completed_at` timestamp are no longer missing from every endpoint that reports a provider's latest scan, which now falls back to scan creation order instead of skipping the provider
|
||||
@@ -0,0 +1 @@
|
||||
Unify how every endpoint resolves a provider latest completed scan, so overlapping scans no longer make findings, compliance and mute rules read from different scans
|
||||
@@ -0,0 +1 @@
|
||||
Scan output uploads and downloads can now target S3-compatible object storage such as MinIO directly via `DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL`, instead of relying on process-wide AWS environment variables that also hijacked unrelated AWS API calls
|
||||
@@ -0,0 +1 @@
|
||||
Scan report downloads from an S3 bucket with default SSE-KMS encryption no longer fail with an `InvalidArgument` error: when `DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION` is set, presigned download URLs are signed with AWS Signature Version 4 for that region
|
||||
@@ -0,0 +1 @@
|
||||
`POST /api/v1/scans` again returns the new scan id in the response `task_args`, which had been empty since the scan broker publish moved to transaction commit
|
||||
@@ -0,0 +1 @@
|
||||
Celery loggers are now declared explicitly in `custom_logging.py` so fatal worker errors are no longer silenced by `disable_existing_loggers=True`. All long-running services in `docker-compose.yml` now have `restart: unless-stopped` so containers recover automatically after unexpected crashes.
|
||||
+2
-2
@@ -71,7 +71,7 @@ name = "prowler-api"
|
||||
package-mode = false
|
||||
# Needed for the SDK compatibility
|
||||
requires-python = ">=3.11,<3.13"
|
||||
version = "1.43.0"
|
||||
version = "1.45.0"
|
||||
|
||||
# Shared ruff baseline (kept in sync with mcp_server/pyproject.toml).
|
||||
# target-version tracks this project's lowest supported Python.
|
||||
@@ -137,7 +137,7 @@ constraint-dependencies = [
|
||||
"aliyun-log-fastpb==0.2.0",
|
||||
"amqp==5.3.1",
|
||||
"annotated-types==0.7.0",
|
||||
"anyio==4.12.1",
|
||||
"anyio==4.14.2",
|
||||
"applicationinsights==0.11.10",
|
||||
"apscheduler==3.11.2",
|
||||
"argcomplete==3.5.3",
|
||||
|
||||
@@ -207,6 +207,11 @@ def drop_database(database: str) -> None:
|
||||
sink_module.get_backend().drop_database(database)
|
||||
|
||||
|
||||
def list_databases() -> list[str]:
|
||||
"""List database names on the ingest cluster. Temp scan DBs always live here."""
|
||||
return ingest.list_databases()
|
||||
|
||||
|
||||
def drop_subgraph(database: str, provider_id: str) -> int:
|
||||
return sink_module.get_backend().drop_subgraph(database, provider_id)
|
||||
|
||||
|
||||
@@ -13,6 +13,7 @@ from api.attack_paths.ingest.driver import (
|
||||
get_session,
|
||||
get_uri,
|
||||
init_driver,
|
||||
list_databases,
|
||||
run_cypher,
|
||||
)
|
||||
|
||||
@@ -25,5 +26,6 @@ __all__ = [
|
||||
"get_session",
|
||||
"get_uri",
|
||||
"init_driver",
|
||||
"list_databases",
|
||||
"run_cypher",
|
||||
]
|
||||
|
||||
@@ -165,6 +165,14 @@ def drop_database(database: str) -> None:
|
||||
session.run(f"DROP DATABASE `{database}` IF EXISTS DESTROY DATA")
|
||||
|
||||
|
||||
def list_databases() -> list[str]:
|
||||
"""List every database name on the Neo4j temp-database cluster."""
|
||||
# A cluster returns one row per hosting server, so dedupe on name
|
||||
with get_session() as session:
|
||||
result = session.run("SHOW DATABASES YIELD name RETURN DISTINCT name")
|
||||
return [record["name"] for record in result]
|
||||
|
||||
|
||||
def clear_cache(database: str) -> None:
|
||||
"""Best-effort cache clear for a Neo4j database."""
|
||||
from api.attack_paths.database import GraphDatabaseQueryException
|
||||
|
||||
@@ -409,7 +409,7 @@ def batch_delete(tenant_id, queryset, batch_size=settings.DJANGO_DELETION_BATCH_
|
||||
|
||||
Args:
|
||||
tenant_id (str): Tenant ID the queryset belongs to.
|
||||
queryset (QuerySet): The queryset of objects to delete.
|
||||
queryset: The queryset of objects to delete.
|
||||
batch_size (int): The number of objects to delete in each batch.
|
||||
|
||||
Returns:
|
||||
|
||||
@@ -1439,8 +1439,20 @@ class InvitationFilter(FilterSet):
|
||||
inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
|
||||
updated_at = DateFilter(field_name="updated_at", lookup_expr="date")
|
||||
expires_at = DateFilter(field_name="expires_at", lookup_expr="date")
|
||||
state = ChoiceFilter(choices=Invitation.State.choices)
|
||||
state__in = ChoiceInFilter(choices=Invitation.State.choices, lookup_expr="in")
|
||||
state = ChoiceFilter(choices=Invitation.State.choices, method="filter_state")
|
||||
state__in = ChoiceInFilter(
|
||||
choices=Invitation.State.choices, lookup_expr="in", method="filter_state_in"
|
||||
)
|
||||
|
||||
def filter_state(self, queryset, name, value):
|
||||
return self.filter_state_in(queryset, name, [value])
|
||||
|
||||
def filter_state_in(self, queryset, name, value):
|
||||
lapsed = Invitation.lapsed_q()
|
||||
query = Q(state__in=value) & ~lapsed
|
||||
if Invitation.State.EXPIRED in value:
|
||||
query |= lapsed
|
||||
return queryset.filter(query)
|
||||
|
||||
class Meta:
|
||||
model = Invitation
|
||||
|
||||
@@ -0,0 +1,116 @@
|
||||
import uuid
|
||||
|
||||
import api.rls
|
||||
import django.db.models.deletion
|
||||
from django.conf import settings
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("api", "0097_attack_paths_scan_db_defaults"),
|
||||
migrations.swappable_dependency(settings.AUTH_USER_MODEL),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name="TenantOnboardingProfile",
|
||||
fields=[
|
||||
(
|
||||
"id",
|
||||
models.UUIDField(
|
||||
default=uuid.uuid4,
|
||||
editable=False,
|
||||
primary_key=True,
|
||||
serialize=False,
|
||||
),
|
||||
),
|
||||
("inserted_at", models.DateTimeField(auto_now_add=True)),
|
||||
(
|
||||
"declared_cloud_accounts",
|
||||
models.CharField(
|
||||
blank=True,
|
||||
choices=[
|
||||
("1", "1"),
|
||||
("2-10", "2-10"),
|
||||
("11-50", "11-50"),
|
||||
("51-200", "51-200"),
|
||||
("200+", "200+"),
|
||||
],
|
||||
max_length=16,
|
||||
null=True,
|
||||
),
|
||||
),
|
||||
(
|
||||
"declared_role",
|
||||
models.CharField(
|
||||
blank=True,
|
||||
choices=[
|
||||
("security", "Security"),
|
||||
("devops_platform", "DevOps / Platform"),
|
||||
("developer", "Developer"),
|
||||
("compliance_grc", "Compliance / GRC"),
|
||||
("other", "Other"),
|
||||
],
|
||||
max_length=32,
|
||||
null=True,
|
||||
),
|
||||
),
|
||||
(
|
||||
"declared_seniority",
|
||||
models.CharField(
|
||||
blank=True,
|
||||
choices=[
|
||||
("practitioner", "Practitioner / IC"),
|
||||
("lead", "Team lead / Manager"),
|
||||
("director", "Director / Head of"),
|
||||
("executive", "VP / C-level"),
|
||||
("founder", "Founder / Owner"),
|
||||
],
|
||||
max_length=32,
|
||||
null=True,
|
||||
),
|
||||
),
|
||||
("skipped", models.BooleanField(default=False)),
|
||||
(
|
||||
"submitted_by",
|
||||
models.ForeignKey(
|
||||
blank=True,
|
||||
null=True,
|
||||
on_delete=django.db.models.deletion.SET_NULL,
|
||||
related_name="tenant_onboarding_profiles",
|
||||
related_query_name="tenant_onboarding_profile",
|
||||
to=settings.AUTH_USER_MODEL,
|
||||
),
|
||||
),
|
||||
(
|
||||
"tenant",
|
||||
models.ForeignKey(
|
||||
on_delete=django.db.models.deletion.CASCADE, to="api.tenant"
|
||||
),
|
||||
),
|
||||
],
|
||||
options={
|
||||
"db_table": "tenant_onboarding_profiles",
|
||||
"abstract": False,
|
||||
},
|
||||
),
|
||||
migrations.AddConstraint(
|
||||
model_name="tenantonboardingprofile",
|
||||
constraint=models.UniqueConstraint(
|
||||
fields=("tenant_id",), name="unique_tenant_onboarding_profile"
|
||||
),
|
||||
),
|
||||
migrations.AddConstraint(
|
||||
model_name="tenantonboardingprofile",
|
||||
# `statements` written out explicitly: RowLevelSecurityConstraint
|
||||
# .deconstruct() does not serialize it, so an autogenerated
|
||||
# migration falls back to ["SELECT"] and leaves the table without
|
||||
# INSERT/UPDATE/DELETE policies.
|
||||
constraint=api.rls.RowLevelSecurityConstraint(
|
||||
"tenant_id",
|
||||
name="rls_on_tenantonboardingprofile",
|
||||
statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -0,0 +1,15 @@
|
||||
from django.db import migrations
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
# The onboarding profile step was reverted after 0098 had been merged, so
|
||||
# the table goes away through a new migration rather than by deleting 0098.
|
||||
dependencies = [
|
||||
("api", "0098_tenant_onboarding_profile"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.DeleteModel(
|
||||
name="TenantOnboardingProfile",
|
||||
),
|
||||
]
|
||||
@@ -0,0 +1,48 @@
|
||||
from django.db import migrations
|
||||
|
||||
TASK_NAME = "attack-paths-reap-orphaned-tmp-databases"
|
||||
INTERVAL_HOURS = 6
|
||||
|
||||
|
||||
def create_periodic_task(apps, schema_editor):
|
||||
IntervalSchedule = apps.get_model("django_celery_beat", "IntervalSchedule")
|
||||
PeriodicTask = apps.get_model("django_celery_beat", "PeriodicTask")
|
||||
|
||||
schedule, _ = IntervalSchedule.objects.get_or_create(
|
||||
every=INTERVAL_HOURS,
|
||||
period="hours",
|
||||
)
|
||||
|
||||
PeriodicTask.objects.update_or_create(
|
||||
name=TASK_NAME,
|
||||
defaults={
|
||||
"task": TASK_NAME,
|
||||
"interval": schedule,
|
||||
"enabled": True,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
def delete_periodic_task(apps, schema_editor):
|
||||
IntervalSchedule = apps.get_model("django_celery_beat", "IntervalSchedule")
|
||||
PeriodicTask = apps.get_model("django_celery_beat", "PeriodicTask")
|
||||
|
||||
PeriodicTask.objects.filter(name=TASK_NAME).delete()
|
||||
|
||||
# Clean up the schedule if no other task references it
|
||||
IntervalSchedule.objects.filter(
|
||||
every=INTERVAL_HOURS,
|
||||
period="hours",
|
||||
periodictask__isnull=True,
|
||||
).delete()
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("api", "0099_delete_tenant_onboarding_profile"),
|
||||
("django_celery_beat", "0019_alter_periodictasks_options"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.RunPython(create_periodic_task, delete_periodic_task),
|
||||
]
|
||||
@@ -617,9 +617,66 @@ class Task(RowLevelSecurityProtectedModel):
|
||||
resource_name = "tasks"
|
||||
|
||||
|
||||
class ScanQuerySet(models.QuerySet):
|
||||
"""Shared selectors for "the latest scan of a provider".
|
||||
|
||||
The queryset must already be scoped by the caller: manager, tenant, RBAC,
|
||||
providers and database alias.
|
||||
"""
|
||||
|
||||
# How "which completed scan is the provider's current one" is ordered.
|
||||
LATEST_ORDER_BY = (
|
||||
models.F("completed_at").desc(nulls_last=True),
|
||||
models.F("inserted_at").desc(),
|
||||
models.F("id").desc(),
|
||||
)
|
||||
|
||||
def _eligible_for_latest(self) -> "ScanQuerySet":
|
||||
"""Restrict to the scans that may be a provider's latest.
|
||||
|
||||
Returns:
|
||||
ScanQuerySet: The completed scans.
|
||||
"""
|
||||
return self.filter(state=StateChoices.COMPLETED)
|
||||
|
||||
def latest_per_provider(self) -> "ScanQuerySet":
|
||||
"""Pick each provider's latest scan with `DISTINCT ON (provider_id)`.
|
||||
|
||||
Returns:
|
||||
ScanQuerySet: One scan per provider, the latest one.
|
||||
"""
|
||||
return (
|
||||
self._eligible_for_latest()
|
||||
.order_by("provider_id", *self.LATEST_ORDER_BY)
|
||||
.distinct("provider_id")
|
||||
)
|
||||
|
||||
def latest_ids_per_provider(self) -> list[UUID]:
|
||||
"""Evaluate `latest_per_provider` and return the scan ids.
|
||||
|
||||
The ids are materialised so callers can pass them as a literal `IN`
|
||||
list; as a subquery Postgres misestimates the row count and picks a
|
||||
slow nested loop.
|
||||
|
||||
Returns:
|
||||
list[UUID]: The id of each provider's latest scan.
|
||||
"""
|
||||
return list(self.latest_per_provider().values_list("id", flat=True))
|
||||
|
||||
def latest_first(self) -> "ScanQuerySet":
|
||||
"""Order eligible scans newest first, without deduplicating per provider.
|
||||
|
||||
Expects the queryset to be already filtered to a single provider.
|
||||
|
||||
Returns:
|
||||
ScanQuerySet: The eligible scans, latest first.
|
||||
"""
|
||||
return self._eligible_for_latest().order_by(*self.LATEST_ORDER_BY)
|
||||
|
||||
|
||||
class Scan(RowLevelSecurityProtectedModel):
|
||||
objects = ActiveProviderManager()
|
||||
all_objects = models.Manager()
|
||||
objects = ActiveProviderManager.from_queryset(ScanQuerySet)()
|
||||
all_objects = ScanQuerySet.as_manager()
|
||||
|
||||
_SCOPING_SCANNER_ARG_KEYS_CACHE: tuple[str, ...] | None = None
|
||||
|
||||
@@ -726,6 +783,12 @@ class Scan(RowLevelSecurityProtectedModel):
|
||||
name="scans_prov_state_ins_desc_idx",
|
||||
),
|
||||
# TODO This might replace `scans_prov_state_ins_desc_idx` completely. Review usage
|
||||
# Since `ScanQuerySet`, no code path reads a provider's
|
||||
# completed scans by `-inserted_at`. The only query left that
|
||||
# matches this index (and `scans_prov_state_ins_desc_idx` above)
|
||||
# is `GET /scans?filter[provider]=…&filter[state]=completed` with
|
||||
# the default sort. Both are candidates to drop in a follow-up
|
||||
# once production `pg_stat_user_indexes.idx_scan` confirms it.
|
||||
models.Index(
|
||||
fields=["tenant_id", "provider_id", "-inserted_at"],
|
||||
condition=Q(state=StateChoices.COMPLETED),
|
||||
@@ -1380,6 +1443,15 @@ class Invitation(RowLevelSecurityProtectedModel):
|
||||
self.email = self.email.strip().lower()
|
||||
super().save(*args, **kwargs)
|
||||
|
||||
@classmethod
|
||||
def lapsed_q(cls):
|
||||
"""Pending invitations whose expiry date has already passed."""
|
||||
return Q(state=cls.State.PENDING, expires_at__lte=datetime.now(UTC))
|
||||
|
||||
@property
|
||||
def is_lapsed(self):
|
||||
return self.state == self.State.PENDING and self.expires_at <= datetime.now(UTC)
|
||||
|
||||
class Meta(RowLevelSecurityProtectedModel.Meta):
|
||||
db_table = "invitations"
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
openapi: 3.0.3
|
||||
info:
|
||||
title: Prowler API
|
||||
version: 1.43.0
|
||||
version: 1.45.0
|
||||
description: |-
|
||||
Prowler API specification.
|
||||
|
||||
|
||||
@@ -187,6 +187,27 @@ class TestRoutingByDatabasePrefix:
|
||||
sink_backend_stub.drop_database.assert_called_once_with("db-tenant-abc")
|
||||
mock_ingest.drop_database.assert_not_called()
|
||||
|
||||
def test_list_databases_always_routes_to_ingest(self, sink_backend_stub):
|
||||
with patch("api.attack_paths.database.ingest") as mock_ingest:
|
||||
mock_ingest.list_databases.return_value = ["db-tmp-scan-uuid-1"]
|
||||
|
||||
assert db_module.list_databases() == ["db-tmp-scan-uuid-1"]
|
||||
|
||||
mock_ingest.list_databases.assert_called_once_with()
|
||||
|
||||
def test_ingest_list_databases_dedupes_cluster_rows(self):
|
||||
from api.attack_paths.ingest import driver as ingest_driver
|
||||
|
||||
with patch.object(ingest_driver, "get_session") as mock_get_session:
|
||||
session = mock_get_session.return_value.__enter__.return_value
|
||||
session.run.return_value = [{"name": "db-tmp-scan-uuid-1"}]
|
||||
|
||||
assert ingest_driver.list_databases() == ["db-tmp-scan-uuid-1"]
|
||||
|
||||
session.run.assert_called_once_with(
|
||||
"SHOW DATABASES YIELD name RETURN DISTINCT name"
|
||||
)
|
||||
|
||||
def test_clear_cache_routes_temp_to_ingest(self, sink_backend_stub):
|
||||
with patch("api.attack_paths.database.ingest") as mock_ingest:
|
||||
db_module.clear_cache("db-tmp-scan-uuid-1")
|
||||
|
||||
@@ -1,14 +1,16 @@
|
||||
from datetime import UTC, datetime
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
import pytest
|
||||
from allauth.socialaccount.models import SocialApp
|
||||
from api.db_router import MainRouter
|
||||
from api.models import (
|
||||
Provider,
|
||||
ProviderComplianceScore,
|
||||
Resource,
|
||||
ResourceTag,
|
||||
SAMLConfiguration,
|
||||
SAMLDomainIndex,
|
||||
Scan,
|
||||
StateChoices,
|
||||
StatusChoices,
|
||||
TenantComplianceSummary,
|
||||
@@ -524,3 +526,226 @@ class TestTenantComplianceSummaryModel:
|
||||
|
||||
assert summary1.id != summary2.id
|
||||
assert summary1.requirements_passed != summary2.requirements_passed
|
||||
|
||||
|
||||
def _latest_scan_fixture(tenant, provider, *, completed_at, inserted_at=None, **kwargs):
|
||||
scan = Scan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=provider,
|
||||
trigger=kwargs.pop("trigger", Scan.TriggerChoices.MANUAL),
|
||||
state=kwargs.pop("state", StateChoices.COMPLETED),
|
||||
completed_at=completed_at,
|
||||
**kwargs,
|
||||
)
|
||||
if inserted_at is not None:
|
||||
# `inserted_at` is auto_now_add, so it has to be forced after the fact.
|
||||
Scan.all_objects.filter(pk=scan.pk).update(inserted_at=inserted_at)
|
||||
scan.refresh_from_db()
|
||||
return scan
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetOrdering:
|
||||
def test_completed_later_wins_over_inserted_later(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""The scan that FINISHED last is current, not the one that started last."""
|
||||
tenant, *_ = tenants_fixture
|
||||
now = datetime.now(UTC)
|
||||
|
||||
finished_last = _latest_scan_fixture(
|
||||
tenant,
|
||||
aws_provider,
|
||||
inserted_at=now - timedelta(hours=3),
|
||||
completed_at=now,
|
||||
)
|
||||
_latest_scan_fixture(
|
||||
tenant,
|
||||
aws_provider,
|
||||
inserted_at=now - timedelta(hours=1),
|
||||
completed_at=now - timedelta(hours=1),
|
||||
)
|
||||
|
||||
assert Scan.all_objects.filter(
|
||||
tenant_id=tenant.id
|
||||
).latest_ids_per_provider() == [finished_last.id]
|
||||
|
||||
def test_null_completed_at_provider_is_still_returned(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""NULLS LAST, not `completed_at__isnull=False`.
|
||||
|
||||
Excluding NULL `completed_at` would drop the provider from every
|
||||
"latest" endpoint instead of falling back to `inserted_at`.
|
||||
"""
|
||||
tenant, *_ = tenants_fixture
|
||||
only_scan = _latest_scan_fixture(tenant, aws_provider, completed_at=None)
|
||||
|
||||
assert Scan.all_objects.filter(
|
||||
tenant_id=tenant.id
|
||||
).latest_ids_per_provider() == [only_scan.id]
|
||||
|
||||
def test_null_completed_at_never_outranks_a_finished_scan(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""Postgres sorts NULLs first under DESC; NULLS LAST is what fixes it."""
|
||||
tenant, *_ = tenants_fixture
|
||||
now = datetime.now(UTC)
|
||||
|
||||
finished = _latest_scan_fixture(
|
||||
tenant,
|
||||
aws_provider,
|
||||
inserted_at=now - timedelta(hours=2),
|
||||
completed_at=now - timedelta(hours=2),
|
||||
)
|
||||
_latest_scan_fixture(
|
||||
tenant,
|
||||
aws_provider,
|
||||
inserted_at=now,
|
||||
completed_at=None,
|
||||
)
|
||||
|
||||
assert Scan.all_objects.filter(
|
||||
tenant_id=tenant.id
|
||||
).latest_ids_per_provider() == [finished.id]
|
||||
|
||||
def test_id_breaks_an_exact_timestamp_tie_deterministically(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
tenant, *_ = tenants_fixture
|
||||
now = datetime.now(UTC)
|
||||
|
||||
scans = [
|
||||
_latest_scan_fixture(
|
||||
tenant, aws_provider, inserted_at=now, completed_at=now
|
||||
)
|
||||
for _ in range(3)
|
||||
]
|
||||
expected = max(scan.id for scan in scans)
|
||||
|
||||
picks = {
|
||||
Scan.all_objects.filter(tenant_id=tenant.id).latest_ids_per_provider()[0]
|
||||
for _ in range(5)
|
||||
}
|
||||
assert picks == {expected}
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetEligibility:
|
||||
def test_unfinished_scans_are_excluded(self, tenants_fixture, aws_provider):
|
||||
tenant, *_ = tenants_fixture
|
||||
_latest_scan_fixture(
|
||||
tenant,
|
||||
aws_provider,
|
||||
completed_at=None,
|
||||
state=StateChoices.EXECUTING,
|
||||
)
|
||||
assert (
|
||||
Scan.all_objects.filter(tenant_id=tenant.id).latest_ids_per_provider() == []
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetManagerChoice:
|
||||
def test_active_manager_hides_soft_deleted_providers(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""`Scan.objects` drops soft-deleted providers, `all_objects` keeps them.
|
||||
|
||||
The queryset must not decide this for the caller.
|
||||
"""
|
||||
tenant, *_ = tenants_fixture
|
||||
scan = _latest_scan_fixture(
|
||||
tenant, aws_provider, completed_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
Provider.all_objects.filter(pk=aws_provider.pk).update(is_deleted=True)
|
||||
|
||||
assert Scan.all_objects.filter(
|
||||
tenant_id=tenant.id
|
||||
).latest_ids_per_provider() == [scan.id]
|
||||
assert Scan.objects.filter(tenant_id=tenant.id).latest_ids_per_provider() == []
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetPerProviderScoping:
|
||||
def test_one_scan_per_provider(self, tenants_fixture, aws_provider_pair):
|
||||
tenant, *_ = tenants_fixture
|
||||
provider_one, provider_two = aws_provider_pair
|
||||
now = datetime.now(UTC)
|
||||
|
||||
newest_one = _latest_scan_fixture(tenant, provider_one, completed_at=now)
|
||||
_latest_scan_fixture(tenant, provider_one, completed_at=now - timedelta(days=1))
|
||||
newest_two = _latest_scan_fixture(tenant, provider_two, completed_at=now)
|
||||
|
||||
assert set(
|
||||
Scan.all_objects.filter(tenant_id=tenant.id).latest_ids_per_provider()
|
||||
) == {newest_one.id, newest_two.id}
|
||||
|
||||
def test_caller_filters_are_preserved(self, tenants_fixture, aws_provider_pair):
|
||||
tenant, *_ = tenants_fixture
|
||||
provider_one, provider_two = aws_provider_pair
|
||||
now = datetime.now(UTC)
|
||||
|
||||
scan_one = _latest_scan_fixture(tenant, provider_one, completed_at=now)
|
||||
_latest_scan_fixture(tenant, provider_two, completed_at=now)
|
||||
|
||||
assert Scan.all_objects.filter(
|
||||
tenant_id=tenant.id, provider__in=[provider_one]
|
||||
).latest_ids_per_provider() == [scan_one.id]
|
||||
|
||||
def test_latest_first_is_ordered_not_deduplicated(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
tenant, *_ = tenants_fixture
|
||||
now = datetime.now(UTC)
|
||||
|
||||
newest = _latest_scan_fixture(tenant, aws_provider, completed_at=now)
|
||||
older = _latest_scan_fixture(
|
||||
tenant, aws_provider, completed_at=now - timedelta(days=1)
|
||||
)
|
||||
|
||||
ordered = list(
|
||||
Scan.all_objects.filter(
|
||||
tenant_id=tenant.id, provider_id=aws_provider.id
|
||||
).latest_first()
|
||||
)
|
||||
assert [scan.id for scan in ordered] == [newest.id, older.id]
|
||||
|
||||
def test_tenant_isolation(self, tenants_fixture, aws_provider):
|
||||
tenant, other_tenant, *_ = tenants_fixture
|
||||
_latest_scan_fixture(tenant, aws_provider, completed_at=datetime.now(UTC))
|
||||
|
||||
assert (
|
||||
Scan.all_objects.filter(tenant_id=other_tenant.id).latest_ids_per_provider()
|
||||
== []
|
||||
)
|
||||
|
||||
def test_empty_queryset_returns_empty_list(self, tenants_fixture):
|
||||
tenant, *_ = tenants_fixture
|
||||
assert (
|
||||
Scan.all_objects.filter(tenant_id=tenant.id).latest_ids_per_provider() == []
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetPerProviderQuerysetShape:
|
||||
def test_returns_a_queryset_not_a_list(self, tenants_fixture, aws_provider):
|
||||
tenant, *_ = tenants_fixture
|
||||
_latest_scan_fixture(tenant, aws_provider, completed_at=datetime.now(UTC))
|
||||
|
||||
qs = Scan.all_objects.filter(tenant_id=tenant.id).latest_per_provider()
|
||||
# Callers chain .values(...) / .values_list(...) onto this.
|
||||
assert qs.values_list("provider_id", flat=True).count() == 1
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestScanQuerySetRelatedManager:
|
||||
def test_reverse_relation_exposes_the_methods(self, tenants_fixture, aws_provider):
|
||||
tenant, *_ = tenants_fixture
|
||||
now = datetime.now(UTC)
|
||||
|
||||
newest = _latest_scan_fixture(tenant, aws_provider, completed_at=now)
|
||||
_latest_scan_fixture(tenant, aws_provider, completed_at=now - timedelta(days=1))
|
||||
|
||||
assert aws_provider.scans.latest_first().first().id == newest.id
|
||||
|
||||
@@ -82,7 +82,7 @@ from django.db import close_old_connections, connection, connections
|
||||
from django.db.models import Count
|
||||
from django.db.models.signals import pre_delete
|
||||
from django.http import JsonResponse
|
||||
from django.test import RequestFactory
|
||||
from django.test import RequestFactory, override_settings
|
||||
from django.test.utils import CaptureQueriesContext
|
||||
from django.urls import reverse
|
||||
from django_celery_results.models import TaskResult
|
||||
@@ -3951,6 +3951,43 @@ class TestScanViewSet:
|
||||
mock_enqueue_scan_execution.assert_called_once()
|
||||
# assert scan.scanner_args == expected_scanner_args
|
||||
|
||||
@patch("api.v1.views.enqueue_scan_execution_on_commit")
|
||||
def test_scans_create_returns_the_scan_id_in_task_args(
|
||||
self,
|
||||
mock_enqueue_scan_execution,
|
||||
authenticated_client,
|
||||
okta_provider,
|
||||
):
|
||||
"""The 202 is a task, so `task_args` is the only place the scan id is.
|
||||
|
||||
It is serialized before the on_commit publish that would otherwise fill
|
||||
the kwargs, so the record has to carry them from the start.
|
||||
"""
|
||||
payload = {
|
||||
"data": {
|
||||
"type": "scans",
|
||||
"attributes": {"name": "New Scan"},
|
||||
"relationships": {
|
||||
"provider": {
|
||||
"data": {"type": "providers", "id": str(okta_provider.id)}
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
response = authenticated_client.post(
|
||||
reverse("scan-list"),
|
||||
data=payload,
|
||||
content_type=API_JSON_CONTENT_TYPE,
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_202_ACCEPTED
|
||||
scan = Scan.objects.get()
|
||||
assert response.json()["data"]["attributes"]["task_args"] == {
|
||||
"scan_id": str(scan.id),
|
||||
"provider_id": str(okta_provider.id),
|
||||
}
|
||||
|
||||
@patch("tasks.tasks.perform_scan_task.apply_async")
|
||||
def test_scans_create_queues_scan_when_provider_has_active_scan(
|
||||
self,
|
||||
@@ -4540,6 +4577,52 @@ class TestScanViewSet:
|
||||
assert response.status_code == status.HTTP_302_FOUND
|
||||
assert response["Location"] == presigned_url
|
||||
|
||||
@override_settings(
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID="access-key",
|
||||
DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY="secret-key",
|
||||
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN="",
|
||||
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION="eu-west-1",
|
||||
)
|
||||
def test_report_s3_redirects_to_the_public_storage_host(
|
||||
self, authenticated_client, scans_fixture, monkeypatch
|
||||
):
|
||||
"""The object is looked up internally but the redirect the browser follows is public."""
|
||||
scan = scans_fixture[0]
|
||||
bucket = "test-bucket"
|
||||
key = "report.zip"
|
||||
scan.output_location = f"s3://{bucket}/{key}"
|
||||
scan.state = StateChoices.COMPLETED
|
||||
scan.save()
|
||||
|
||||
monkeypatch.setattr(
|
||||
"api.v1.views.env",
|
||||
type("env", (), {"str": lambda self, *_args, **_kwargs: bucket})(),
|
||||
)
|
||||
|
||||
head_calls = []
|
||||
|
||||
class InternalS3Client:
|
||||
def head_object(self, Bucket, Key):
|
||||
head_calls.append((Bucket, Key))
|
||||
return {}
|
||||
|
||||
def generate_presigned_url(self, *_args, **_kwargs):
|
||||
raise AssertionError("the internal client must not sign the redirect")
|
||||
|
||||
monkeypatch.setattr("api.v1.views.get_s3_client", lambda: InternalS3Client())
|
||||
|
||||
url = reverse("scan-report", kwargs={"pk": scan.id})
|
||||
response = authenticated_client.get(url)
|
||||
|
||||
assert response.status_code == status.HTTP_302_FOUND
|
||||
assert head_calls == [(bucket, key)]
|
||||
|
||||
location = urlparse(response["Location"])
|
||||
assert location.netloc == "storage.example.com"
|
||||
assert location.path == f"/{bucket}/{key}"
|
||||
assert "X-Amz-Signature" in parse_qs(location.query)
|
||||
|
||||
def test_report_s3_success_no_local_files(
|
||||
self, authenticated_client, scans_fixture, monkeypatch
|
||||
):
|
||||
@@ -8784,6 +8867,190 @@ class TestInvitationViewSet:
|
||||
user.id
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _invitation_create_payload(email, role):
|
||||
return json.dumps(
|
||||
{
|
||||
"data": {
|
||||
"type": "invitations",
|
||||
"attributes": {"email": email},
|
||||
"relationships": {
|
||||
"roles": {"data": [{"type": "roles", "id": str(role.id)}]}
|
||||
},
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _create_lapsed_invitation(email, tenant, inviter):
|
||||
return Invitation.objects.create(
|
||||
email=email,
|
||||
state=Invitation.State.PENDING,
|
||||
expires_at=datetime.now(UTC) - timedelta(days=1),
|
||||
inviter=inviter,
|
||||
tenant=tenant,
|
||||
)
|
||||
|
||||
def test_invitations_create_with_lapsed_pending_invitation_for_same_email(
|
||||
self,
|
||||
authenticated_client,
|
||||
create_test_user,
|
||||
tenants_fixture,
|
||||
invitations_fixture,
|
||||
roles_fixture,
|
||||
):
|
||||
lapsed_invitation, expired_invitation = invitations_fixture
|
||||
lapsed_invitation.expires_at = datetime.now(UTC) - timedelta(days=1)
|
||||
lapsed_invitation.save()
|
||||
other_email_lapsed_invitation = self._create_lapsed_invitation(
|
||||
"other@prowler.com", tenants_fixture[0], create_test_user
|
||||
)
|
||||
|
||||
response = authenticated_client.post(
|
||||
reverse("invitation-list"),
|
||||
data=self._invitation_create_payload(
|
||||
lapsed_invitation.email, roles_fixture[0]
|
||||
),
|
||||
content_type="application/vnd.api+json",
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_201_CREATED
|
||||
new_invitation = Invitation.objects.get(id=response.json()["data"]["id"])
|
||||
assert new_invitation.email == lapsed_invitation.email
|
||||
assert new_invitation.state == Invitation.State.PENDING
|
||||
lapsed_invitation.refresh_from_db()
|
||||
assert lapsed_invitation.state == Invitation.State.EXPIRED
|
||||
expired_invitation.refresh_from_db()
|
||||
assert expired_invitation.state == Invitation.State.EXPIRED
|
||||
other_email_lapsed_invitation.refresh_from_db()
|
||||
assert other_email_lapsed_invitation.state == Invitation.State.PENDING
|
||||
|
||||
def test_invitations_create_with_active_pending_invitation_for_same_email(
|
||||
self,
|
||||
authenticated_client,
|
||||
create_test_user,
|
||||
tenants_fixture,
|
||||
invitations_fixture,
|
||||
roles_fixture,
|
||||
):
|
||||
active_invitation, _ = invitations_fixture
|
||||
self._create_lapsed_invitation(
|
||||
active_invitation.email, tenants_fixture[0], create_test_user
|
||||
)
|
||||
invitation_count = Invitation.objects.count()
|
||||
|
||||
response = authenticated_client.post(
|
||||
reverse("invitation-list"),
|
||||
data=self._invitation_create_payload(
|
||||
active_invitation.email, roles_fixture[0]
|
||||
),
|
||||
content_type="application/vnd.api+json",
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_400_BAD_REQUEST
|
||||
assert (
|
||||
response.json()["errors"][0]["source"]["pointer"]
|
||||
== "/data/attributes/email"
|
||||
)
|
||||
assert Invitation.objects.count() == invitation_count
|
||||
active_invitation.refresh_from_db()
|
||||
assert active_invitation.state == Invitation.State.PENDING
|
||||
|
||||
def test_invitations_create_ignores_pending_invitations_from_other_tenants(
|
||||
self, authenticated_client, create_test_user, tenants_fixture, roles_fixture
|
||||
):
|
||||
email = "cross_tenant@prowler.com"
|
||||
other_tenant = tenants_fixture[1]
|
||||
other_tenant_lapsed_invitation = self._create_lapsed_invitation(
|
||||
email, other_tenant, create_test_user
|
||||
)
|
||||
Invitation.objects.create(
|
||||
email=email, inviter=create_test_user, tenant=other_tenant
|
||||
)
|
||||
|
||||
response = authenticated_client.post(
|
||||
reverse("invitation-list"),
|
||||
data=self._invitation_create_payload(email, roles_fixture[0]),
|
||||
content_type="application/vnd.api+json",
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_201_CREATED
|
||||
other_tenant_lapsed_invitation.refresh_from_db()
|
||||
assert other_tenant_lapsed_invitation.state == Invitation.State.PENDING
|
||||
|
||||
def test_invitations_report_lapsed_pending_invitation_as_expired(
|
||||
self,
|
||||
authenticated_client,
|
||||
create_test_user,
|
||||
tenants_fixture,
|
||||
invitations_fixture,
|
||||
):
|
||||
active_invitation, expired_invitation = invitations_fixture
|
||||
lapsed_invitation = self._create_lapsed_invitation(
|
||||
"lapsed@prowler.com", tenants_fixture[0], create_test_user
|
||||
)
|
||||
|
||||
list_response = authenticated_client.get(reverse("invitation-list"))
|
||||
retrieve_response = authenticated_client.get(
|
||||
reverse("invitation-detail", kwargs={"pk": lapsed_invitation.id})
|
||||
)
|
||||
|
||||
assert list_response.status_code == status.HTTP_200_OK
|
||||
assert retrieve_response.status_code == status.HTTP_200_OK
|
||||
assert {
|
||||
invitation["id"]: invitation["attributes"]["state"]
|
||||
for invitation in list_response.json()["data"]
|
||||
} == {
|
||||
str(active_invitation.id): Invitation.State.PENDING.value,
|
||||
str(expired_invitation.id): Invitation.State.EXPIRED.value,
|
||||
str(lapsed_invitation.id): Invitation.State.EXPIRED.value,
|
||||
}
|
||||
assert (
|
||||
retrieve_response.json()["data"]["attributes"]["state"]
|
||||
== Invitation.State.EXPIRED.value
|
||||
)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"filter_name, filter_value, expected_invitations",
|
||||
[
|
||||
("state", "pending", {"active"}),
|
||||
("state", "expired", {"expired", "lapsed"}),
|
||||
("state", "accepted", set()),
|
||||
("state__in", "pending", {"active"}),
|
||||
("state__in", "expired", {"expired", "lapsed"}),
|
||||
("state__in", "pending,expired", {"active", "expired", "lapsed"}),
|
||||
("state__in", "accepted,revoked", set()),
|
||||
],
|
||||
)
|
||||
def test_invitations_filter_state_treats_lapsed_pending_as_expired(
|
||||
self,
|
||||
authenticated_client,
|
||||
create_test_user,
|
||||
tenants_fixture,
|
||||
invitations_fixture,
|
||||
filter_name,
|
||||
filter_value,
|
||||
expected_invitations,
|
||||
):
|
||||
active_invitation, expired_invitation = invitations_fixture
|
||||
lapsed_invitation = self._create_lapsed_invitation(
|
||||
"lapsed@prowler.com", tenants_fixture[0], create_test_user
|
||||
)
|
||||
invitation_ids = {
|
||||
"active": str(active_invitation.id),
|
||||
"expired": str(expired_invitation.id),
|
||||
"lapsed": str(lapsed_invitation.id),
|
||||
}
|
||||
|
||||
response = authenticated_client.get(
|
||||
reverse("invitation-list"), {f"filter[{filter_name}]": filter_value}
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_200_OK
|
||||
assert {invitation["id"] for invitation in response.json()["data"]} == {
|
||||
invitation_ids[name] for name in expected_invitations
|
||||
}
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"email",
|
||||
[
|
||||
@@ -8791,8 +9058,10 @@ class TestInvitationViewSet:
|
||||
"invalid_email@",
|
||||
# There is a pending invitation with this email
|
||||
"testing@prowler.com",
|
||||
"TESTING@prowler.com",
|
||||
# User is already a member of the tenant
|
||||
TEST_USER,
|
||||
TEST_USER.upper(),
|
||||
],
|
||||
)
|
||||
def test_invitations_create_invalid_email(
|
||||
@@ -9047,6 +9316,56 @@ class TestInvitationViewSet:
|
||||
== "This invitation cannot be revoked."
|
||||
)
|
||||
|
||||
def test_invitations_delete_lapsed_invitation(
|
||||
self, authenticated_client, invitations_fixture
|
||||
):
|
||||
invitation, *_ = invitations_fixture
|
||||
invitation.expires_at = datetime.now(UTC) - timedelta(days=1)
|
||||
invitation.save()
|
||||
|
||||
response = authenticated_client.delete(
|
||||
reverse("invitation-detail", kwargs={"pk": str(invitation.id)})
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_400_BAD_REQUEST
|
||||
assert (
|
||||
response.json()["errors"][0]["detail"]
|
||||
== "This invitation cannot be revoked."
|
||||
)
|
||||
invitation.refresh_from_db()
|
||||
assert invitation.state == Invitation.State.PENDING
|
||||
|
||||
def test_invitations_partial_update_lapsed_invitation(
|
||||
self, authenticated_client, invitations_fixture
|
||||
):
|
||||
invitation, *_ = invitations_fixture
|
||||
invitation.expires_at = datetime.now(UTC) - timedelta(days=1)
|
||||
invitation.save()
|
||||
data = {
|
||||
"data": {
|
||||
"id": str(invitation.id),
|
||||
"type": "invitations",
|
||||
"attributes": {
|
||||
"email": invitation.email,
|
||||
"expires_at": self.TOMORROW_ISO,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
response = authenticated_client.patch(
|
||||
reverse("invitation-detail", kwargs={"pk": str(invitation.id)}),
|
||||
data=json.dumps(data),
|
||||
content_type="application/vnd.api+json",
|
||||
)
|
||||
|
||||
assert response.status_code == status.HTTP_400_BAD_REQUEST
|
||||
assert (
|
||||
response.json()["errors"][0]["detail"]
|
||||
== "This invitation cannot be updated."
|
||||
)
|
||||
invitation.refresh_from_db()
|
||||
assert invitation.is_lapsed
|
||||
|
||||
def test_invitations_accept_invitation_new_user(self, client, invitations_fixture):
|
||||
invitation, *_ = invitations_fixture
|
||||
|
||||
|
||||
@@ -2149,6 +2149,12 @@ class InvitationSerializer(RLSSerializer):
|
||||
if tenant_id is not None:
|
||||
self.fields["roles"].queryset = Role.objects.filter(tenant_id=tenant_id)
|
||||
|
||||
def to_representation(self, instance):
|
||||
data = super().to_representation(instance)
|
||||
if instance.is_lapsed:
|
||||
data["state"] = Invitation.State.EXPIRED.value
|
||||
return data
|
||||
|
||||
class Meta:
|
||||
model = Invitation
|
||||
fields = [
|
||||
@@ -2175,6 +2181,7 @@ class InvitationBaseWriteSerializer(BaseWriteSerializer):
|
||||
self.fields["roles"].queryset = Role.objects.filter(tenant_id=tenant_id)
|
||||
|
||||
def validate_email(self, value):
|
||||
value = value.strip().lower()
|
||||
user = User.objects.filter(email=value).first()
|
||||
tenant_id = self.context["tenant_id"]
|
||||
if user and Membership.objects.filter(user=user, tenant=tenant_id).exists():
|
||||
@@ -2182,9 +2189,13 @@ class InvitationBaseWriteSerializer(BaseWriteSerializer):
|
||||
"The user may already be a member of the tenant or there was an issue with the "
|
||||
"email provided."
|
||||
)
|
||||
if Invitation.objects.filter(
|
||||
email=value, state=Invitation.State.PENDING
|
||||
).exists():
|
||||
pending_invitations = Invitation.objects.filter(
|
||||
tenant_id=tenant_id, email=value, state=Invitation.State.PENDING
|
||||
)
|
||||
pending_invitations.filter(Invitation.lapsed_q()).update(
|
||||
state=Invitation.State.EXPIRED
|
||||
)
|
||||
if pending_invitations.filter(expires_at__gt=datetime.now(UTC)).exists():
|
||||
raise ValidationError(
|
||||
"Unable to process your request. Please check the information provided and "
|
||||
"try again."
|
||||
|
||||
@@ -326,7 +326,7 @@ from rest_framework_simplejwt.token_blacklist.models import (
|
||||
)
|
||||
from tasks.beat import schedule_provider_scan
|
||||
from tasks.jobs.attack_paths import db_utils as attack_paths_db_utils
|
||||
from tasks.jobs.export import get_s3_client
|
||||
from tasks.jobs.export import get_s3_client, get_s3_presign_client
|
||||
from tasks.tasks import (
|
||||
QUEUED_SCAN_TASK_STATE,
|
||||
backfill_compliance_summaries_task,
|
||||
@@ -2407,7 +2407,8 @@ class ScanViewSet(ProviderVisibilityMixin, BaseRLSViewSet):
|
||||
}
|
||||
if content_type:
|
||||
params["ResponseContentType"] = content_type
|
||||
url = client.generate_presigned_url(
|
||||
# The browser follows this URL, so it is signed against the public host.
|
||||
url = (get_s3_presign_client() or client).generate_presigned_url(
|
||||
"get_object",
|
||||
Params=params,
|
||||
ExpiresIn=300,
|
||||
@@ -2821,6 +2822,15 @@ class ScanViewSet(ProviderVisibilityMixin, BaseRLSViewSet):
|
||||
tenant_id=self.request.tenant_id,
|
||||
task_id=pre_task_id,
|
||||
task_status=(QUEUED_SCAN_TASK_STATE if active_scan else None),
|
||||
# This response is serialized before the on_commit publish,
|
||||
# so without these the caller gets a task id and no scan id.
|
||||
# Kept in step with what `enqueue_scan_execution_on_commit`
|
||||
# publishes below.
|
||||
task_kwargs={
|
||||
"tenant_id": str(self.request.tenant_id),
|
||||
"scan_id": str(scan.id),
|
||||
"provider_id": str(scan.provider_id),
|
||||
},
|
||||
)
|
||||
|
||||
if not active_scan:
|
||||
@@ -3477,12 +3487,8 @@ class ResourceViewSet(PaginateByPkMixin, BaseRLSViewSet):
|
||||
filtered_queryset = self.filter_queryset(self.get_queryset())
|
||||
|
||||
latest_scans = (
|
||||
Scan.all_objects.filter(
|
||||
tenant_id=tenant_id,
|
||||
state=StateChoices.COMPLETED,
|
||||
)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
Scan.all_objects.filter(tenant_id=tenant_id)
|
||||
.latest_per_provider()
|
||||
.values("provider_id")
|
||||
)
|
||||
|
||||
@@ -3614,11 +3620,9 @@ class ResourceViewSet(PaginateByPkMixin, BaseRLSViewSet):
|
||||
tenant_id = request.tenant_id
|
||||
query_params = request.query_params
|
||||
|
||||
latest_scans_queryset = (
|
||||
Scan.all_objects.filter(tenant_id=tenant_id, state=StateChoices.COMPLETED)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
)
|
||||
latest_scans_queryset = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id
|
||||
).latest_per_provider()
|
||||
|
||||
queryset = ResourceScanSummary.objects.filter(
|
||||
tenant_id=tenant_id,
|
||||
@@ -4205,12 +4209,9 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
|
||||
tenant_id = request.tenant_id
|
||||
filtered_queryset = self.filter_queryset(self.get_queryset())
|
||||
|
||||
latest_scan_ids = list(
|
||||
Scan.all_objects.filter(tenant_id=tenant_id, state=StateChoices.COMPLETED)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
latest_scan_ids = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id
|
||||
).latest_ids_per_provider()
|
||||
filtered_queryset = filtered_queryset.filter(
|
||||
tenant_id=tenant_id, scan_id__in=latest_scan_ids
|
||||
)
|
||||
@@ -4233,11 +4234,9 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
|
||||
tenant_id = request.tenant_id
|
||||
query_params = request.query_params
|
||||
|
||||
latest_scans_queryset = (
|
||||
Scan.all_objects.filter(tenant_id=tenant_id, state=StateChoices.COMPLETED)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
)
|
||||
latest_scans_queryset = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id
|
||||
).latest_per_provider()
|
||||
raw_latest_scans_ids = list(
|
||||
latest_scans_queryset.values_list("id", "unique_resource_count")
|
||||
)
|
||||
@@ -4471,7 +4470,7 @@ class InvitationViewSet(BaseRLSViewSet):
|
||||
|
||||
def partial_update(self, request, *args, **kwargs):
|
||||
instance = self.get_object()
|
||||
if instance.state != Invitation.State.PENDING:
|
||||
if instance.state != Invitation.State.PENDING or instance.is_lapsed:
|
||||
raise ValidationError(detail="This invitation cannot be updated.")
|
||||
serializer = self.get_serializer(
|
||||
instance,
|
||||
@@ -4485,7 +4484,7 @@ class InvitationViewSet(BaseRLSViewSet):
|
||||
|
||||
def destroy(self, request, *args, **kwargs):
|
||||
instance = self.get_object()
|
||||
if instance.state != Invitation.State.PENDING:
|
||||
if instance.state != Invitation.State.PENDING or instance.is_lapsed:
|
||||
raise ValidationError(detail="This invitation cannot be revoked.")
|
||||
instance.state = Invitation.State.REVOKED
|
||||
instance.save()
|
||||
@@ -4978,11 +4977,7 @@ class ComplianceOverviewViewSet(
|
||||
if provider_filters:
|
||||
scans = scans.filter(**provider_filters)
|
||||
|
||||
return list(
|
||||
scans.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
return scans.latest_ids_per_provider()
|
||||
|
||||
def _filtered_queryset_for_latest_provider_scans(self, latest_scan_ids=None):
|
||||
if latest_scan_ids is None:
|
||||
@@ -5724,14 +5719,9 @@ class OverviewViewSet(ProviderFilterParamsMixin, BaseRLSViewSet):
|
||||
else {}
|
||||
)
|
||||
|
||||
latest_scan_ids = (
|
||||
Scan.all_objects.filter(
|
||||
tenant_id=tenant_id, state=StateChoices.COMPLETED, **provider_filter
|
||||
)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
latest_scan_ids = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id, **provider_filter
|
||||
).latest_ids_per_provider()
|
||||
|
||||
return filtered_queryset.filter(
|
||||
tenant_id=tenant_id, scan_id__in=latest_scan_ids
|
||||
@@ -5758,16 +5748,10 @@ class OverviewViewSet(ProviderFilterParamsMixin, BaseRLSViewSet):
|
||||
|
||||
def _latest_scan_ids_for_allowed_providers(self, tenant_id, provider_filters=None):
|
||||
provider_filter = self._get_provider_filter()
|
||||
queryset = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id, state=StateChoices.COMPLETED, **provider_filter
|
||||
)
|
||||
queryset = Scan.all_objects.filter(tenant_id=tenant_id, **provider_filter)
|
||||
if provider_filters:
|
||||
queryset = queryset.filter(**provider_filters)
|
||||
return (
|
||||
queryset.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
return queryset.latest_ids_per_provider()
|
||||
|
||||
@action(detail=False, methods=["get"], url_name="providers")
|
||||
def providers(self, request):
|
||||
@@ -5779,14 +5763,9 @@ class OverviewViewSet(ProviderFilterParamsMixin, BaseRLSViewSet):
|
||||
else {}
|
||||
)
|
||||
|
||||
latest_scan_ids = (
|
||||
Scan.all_objects.filter(
|
||||
tenant_id=tenant_id, state=StateChoices.COMPLETED, **provider_filter
|
||||
)
|
||||
.order_by("provider_id", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
latest_scan_ids = Scan.all_objects.filter(
|
||||
tenant_id=tenant_id, **provider_filter
|
||||
).latest_ids_per_provider()
|
||||
|
||||
findings_aggregated = (
|
||||
queryset.filter(scan_id__in=latest_scan_ids)
|
||||
@@ -7933,18 +7912,13 @@ class FindingGroupViewSet(JsonApiFilterMixin, BaseRLSViewSet):
|
||||
|
||||
def _get_latest_findings_per_provider(self, filtered_queryset):
|
||||
"""Keep only findings from each provider's most recent completed scan."""
|
||||
# Materialize to a literal IN list. Left as a subquery, Postgres can't
|
||||
# estimate the match count and picks a serial nested loop on
|
||||
# resource_finding_mappings when one scan dominates findings
|
||||
latest_scan_ids = list(
|
||||
Scan.objects.filter(
|
||||
tenant_id=self.request.tenant_id,
|
||||
state=StateChoices.COMPLETED,
|
||||
)
|
||||
.order_by("provider_id", "-completed_at", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
# `latest_ids_per_provider` materializes to a literal IN list.
|
||||
# Left as a subquery, Postgres can't estimate the match count and picks
|
||||
# a serial nested loop on resource_finding_mappings when one scan
|
||||
# dominates findings
|
||||
latest_scan_ids = Scan.objects.filter(
|
||||
tenant_id=self.request.tenant_id
|
||||
).latest_ids_per_provider()
|
||||
return filtered_queryset.filter(scan_id__in=latest_scan_ids)
|
||||
|
||||
def _post_process_aggregation(self, aggregated_data):
|
||||
@@ -8890,16 +8864,14 @@ class FindingGroupViewSet(JsonApiFilterMixin, BaseRLSViewSet):
|
||||
tenant_id = request.tenant_id
|
||||
queryset = self._get_finding_queryset()
|
||||
|
||||
# Order by -completed_at (matching the /latest summary path and the
|
||||
# daily summary upsert keyed on midnight(completed_at)) so that
|
||||
# overlapping scans do not make /resources and /latest read from
|
||||
# different scans and report diverging counts.
|
||||
latest_scan_ids = (
|
||||
Scan.objects.filter(tenant_id=tenant_id, state=StateChoices.COMPLETED)
|
||||
.order_by("provider_id", "-completed_at", "-inserted_at")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
# The shared selector orders by -completed_at (matching the /latest
|
||||
# summary path and the daily summary upsert keyed on
|
||||
# midnight(completed_at)) so that overlapping scans do not make
|
||||
# /resources and /latest read from different scans and report
|
||||
# diverging counts.
|
||||
latest_scan_ids = Scan.objects.filter(
|
||||
tenant_id=tenant_id
|
||||
).latest_ids_per_provider()
|
||||
|
||||
normalized_params = self._normalize_jsonapi_params(request.query_params)
|
||||
# Remove date filters since we're using latest
|
||||
|
||||
@@ -231,6 +231,62 @@ LOGGING = {
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
# Celery loggers must be declared explicitly because
|
||||
# disable_existing_loggers=True silences any logger that exists at
|
||||
# dictConfig time but is not named here. Without these, fatal worker
|
||||
# errors (e.g. celery.worker CRITICAL) produce no output.
|
||||
# "celery" must keep propagating: get_task_logger() parents task
|
||||
# loggers under celery.task, so blocking here hides them from root.
|
||||
"celery": {
|
||||
"level": LEVEL,
|
||||
"propagate": True,
|
||||
},
|
||||
"celery.worker": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"celery.worker.consumer": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"celery.worker.consumer.consumer": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"kombu": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"kombu.transport.redis": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"billiard": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
"amqp": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
# WARNING keeps task failures but skips one "succeeded" line per task.
|
||||
"celery.app.trace": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": "WARNING",
|
||||
"propagate": False,
|
||||
},
|
||||
"celery.beat": {
|
||||
"handlers": ["tasks_console"],
|
||||
"level": LEVEL,
|
||||
"propagate": False,
|
||||
},
|
||||
},
|
||||
# Gunicorn required configuration
|
||||
"root": {
|
||||
|
||||
@@ -7,6 +7,7 @@ from config.settings.eventstream import * # noqa
|
||||
from config.settings.partitions import * # noqa
|
||||
from config.settings.sentry import * # noqa
|
||||
from config.settings.social_login import * # noqa
|
||||
from django.core.exceptions import ImproperlyConfigured
|
||||
|
||||
SECRET_KEY = env("SECRET_KEY", default="secret")
|
||||
DEBUG = env.bool("DJANGO_DEBUG", default=False)
|
||||
@@ -295,6 +296,14 @@ DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY = env.str(
|
||||
)
|
||||
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN = env.str("DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN", "")
|
||||
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION = env.str("DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION", "")
|
||||
# Storage endpoint the API and Celery workers use to talk to S3-compatible object storage
|
||||
# such as MinIO. Empty means the real AWS S3 endpoint, which is unaffected.
|
||||
DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL = env.str("DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL", "")
|
||||
# Browser-reachable storage host used to sign download URLs. Empty means sign against the
|
||||
# same endpoint the API talks to, which is what Prowler Cloud on S3 does.
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL = env.str(
|
||||
"DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL", ""
|
||||
)
|
||||
|
||||
# HTTP Security Headers
|
||||
SECURE_CONTENT_TYPE_NOSNIFF = True
|
||||
@@ -320,6 +329,17 @@ ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES = env.int(
|
||||
"ATTACK_PATHS_SCAN_STALE_THRESHOLD_MINUTES", 960
|
||||
) # 16h
|
||||
|
||||
# Minimum age (of the scan row, or of the scan id itself when the row is gone) before
|
||||
# the periodic reaper will drop an orphaned temp Neo4j database. Keeps a scan that is
|
||||
# still legitimately in flight from ever losing its staging database mid-run.
|
||||
ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS = env.int(
|
||||
"ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS", 6
|
||||
)
|
||||
if ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS <= 0:
|
||||
raise ImproperlyConfigured(
|
||||
"ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS must be a positive number of hours"
|
||||
)
|
||||
|
||||
# Selects where the persistent attack-paths graph is stored. The scan
|
||||
# temporary database is always Neo4j; only the sink is configurable.
|
||||
# Valid values: "neo4j" (default, OSS and local dev), "neptune" (hosted).
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
"""Periodic reaper for orphaned temp Neo4j scan databases.
|
||||
|
||||
`scan.py` creates a throw-away `db-tmp-scan-<attack_paths_scan_id>` database per
|
||||
scan and drops it once the scan finishes, success or failure. When the worker
|
||||
or Neo4j itself dies mid-scan, that drop never runs and nothing else ever
|
||||
revisits the database - it sits there forever. This sweep lists every temp
|
||||
database on the ingest cluster and drops the ones whose scan is gone or has
|
||||
been finished for longer than the configured safety margin.
|
||||
"""
|
||||
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
from api.attack_paths import database as graph_database
|
||||
from api.db_router import MainRouter
|
||||
from api.models import AttackPathsScan, StateChoices
|
||||
from api.uuid_utils import datetime_from_uuid7
|
||||
from celery.utils.log import get_task_logger
|
||||
from config.django.base import ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS
|
||||
from uuid6 import UUID as UUID7
|
||||
|
||||
logger = get_task_logger(__name__)
|
||||
|
||||
TERMINAL_STATES = (
|
||||
StateChoices.COMPLETED,
|
||||
StateChoices.FAILED,
|
||||
StateChoices.CANCELLED,
|
||||
)
|
||||
|
||||
|
||||
def reap_orphaned_tmp_databases() -> dict:
|
||||
"""Drop temp Neo4j scan databases whose scan is gone or long finished.
|
||||
|
||||
A failure listing databases aborts the whole sweep (nothing to iterate).
|
||||
A failure reaping one database is logged and skipped so the rest of the
|
||||
sweep still runs.
|
||||
"""
|
||||
now = datetime.now(tz=UTC)
|
||||
safety_margin = timedelta(hours=ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS)
|
||||
|
||||
try:
|
||||
databases = graph_database.list_databases()
|
||||
except Exception:
|
||||
logger.exception("Failed to list ingest Neo4j databases for temp-db reap")
|
||||
return {"dropped_count": 0, "databases": []}
|
||||
|
||||
tmp_databases = [
|
||||
name for name in databases if name.startswith(graph_database.TEMP_DB_PREFIX)
|
||||
]
|
||||
|
||||
dropped: list[str] = []
|
||||
for database in tmp_databases:
|
||||
try:
|
||||
if _is_orphaned(database, now, safety_margin):
|
||||
graph_database.drop_database(database)
|
||||
dropped.append(database)
|
||||
logger.info(f"Dropped orphaned temp Neo4j database `{database}`")
|
||||
except Exception:
|
||||
logger.exception(f"Failed to reap temp Neo4j database `{database}`")
|
||||
|
||||
logger.info(f"Temp Neo4j database reap: {len(dropped)} dropped")
|
||||
return {"dropped_count": len(dropped), "databases": dropped}
|
||||
|
||||
|
||||
def _is_orphaned(database: str, now: datetime, safety_margin: timedelta) -> bool:
|
||||
"""Decide whether a temp database is safe to drop.
|
||||
|
||||
No scan row: the row was hard-deleted (tenant/provider cleanup) or was
|
||||
never created. Falls back to the scan id's own UUIDv7 timestamp so a
|
||||
database created moments ago is never touched even without a row to check.
|
||||
|
||||
Scan row present: only reapable once it reached a terminal state and has
|
||||
been finished for longer than the safety margin, so a scan still
|
||||
legitimately executing is never touched.
|
||||
"""
|
||||
scan_id = database[len(graph_database.TEMP_DB_PREFIX) :]
|
||||
|
||||
try:
|
||||
scan_uuid = UUID7(scan_id)
|
||||
except ValueError:
|
||||
logger.warning(
|
||||
f"Temp database `{database}` has an unparseable scan id, skipping"
|
||||
)
|
||||
return False
|
||||
|
||||
# Global sweep with no tenant context: admin_db bypasses RLS on purpose, the same
|
||||
# way cleanup_stale_attack_paths_scans finds stale scans across every tenant.
|
||||
scan = (
|
||||
AttackPathsScan.all_objects.using(MainRouter.admin_db)
|
||||
.filter(id=scan_uuid)
|
||||
.first()
|
||||
)
|
||||
|
||||
if scan is None:
|
||||
if scan_uuid.version != 7:
|
||||
logger.warning(
|
||||
f"Temp database `{database}` has no scan row and a non-UUIDv7 id, "
|
||||
"skipping"
|
||||
)
|
||||
return False
|
||||
return now - datetime_from_uuid7(scan_uuid) >= safety_margin
|
||||
|
||||
if scan.state not in TERMINAL_STATES:
|
||||
return False
|
||||
|
||||
# `mark_scan_finished` does not touch `updated_at`, so prefer `completed_at`
|
||||
finished_at = scan.completed_at or scan.updated_at
|
||||
return now - finished_at >= safety_margin
|
||||
@@ -499,10 +499,13 @@ def backfill_provider_compliance_scores(tenant_id: str) -> dict:
|
||||
provider_id__in=existing_providers
|
||||
)
|
||||
|
||||
# `completed_scans` keeps its own `completed_at__isnull=False`: this
|
||||
# task writes a *dated* ProviderComplianceScore row, so unlike the read
|
||||
# paths it genuinely cannot use a scan without a `completed_at`.
|
||||
scan_info = list(
|
||||
completed_scans.order_by("provider_id", "-completed_at")
|
||||
.distinct("provider_id")
|
||||
.values("id", "provider_id", "completed_at")
|
||||
completed_scans.latest_per_provider().values(
|
||||
"id", "provider_id", "completed_at"
|
||||
)
|
||||
)
|
||||
|
||||
if not scan_info:
|
||||
|
||||
@@ -6,6 +6,7 @@ import boto3
|
||||
import config.django.base as base
|
||||
from api.db_utils import rls_transaction
|
||||
from api.models import Scan
|
||||
from botocore.config import Config
|
||||
from botocore.exceptions import ClientError, NoCredentialsError, ParamValidationError
|
||||
from celery.utils.log import get_task_logger
|
||||
from django.conf import settings
|
||||
@@ -206,15 +207,21 @@ def get_s3_client():
|
||||
This function attempts to initialize an S3 client by reading the AWS access key, secret key,
|
||||
session token, and region from environment variables. It then validates the client by listing
|
||||
available S3 buckets. If an error occurs during this process (for example, due to missing or
|
||||
invalid credentials), it falls back to creating an S3 client without explicitly provided credentials,
|
||||
which may rely on other configuration sources (e.g., IAM roles).
|
||||
invalid credentials), it falls back to creating an S3 client without explicitly provided
|
||||
credentials, which may rely on other configuration sources (e.g., IAM roles).
|
||||
|
||||
That fallback is only safe when no explicit endpoint is configured: with an endpoint set, the
|
||||
explicit client already targets the intended S3-compatible storage, and the fallback client
|
||||
would go to the AWS default provider chain instead, an unrelated real-AWS account reachable
|
||||
from the host. So when an endpoint is configured, the original error propagates instead.
|
||||
|
||||
Returns:
|
||||
boto3.client: A configured S3 client instance.
|
||||
|
||||
Raises:
|
||||
ClientError, NoCredentialsError, or ParamValidationError if both attempts to create a client fail.
|
||||
ClientError, NoCredentialsError, or ParamValidationError if the client cannot be created.
|
||||
"""
|
||||
endpoint = settings.DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL
|
||||
s3_client = None
|
||||
try:
|
||||
s3_client = boto3.client(
|
||||
@@ -222,16 +229,68 @@ def get_s3_client():
|
||||
aws_access_key_id=settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID,
|
||||
aws_secret_access_key=settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY,
|
||||
aws_session_token=settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN,
|
||||
region_name=settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION,
|
||||
# Storage that has no meaningful region, MinIO among it, is usually configured
|
||||
# without one, and botocore rejects an empty region before any request is made.
|
||||
region_name=settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION or "us-east-1",
|
||||
endpoint_url=endpoint or None,
|
||||
)
|
||||
s3_client.list_buckets()
|
||||
except (ClientError, NoCredentialsError, ParamValidationError, ValueError):
|
||||
if endpoint:
|
||||
raise
|
||||
s3_client = boto3.client("s3")
|
||||
s3_client.list_buckets()
|
||||
|
||||
return s3_client
|
||||
|
||||
|
||||
def get_s3_presign_client():
|
||||
"""Return a client that signs download URLs with SigV4.
|
||||
|
||||
It is used when a public or internal storage host is configured, or when the bucket's
|
||||
region is: boto3 otherwise presigns S3 URLs with SigV2, which S3 rejects for SSE-KMS
|
||||
objects. None means none of those is set and the caller should presign with its own
|
||||
client, which leaves those deployments with the URL they get today.
|
||||
|
||||
The public endpoint wins when both are set: the internal endpoint may only be reachable
|
||||
from inside the cluster, and a URL signed against it would not open in a browser.
|
||||
"""
|
||||
endpoint = (
|
||||
settings.DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL
|
||||
or settings.DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL
|
||||
)
|
||||
if not endpoint and not settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION:
|
||||
return None
|
||||
|
||||
# Blank keys are signed as-is (empty credential scope) instead of deferring to the
|
||||
# provider chain, so static credentials are only passed when they are set.
|
||||
credentials = {}
|
||||
if (
|
||||
settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID
|
||||
and settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY
|
||||
):
|
||||
credentials = {
|
||||
"aws_access_key_id": settings.DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID,
|
||||
"aws_secret_access_key": settings.DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY,
|
||||
# An empty string is a token as far as botocore is concerned: it appends an
|
||||
# empty X-Amz-Security-Token that storage counts when it recomputes the signature.
|
||||
"aws_session_token": settings.DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN or None,
|
||||
}
|
||||
|
||||
return boto3.client(
|
||||
"s3",
|
||||
**credentials,
|
||||
# SigV4 puts the region in the credential scope, and MinIO answers to us-east-1
|
||||
# unless it was told otherwise, so an empty region would sign an unusable URL.
|
||||
region_name=settings.DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION or "us-east-1",
|
||||
endpoint_url=endpoint or None,
|
||||
# The signature covers the host, so the addressing style has to be pinned rather
|
||||
# than guessed from the endpoint: MinIO serves path-style, and on AWS it keeps the
|
||||
# regional host instead of the global one, which redirects for new buckets.
|
||||
config=Config(signature_version="s3v4", s3={"addressing_style": "path"}),
|
||||
)
|
||||
|
||||
|
||||
def _upload_to_s3(
|
||||
tenant_id: str, scan_id: str, local_path: str, relative_key: str
|
||||
) -> str | None:
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
from collections.abc import Iterable
|
||||
|
||||
from api.db_utils import rls_transaction
|
||||
from api.models import Finding, MuteRule, Scan, StateChoices
|
||||
from api.models import Finding, MuteRule, Scan
|
||||
from celery.utils.log import get_task_logger
|
||||
|
||||
logger = get_task_logger(__name__)
|
||||
@@ -39,17 +39,9 @@ def mute_findings_in_latest_scans(
|
||||
|
||||
with rls_transaction(tenant_id):
|
||||
mute_rule = MuteRule.objects.get(id=mute_rule_id, tenant_id=tenant_id)
|
||||
latest_scans = list(
|
||||
Scan.objects.filter(
|
||||
tenant_id=tenant_id,
|
||||
provider_id__in=provider_ids,
|
||||
state=StateChoices.COMPLETED,
|
||||
completed_at__isnull=False,
|
||||
)
|
||||
.order_by("provider_id", "-completed_at", "-inserted_at", "-id")
|
||||
.distinct("provider_id")
|
||||
.values_list("id", flat=True)
|
||||
)
|
||||
latest_scans = Scan.objects.filter(
|
||||
tenant_id=tenant_id, provider_id__in=provider_ids
|
||||
).latest_ids_per_provider()
|
||||
|
||||
changed_scan_ids = []
|
||||
findings_muted = 0
|
||||
|
||||
@@ -84,6 +84,7 @@ _SKIP_RECOVERY = {
|
||||
"scan-perform-scheduled",
|
||||
"attack-paths-scan-perform",
|
||||
"attack-paths-cleanup-stale-scans",
|
||||
"attack-paths-reap-orphaned-tmp-databases",
|
||||
"reconcile-orphan-tasks",
|
||||
}
|
||||
|
||||
|
||||
@@ -2700,20 +2700,37 @@ def reset_ephemeral_resource_findings_count(tenant_id: str, scan_id: str) -> dic
|
||||
# refreshed). Wiping based on the older scan would zero counts the newer
|
||||
# scan just set. Skip and let the newer scan's reset task do the work; if
|
||||
# this task was delayed in the queue, that's the correct outcome.
|
||||
# `completed_at__isnull=False` is required: Postgres orders NULL first in
|
||||
# DESC, so a sibling COMPLETED scan with a missing completed_at would sort
|
||||
# as "newest" and incorrectly cause us to skip.
|
||||
#
|
||||
# The comparison must be against the newest *full-scope* scan, which is
|
||||
# what this variable has always been named after but did not use to be:
|
||||
# the query filtered nothing about scope, so any newer scan that is not
|
||||
# full-scope (an imported one, for instance) made the full-scope scan
|
||||
# skip its own cleanup and leave ephemeral resources with a stale
|
||||
# failed_findings_count permanently.
|
||||
#
|
||||
# `is_full_scope()` reads `trigger` plus the scoping keys inside
|
||||
# `scanner_args`, which is not expressible as a WHERE clause, so the
|
||||
# candidates are walked newest-first in Python until the first full-scope
|
||||
# one. The walk needs no cap: `scan` is itself a full-scope candidate, so
|
||||
# it stops at `scan` at the latest, after reading only the scans newer than
|
||||
# it. A fixed window would return None once more newer scoped scans had
|
||||
# landed than it inspected, and skip the cleanup exactly like the bug above.
|
||||
#
|
||||
# NULL `completed_at` no longer needs an explicit filter here: the shared
|
||||
# ordering in `ScanQuerySet.LATEST_ORDER_BY` sorts NULLs last
|
||||
# rather than excluding them, which also fixes the case where a provider
|
||||
# whose completed scans all have a NULL `completed_at` resolved to None and
|
||||
# therefore never ran the reset at all.
|
||||
with rls_transaction(tenant_id):
|
||||
latest_full_scope_scan_id = (
|
||||
Scan.objects.filter(
|
||||
tenant_id=tenant_id,
|
||||
provider_id=scan.provider_id,
|
||||
state=StateChoices.COMPLETED,
|
||||
completed_at__isnull=False,
|
||||
)
|
||||
.order_by("-completed_at", "-inserted_at")
|
||||
.values_list("id", flat=True)
|
||||
.first()
|
||||
candidates = (
|
||||
Scan.objects.filter(tenant_id=tenant_id, provider_id=scan.provider_id)
|
||||
.latest_first()
|
||||
.only("id", "trigger", "scanner_args")
|
||||
.iterator(chunk_size=100)
|
||||
)
|
||||
latest_full_scope_scan_id = next(
|
||||
(candidate.id for candidate in candidates if candidate.is_full_scope()),
|
||||
None,
|
||||
)
|
||||
if latest_full_scope_scan_id != scan.id:
|
||||
logger.info(
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import json
|
||||
import os
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from pathlib import Path
|
||||
@@ -42,6 +43,7 @@ from tasks.jobs.attack_paths import (
|
||||
)
|
||||
from tasks.jobs.attack_paths import db_utils as attack_paths_db_utils
|
||||
from tasks.jobs.attack_paths.cleanup import cleanup_stale_attack_paths_scans
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
from tasks.jobs.backfill import (
|
||||
aggregate_scan_category_summaries,
|
||||
aggregate_scan_resource_group_summaries,
|
||||
@@ -163,13 +165,28 @@ def create_scan_task_record(
|
||||
task_id: str,
|
||||
task_name: str = "scan-perform",
|
||||
task_status: str | None = states.PENDING,
|
||||
task_kwargs: dict | None = None,
|
||||
) -> Task:
|
||||
"""Pre-create the TaskResult + Task rows for a pre-generated task id.
|
||||
|
||||
Pass ``task_kwargs`` when the response built from this record is serialized
|
||||
before the broker publish. ``task_kwargs`` is otherwise only written by the
|
||||
``before_task_publish`` signal (``api/signals.py``), and the scan publish is
|
||||
deferred to ``on_commit``, so the 202 would carry an empty ``task_args`` and
|
||||
the caller would have no way to learn the scan id it was just handed a task
|
||||
for. The publish later overwrites the field with the same kwargs as a Python
|
||||
repr; both forms decode to the same dict (``decode_celery_field``).
|
||||
"""
|
||||
if task_status is None:
|
||||
task_status = states.PENDING
|
||||
|
||||
defaults = {"status": task_status, "task_name": task_name}
|
||||
if task_kwargs is not None:
|
||||
defaults["task_kwargs"] = json.dumps(task_kwargs)
|
||||
|
||||
task_result, _ = TaskResult.objects.update_or_create(
|
||||
task_id=str(task_id),
|
||||
defaults={"status": task_status, "task_name": task_name},
|
||||
defaults=defaults,
|
||||
)
|
||||
prowler_task, _ = Task.objects.update_or_create(
|
||||
id=str(task_id),
|
||||
@@ -711,6 +728,13 @@ def cleanup_stale_attack_paths_scans_task():
|
||||
return cleanup_stale_attack_paths_scans()
|
||||
|
||||
|
||||
@shared_task(
|
||||
name="attack-paths-reap-orphaned-tmp-databases", queue="attack-paths-scans"
|
||||
)
|
||||
def reap_orphaned_attack_paths_tmp_databases_task():
|
||||
return reap_orphaned_tmp_databases()
|
||||
|
||||
|
||||
@shared_task(name="reconcile-orphan-tasks", queue="celery")
|
||||
def reconcile_orphan_tasks_task():
|
||||
"""Periodic watchdog: recover tasks whose worker is gone (deploys, crashes)."""
|
||||
|
||||
@@ -0,0 +1,286 @@
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from unittest.mock import patch
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from api.attack_paths.database import TEMP_DB_PREFIX
|
||||
from api.models import AttackPathsScan, StateChoices
|
||||
from api.uuid_utils import datetime_to_uuid7
|
||||
from config.django.base import ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS
|
||||
|
||||
MARGIN = timedelta(hours=ATTACK_PATHS_TMP_DB_REAP_SAFETY_MARGIN_HOURS)
|
||||
|
||||
|
||||
def _tmp_db_name(scan_uuid) -> str:
|
||||
return f"{TEMP_DB_PREFIX}{scan_uuid}"
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestReapOrphanedTmpDatabases:
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_ignores_databases_without_the_temp_prefix(self, mock_list, mock_drop):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
mock_list.return_value = ["db-tenant-abc123", "system", "neo4j"]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_drops_temp_db_with_no_scan_row_past_safety_margin(
|
||||
self, mock_list, mock_drop
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
old_scan_id = datetime_to_uuid7(
|
||||
datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
)
|
||||
database = _tmp_db_name(old_scan_id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 1, "databases": [database]}
|
||||
mock_drop.assert_called_once_with(database)
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_preserves_temp_db_with_no_scan_row_inside_safety_margin(
|
||||
self, mock_list, mock_drop
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
recent_scan_id = datetime_to_uuid7(datetime.now(tz=UTC) - timedelta(minutes=5))
|
||||
database = _tmp_db_name(recent_scan_id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_preserves_temp_db_with_unparseable_scan_id(self, mock_list, mock_drop):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
database = f"{TEMP_DB_PREFIX}not-a-uuid"
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_drops_terminal_scan_past_safety_margin(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
old_updated_at = datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=StateChoices.COMPLETED,
|
||||
)
|
||||
AttackPathsScan.objects.filter(id=scan.id).update(updated_at=old_updated_at)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 1, "databases": [database]}
|
||||
mock_drop.assert_called_once_with(database)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"state",
|
||||
[StateChoices.FAILED, StateChoices.CANCELLED],
|
||||
)
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_drops_other_terminal_states_past_safety_margin(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider, state
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
old_updated_at = datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=state,
|
||||
)
|
||||
AttackPathsScan.objects.filter(id=scan.id).update(updated_at=old_updated_at)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result["dropped_count"] == 1
|
||||
mock_drop.assert_called_once_with(database)
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_preserves_terminal_scan_inside_safety_margin(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=StateChoices.COMPLETED,
|
||||
)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_margin_counts_from_completed_at_not_updated_at(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
old = datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=StateChoices.COMPLETED,
|
||||
)
|
||||
AttackPathsScan.objects.filter(id=scan.id).update(
|
||||
updated_at=old, completed_at=datetime.now(tz=UTC)
|
||||
)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_drops_scan_completed_past_safety_margin(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
old = datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=StateChoices.FAILED,
|
||||
)
|
||||
AttackPathsScan.objects.filter(id=scan.id).update(
|
||||
updated_at=old, completed_at=old
|
||||
)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 1, "databases": [database]}
|
||||
mock_drop.assert_called_once_with(database)
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_never_drops_an_executing_scan_regardless_of_age(
|
||||
self, mock_list, mock_drop, tenants_fixture, aws_provider
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
tenant = tenants_fixture[0]
|
||||
very_old = datetime.now(tz=UTC) - timedelta(days=30)
|
||||
scan = AttackPathsScan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=aws_provider,
|
||||
state=StateChoices.EXECUTING,
|
||||
)
|
||||
AttackPathsScan.objects.filter(id=scan.id).update(updated_at=very_old)
|
||||
|
||||
database = _tmp_db_name(scan.id)
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_one_failed_drop_does_not_stop_the_rest_of_the_sweep(
|
||||
self, mock_list, mock_drop
|
||||
):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
old_time = datetime.now(tz=UTC) - MARGIN - timedelta(hours=1)
|
||||
failing_scan_id = datetime_to_uuid7(old_time)
|
||||
succeeding_scan_id = datetime_to_uuid7(old_time)
|
||||
failing_db = _tmp_db_name(failing_scan_id)
|
||||
succeeding_db = _tmp_db_name(succeeding_scan_id)
|
||||
mock_list.return_value = [failing_db, succeeding_db]
|
||||
mock_drop.side_effect = [Exception("boom"), None]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 1, "databases": [succeeding_db]}
|
||||
assert mock_drop.call_count == 2
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_returns_empty_result_when_listing_databases_fails(self, mock_list):
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
mock_list.side_effect = Exception("neo4j unreachable")
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.drop_database")
|
||||
@patch("tasks.jobs.attack_paths.tmp_db_reaper.graph_database.list_databases")
|
||||
def test_preserves_temp_db_with_random_uuid_and_no_row(self, mock_list, mock_drop):
|
||||
"""A non-UUIDv7 id with no matching row has no reliable timestamp, so it
|
||||
must be left alone rather than guessed at."""
|
||||
from tasks.jobs.attack_paths.tmp_db_reaper import reap_orphaned_tmp_databases
|
||||
|
||||
database = _tmp_db_name(uuid4())
|
||||
mock_list.return_value = [database]
|
||||
|
||||
result = reap_orphaned_tmp_databases()
|
||||
|
||||
assert result == {"dropped_count": 0, "databases": []}
|
||||
mock_drop.assert_not_called()
|
||||
|
||||
|
||||
class TestReapOrphanedTmpDatabasesTask:
|
||||
@patch(
|
||||
"tasks.tasks.reap_orphaned_tmp_databases",
|
||||
return_value={"dropped_count": 2, "databases": ["db-tmp-scan-a"]},
|
||||
)
|
||||
def test_task_invokes_the_reaper(self, mock_reap):
|
||||
from tasks.tasks import reap_orphaned_attack_paths_tmp_databases_task
|
||||
|
||||
result = reap_orphaned_attack_paths_tmp_databases_task.run()
|
||||
|
||||
assert result == {"dropped_count": 2, "databases": ["db-tmp-scan-a"]}
|
||||
mock_reap.assert_called_once_with()
|
||||
@@ -3,16 +3,20 @@ import uuid
|
||||
import zipfile
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
from unittest.mock import MagicMock, call, patch
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
|
||||
import boto3
|
||||
import pytest
|
||||
from botocore.exceptions import ClientError
|
||||
from django.test import override_settings
|
||||
from tasks.jobs.export import (
|
||||
_compress_output_files,
|
||||
_generate_compliance_output_directory,
|
||||
_generate_output_directory,
|
||||
_upload_to_s3,
|
||||
get_s3_client,
|
||||
get_s3_presign_client,
|
||||
)
|
||||
|
||||
|
||||
@@ -47,15 +51,59 @@ class TestOutputs:
|
||||
assert client is not None
|
||||
client_mock.list_buckets.assert_called()
|
||||
|
||||
@patch("tasks.jobs.export.boto3.client")
|
||||
@override_settings(
|
||||
DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID="access-key",
|
||||
DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY="secret-key",
|
||||
DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN="",
|
||||
DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION="",
|
||||
)
|
||||
def test_get_s3_client_without_a_region_uses_a_default(self, mock_boto_client):
|
||||
"""botocore rejects an empty region up front, and the download views do not catch it."""
|
||||
get_s3_client()
|
||||
|
||||
assert mock_boto_client.call_args.kwargs["region_name"] == "us-east-1"
|
||||
|
||||
@patch("tasks.jobs.export.boto3.client")
|
||||
@override_settings(DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL="http://minio:9000")
|
||||
def test_get_s3_client_passes_the_endpoint_when_set(self, mock_boto_client):
|
||||
get_s3_client()
|
||||
|
||||
assert mock_boto_client.call_args.kwargs["endpoint_url"] == "http://minio:9000"
|
||||
|
||||
@patch("tasks.jobs.export.boto3.client")
|
||||
@override_settings(DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL="")
|
||||
def test_get_s3_client_endpoint_empty_by_default(self, mock_boto_client):
|
||||
"""Empty keeps today's behavior: no endpoint override, real S3 is used."""
|
||||
get_s3_client()
|
||||
|
||||
assert mock_boto_client.call_args.kwargs["endpoint_url"] is None
|
||||
|
||||
@patch("tasks.jobs.export.boto3.client")
|
||||
@override_settings(DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL="http://minio:9000")
|
||||
def test_get_s3_client_does_not_fall_back_when_endpoint_set(self, mock_boto_client):
|
||||
"""A configured endpoint means the explicit client failed talking to it. The fallback
|
||||
goes to the default provider chain (e.g. an EC2 instance role) against real AWS, so it
|
||||
must not be used: the original error propagates instead."""
|
||||
error = ClientError({"Error": {"Code": "403"}}, "ListBuckets")
|
||||
mock_boto_client.side_effect = error
|
||||
|
||||
with pytest.raises(ClientError):
|
||||
get_s3_client()
|
||||
|
||||
mock_boto_client.assert_called_once()
|
||||
|
||||
@patch("tasks.jobs.export.boto3.client")
|
||||
@patch("tasks.jobs.export.settings")
|
||||
def test_get_s3_client_fallback(self, mock_settings, mock_boto_client):
|
||||
mock_settings.DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL = ""
|
||||
mock_boto_client.side_effect = [
|
||||
ClientError({"Error": {"Code": "403"}}, "ListBuckets"),
|
||||
MagicMock(),
|
||||
]
|
||||
client = get_s3_client()
|
||||
assert client is not None
|
||||
assert mock_boto_client.call_args_list[1] == call("s3")
|
||||
|
||||
@patch("tasks.jobs.export.get_s3_client")
|
||||
@patch("tasks.jobs.export.base")
|
||||
@@ -243,3 +291,167 @@ class TestOutputs:
|
||||
assert os.path.isdir(os.path.dirname(ens))
|
||||
assert threatscore.endswith(f"aws-test-check-{expected_timestamp}")
|
||||
assert ens.endswith(f"aws-test-check-{expected_timestamp}")
|
||||
|
||||
|
||||
PRESIGN_SETTINGS = {
|
||||
"DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID": "access-key",
|
||||
"DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY": "secret-key",
|
||||
"DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN": "",
|
||||
"DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION": "eu-west-1",
|
||||
}
|
||||
|
||||
|
||||
def _presign(client):
|
||||
return client.generate_presigned_url(
|
||||
"get_object",
|
||||
Params={"Bucket": "output-bucket", "Key": "tenant/scan/report.zip"},
|
||||
ExpiresIn=300,
|
||||
)
|
||||
|
||||
|
||||
class TestS3PresignClient:
|
||||
@override_settings(
|
||||
**{**PRESIGN_SETTINGS, "DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION": ""},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="",
|
||||
)
|
||||
def test_no_public_endpoint_and_no_region_returns_none(self):
|
||||
# Without a region, SigV4 would have to guess one and break other regions.
|
||||
assert get_s3_presign_client() is None
|
||||
|
||||
@override_settings(**PRESIGN_SETTINGS, DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="")
|
||||
def test_region_without_public_endpoint_signs_sigv4_on_the_regional_host(self):
|
||||
# SSE-KMS objects reject the SigV2 URLs boto3 presigns by default, and the
|
||||
# global host redirects for new buckets, which breaks a SigV4 signature.
|
||||
url = urlparse(_presign(get_s3_presign_client()))
|
||||
query = parse_qs(url.query)
|
||||
|
||||
assert url.netloc == "s3.eu-west-1.amazonaws.com"
|
||||
assert url.path == "/output-bucket/tenant/scan/report.zip"
|
||||
assert query["X-Amz-Algorithm"] == ["AWS4-HMAC-SHA256"]
|
||||
assert "/eu-west-1/s3/aws4_request" in query["X-Amz-Credential"][0]
|
||||
|
||||
@override_settings(
|
||||
**{
|
||||
**PRESIGN_SETTINGS,
|
||||
"DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID": "",
|
||||
"DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY": "",
|
||||
},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="",
|
||||
)
|
||||
def test_region_without_static_keys_signs_with_the_default_chain(self, monkeypatch):
|
||||
# An ECS task role reaches boto3 through the default chain, like the env here.
|
||||
# A fresh default session keeps these keys from being cached for later tests.
|
||||
monkeypatch.setattr(boto3, "DEFAULT_SESSION", None)
|
||||
monkeypatch.setenv("AWS_ACCESS_KEY_ID", "role-access-key")
|
||||
monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "role-secret-key")
|
||||
monkeypatch.setenv("AWS_DEFAULT_REGION", "us-east-1")
|
||||
|
||||
query = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert query["X-Amz-Credential"][0].startswith("role-access-key/")
|
||||
assert "/eu-west-1/s3/aws4_request" in query["X-Amz-Credential"][0]
|
||||
|
||||
@override_settings(
|
||||
**{**PRESIGN_SETTINGS, "DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION": ""},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="",
|
||||
DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL="http://minio:9000",
|
||||
)
|
||||
def test_internal_endpoint_without_public_endpoint_signs_against_it(self):
|
||||
# No browser-reachable host was configured, so the internal one is the best
|
||||
# available target instead of falling through to the real AWS host.
|
||||
url = urlparse(_presign(get_s3_presign_client()))
|
||||
|
||||
assert url.netloc == "minio:9000"
|
||||
assert url.path == "/output-bucket/tenant/scan/report.zip"
|
||||
|
||||
@override_settings(
|
||||
**PRESIGN_SETTINGS,
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
DJANGO_OUTPUT_S3_AWS_ENDPOINT_URL="http://minio:9000",
|
||||
)
|
||||
def test_public_endpoint_wins_over_the_internal_endpoint(self):
|
||||
url = urlparse(_presign(get_s3_presign_client()))
|
||||
|
||||
assert url.netloc == "storage.example.com"
|
||||
|
||||
@override_settings(
|
||||
**PRESIGN_SETTINGS,
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_url_targets_the_public_host_in_path_style(self):
|
||||
url = urlparse(_presign(get_s3_presign_client()))
|
||||
|
||||
assert url.netloc == "storage.example.com"
|
||||
assert url.path == "/output-bucket/tenant/scan/report.zip"
|
||||
|
||||
@override_settings(
|
||||
**PRESIGN_SETTINGS,
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_signature_covers_the_public_host(self):
|
||||
query = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert query["X-Amz-SignedHeaders"] == ["host"]
|
||||
assert "/eu-west-1/s3/aws4_request" in query["X-Amz-Credential"][0]
|
||||
|
||||
@override_settings(
|
||||
**PRESIGN_SETTINGS,
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_signature_is_bound_to_the_host_it_was_signed_against(self):
|
||||
"""Rewriting the host afterwards cannot work, which is why the endpoint is a setting."""
|
||||
public = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
with override_settings(
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="http://minio:9000"
|
||||
):
|
||||
internal = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert public["X-Amz-Signature"] != internal["X-Amz-Signature"]
|
||||
|
||||
@override_settings(
|
||||
**{**PRESIGN_SETTINGS, "DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION": ""},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_region_falls_back_to_the_minio_default(self):
|
||||
query = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert "/us-east-1/s3/aws4_request" in query["X-Amz-Credential"][0]
|
||||
|
||||
@override_settings(
|
||||
**PRESIGN_SETTINGS,
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_unset_session_token_is_left_out_of_the_url(self):
|
||||
"""An empty token still reaches the URL as a blank param that storage signs over."""
|
||||
url = _presign(get_s3_presign_client())
|
||||
query = parse_qs(urlparse(url).query, keep_blank_values=True)
|
||||
|
||||
assert "X-Amz-Security-Token" not in query
|
||||
|
||||
@override_settings(
|
||||
**{**PRESIGN_SETTINGS, "DJANGO_OUTPUT_S3_AWS_SESSION_TOKEN": "session-token"},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_session_token_is_forwarded_when_set(self):
|
||||
query = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert query["X-Amz-Security-Token"] == ["session-token"]
|
||||
|
||||
@override_settings(
|
||||
**{
|
||||
**PRESIGN_SETTINGS,
|
||||
"DJANGO_OUTPUT_S3_AWS_ACCESS_KEY_ID": "",
|
||||
"DJANGO_OUTPUT_S3_AWS_SECRET_ACCESS_KEY": "",
|
||||
},
|
||||
DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL="https://storage.example.com",
|
||||
)
|
||||
def test_blank_static_credentials_defer_to_the_provider_chain(self, monkeypatch):
|
||||
"""Empty keys would otherwise be signed as-is, yielding a blank credential scope."""
|
||||
monkeypatch.setenv("AWS_ACCESS_KEY_ID", "chain-key")
|
||||
monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "chain-secret")
|
||||
monkeypatch.delenv("AWS_SESSION_TOKEN", raising=False)
|
||||
|
||||
query = parse_qs(urlparse(_presign(get_s3_presign_client())).query)
|
||||
|
||||
assert query["X-Amz-Credential"][0].startswith("chain-key/")
|
||||
|
||||
@@ -5967,6 +5967,112 @@ class TestResetEphemeralResourceFindingsCount:
|
||||
resource2.refresh_from_db()
|
||||
assert resource2.failed_findings_count == 5
|
||||
|
||||
def test_runs_when_newer_scan_is_not_full_scope(
|
||||
self, tenants_fixture, scans_fixture, aws_provider, resources_fixture
|
||||
):
|
||||
"""A newer scoped scan must not block the full-scope scan's cleanup.
|
||||
|
||||
The race guard used to pick the newest COMPLETED scan of any scope
|
||||
despite being named after full-scope ones, so a single scoped scan
|
||||
landing after a complete one made the complete scan skip its cleanup
|
||||
and leave ephemeral resources with a stale count permanently.
|
||||
"""
|
||||
from datetime import timedelta
|
||||
|
||||
tenant, *_ = tenants_fixture
|
||||
scan1, *_ = scans_fixture
|
||||
resource1, resource2, _ = resources_fixture
|
||||
|
||||
Resource.objects.filter(id=resource2.id).update(failed_findings_count=5)
|
||||
self._make_scan_summary(tenant.id, scan1.id, resource1)
|
||||
|
||||
newer_completed_at = scan1.completed_at + timedelta(minutes=5)
|
||||
Scan.objects.create(
|
||||
name="Newer scoped scan",
|
||||
provider=aws_provider,
|
||||
trigger=Scan.TriggerChoices.MANUAL,
|
||||
state=StateChoices.COMPLETED,
|
||||
tenant_id=tenant.id,
|
||||
started_at=newer_completed_at,
|
||||
completed_at=newer_completed_at,
|
||||
scanner_args={"checks": ["check1"]},
|
||||
)
|
||||
|
||||
result = reset_ephemeral_resource_findings_count(
|
||||
tenant_id=str(tenant.id), scan_id=str(scan1.id)
|
||||
)
|
||||
|
||||
assert result["status"] == "completed"
|
||||
|
||||
resource2.refresh_from_db()
|
||||
assert resource2.failed_findings_count == 0
|
||||
|
||||
def test_runs_when_many_newer_scans_are_not_full_scope(
|
||||
self, tenants_fixture, scans_fixture, aws_provider, resources_fixture
|
||||
):
|
||||
"""The walk must not give up before it reaches the full-scope scan.
|
||||
|
||||
A fixed look-back window returned None once more newer scoped scans
|
||||
had landed than it inspected, and skipped the cleanup exactly like the
|
||||
original bug did with one.
|
||||
"""
|
||||
from datetime import timedelta
|
||||
|
||||
tenant, *_ = tenants_fixture
|
||||
scan1, *_ = scans_fixture
|
||||
resource1, resource2, _ = resources_fixture
|
||||
|
||||
Resource.objects.filter(id=resource2.id).update(failed_findings_count=5)
|
||||
self._make_scan_summary(tenant.id, scan1.id, resource1)
|
||||
|
||||
for minutes in range(1, 41):
|
||||
newer_completed_at = scan1.completed_at + timedelta(minutes=minutes)
|
||||
Scan.objects.create(
|
||||
name=f"Newer scoped scan {minutes}",
|
||||
provider=aws_provider,
|
||||
trigger=Scan.TriggerChoices.MANUAL,
|
||||
state=StateChoices.COMPLETED,
|
||||
tenant_id=tenant.id,
|
||||
started_at=newer_completed_at,
|
||||
completed_at=newer_completed_at,
|
||||
scanner_args={"checks": ["check1"]},
|
||||
)
|
||||
|
||||
result = reset_ephemeral_resource_findings_count(
|
||||
tenant_id=str(tenant.id), scan_id=str(scan1.id)
|
||||
)
|
||||
|
||||
assert result["status"] == "completed"
|
||||
|
||||
resource2.refresh_from_db()
|
||||
assert resource2.failed_findings_count == 0
|
||||
|
||||
def test_runs_when_completed_at_is_null(
|
||||
self, tenants_fixture, scans_fixture, aws_provider, resources_fixture
|
||||
):
|
||||
"""NULL `completed_at` used to make the reset never run at all.
|
||||
|
||||
The old guard filtered `completed_at__isnull=False`, so a provider
|
||||
whose completed scans all had a NULL `completed_at` resolved the
|
||||
"latest" scan to None, which never equals `scan.id`.
|
||||
"""
|
||||
tenant, *_ = tenants_fixture
|
||||
scan1, *_ = scans_fixture
|
||||
resource1, resource2, _ = resources_fixture
|
||||
|
||||
Scan.all_objects.filter(id=scan1.id).update(completed_at=None)
|
||||
Resource.objects.filter(id=resource2.id).update(failed_findings_count=5)
|
||||
self._make_scan_summary(tenant.id, scan1.id, resource1)
|
||||
|
||||
result = reset_ephemeral_resource_findings_count(
|
||||
tenant_id=str(tenant.id), scan_id=str(scan1.id)
|
||||
)
|
||||
|
||||
assert result["status"] == "completed"
|
||||
|
||||
resource2.refresh_from_db()
|
||||
assert resource2.failed_findings_count == 0
|
||||
|
||||
def test_does_not_touch_other_providers_resources(
|
||||
self, tenants_fixture, scans_fixture, aws_provider, resources_fixture
|
||||
):
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import json
|
||||
import uuid
|
||||
from contextlib import contextmanager
|
||||
from datetime import UTC, datetime
|
||||
@@ -14,6 +15,7 @@ from api.models import (
|
||||
StateChoices,
|
||||
Task,
|
||||
)
|
||||
from api.v1.serializers import TaskSerializer
|
||||
from botocore.exceptions import ClientError
|
||||
from celery import states
|
||||
from django_celery_beat.models import IntervalSchedule, PeriodicTask
|
||||
@@ -32,6 +34,7 @@ from tasks.tasks import (
|
||||
_scan_tmp_output_directory,
|
||||
check_integrations_task,
|
||||
check_lighthouse_provider_connection_task,
|
||||
create_scan_task_record,
|
||||
generate_outputs_task,
|
||||
mute_findings_in_latest_scans_task,
|
||||
perform_attack_paths_scan_task,
|
||||
@@ -3384,3 +3387,79 @@ class TestTaskTimeLimits:
|
||||
"lighthouse-provider-connection-check",
|
||||
):
|
||||
assert celery_app.tasks[name].time_limit < default
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
class TestCreateScanTaskRecord:
|
||||
"""`task_kwargs` is what a response built before the publish can report."""
|
||||
|
||||
def _scan(self, tenant, provider):
|
||||
"""A manual scan, like the one `POST /api/v1/scans` creates."""
|
||||
return Scan.objects.create(
|
||||
tenant_id=tenant.id,
|
||||
provider=provider,
|
||||
name="Manual scan",
|
||||
trigger=Scan.TriggerChoices.MANUAL,
|
||||
state=StateChoices.AVAILABLE,
|
||||
)
|
||||
|
||||
def _publish_kwargs(self, tenant, scan):
|
||||
"""What `enqueue_scan_execution_on_commit` publishes for this scan."""
|
||||
return {
|
||||
"tenant_id": str(tenant.id),
|
||||
"scan_id": str(scan.id),
|
||||
"provider_id": str(scan.provider_id),
|
||||
}
|
||||
|
||||
def _task_args(self, task):
|
||||
"""Read the record back the way `TaskSerializer` does."""
|
||||
return TaskSerializer(task).data["task_args"]
|
||||
|
||||
def test_the_stored_kwargs_are_the_ones_the_publish_would_send(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""The 202 reports what is stored here, so it has to be the dispatch kwargs."""
|
||||
tenant = tenants_fixture[0]
|
||||
scan = self._scan(tenant, aws_provider)
|
||||
|
||||
task = create_scan_task_record(
|
||||
tenant_id=str(tenant.id),
|
||||
task_id=str(uuid.uuid4()),
|
||||
task_kwargs=self._publish_kwargs(tenant, scan),
|
||||
)
|
||||
|
||||
assert self._task_args(task) == {
|
||||
"scan_id": str(scan.id),
|
||||
"provider_id": str(aws_provider.id),
|
||||
}
|
||||
|
||||
def test_a_record_created_without_kwargs_reports_none(self, tenants_fixture):
|
||||
"""The argument is optional, so the other callers keep their behaviour."""
|
||||
task = create_scan_task_record(
|
||||
tenant_id=str(tenants_fixture[0].id),
|
||||
task_id=str(uuid.uuid4()),
|
||||
)
|
||||
|
||||
assert self._task_args(task) == {}
|
||||
|
||||
def test_the_publish_can_overwrite_the_stored_kwargs(
|
||||
self, tenants_fixture, aws_provider
|
||||
):
|
||||
"""django-celery-results stores a Python repr; both must decode alike."""
|
||||
tenant = tenants_fixture[0]
|
||||
scan = self._scan(tenant, aws_provider)
|
||||
task_id = str(uuid.uuid4())
|
||||
kwargs = self._publish_kwargs(tenant, scan)
|
||||
|
||||
task = create_scan_task_record(
|
||||
tenant_id=str(tenant.id), task_id=task_id, task_kwargs=kwargs
|
||||
)
|
||||
before = self._task_args(task)
|
||||
|
||||
# What `before_task_publish` writes once the task reaches the broker.
|
||||
task_result = TaskResult.objects.get(task_id=task_id)
|
||||
task_result.task_kwargs = json.dumps(repr(kwargs))
|
||||
task_result.save(update_fields=["task_kwargs"])
|
||||
task.refresh_from_db()
|
||||
|
||||
assert self._task_args(task) == before
|
||||
|
||||
Generated
+5
-5
@@ -53,7 +53,7 @@ constraints = [
|
||||
{ name = "aliyun-log-fastpb", specifier = "==0.2.0" },
|
||||
{ name = "amqp", specifier = "==5.3.1" },
|
||||
{ name = "annotated-types", specifier = "==0.7.0" },
|
||||
{ name = "anyio", specifier = "==4.12.1" },
|
||||
{ name = "anyio", specifier = "==4.14.2" },
|
||||
{ name = "applicationinsights", specifier = "==0.11.10" },
|
||||
{ name = "apscheduler", specifier = "==3.11.2" },
|
||||
{ name = "argcomplete", specifier = "==3.5.3" },
|
||||
@@ -969,15 +969,15 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "anyio"
|
||||
version = "4.12.1"
|
||||
version = "4.14.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "idna" },
|
||||
{ name = "typing-extensions" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/96/f0/5eb65b2bb0d09ac6776f2eb54adee6abe8228ea05b20a5ad0e4945de8aac/anyio-4.12.1.tar.gz", hash = "sha256:41cfcc3a4c85d3f05c932da7c26d0201ac36f72abd4435ba90d0464a3ffed703", size = 228685, upload-time = "2026-01-06T11:45:21.246Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f", size = 260176, upload-time = "2026-07-12T20:29:07.082Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/38/0e/27be9fdef66e72d64c0cdc3cc2823101b80585f8119b5c112c2e8f5f7dab/anyio-4.12.1-py3-none-any.whl", hash = "sha256:d405828884fc140aa80a3c667b8beed277f1dfedec42ba031bd6ac3db606ab6c", size = 113592, upload-time = "2026-01-06T11:45:19.497Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/da/35/f2287558c17e29fafc8ef3daf819bb9834061cfa43bff8014f7df7f63bdc/anyio-4.14.2-py3-none-any.whl", hash = "sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d1494", size = 125813, upload-time = "2026-07-12T20:29:05.763Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4938,7 +4938,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "prowler-api"
|
||||
version = "1.43.0"
|
||||
version = "1.45.0"
|
||||
source = { virtual = "." }
|
||||
dependencies = [
|
||||
{ name = "cartography" },
|
||||
|
||||
@@ -212,6 +212,14 @@ mainConfig:
|
||||
# MEDIUM
|
||||
ecr_repository_vulnerability_minimum_severity: "MEDIUM"
|
||||
|
||||
# AWS Inspector2
|
||||
# aws.inspector2_coverage_recently_scanned
|
||||
# Maximum days since Inspector2 last scanned an actively covered resource
|
||||
inspector2_max_days_since_last_scan: 3
|
||||
# aws.inspector2_active_findings_within_max_age
|
||||
# Maximum days an Inspector2 finding can stay active since it was first observed
|
||||
inspector2_active_finding_max_age_days: 192
|
||||
|
||||
# AWS Trusted Advisor
|
||||
# aws.trustedadvisor_premium_support_plan_subscribed
|
||||
verify_premium_support_plans: True
|
||||
|
||||
@@ -1,46 +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()
|
||||
|
||||
# Shorten the long FedRAMP KSI descriptions for better display
|
||||
ksi_short_names = {
|
||||
"A secure cloud service offering will protect user data, control access, and apply zero trust principles": "Identity and Access Management",
|
||||
"A secure cloud service offering will use cloud native architecture and design principles to enforce and enhance the Confidentiality, Integrity and Availability of the system": "Cloud Native Architecture",
|
||||
"A secure cloud service provider will ensure that all system changes are properly documented and configuration baselines are updated accordingly": "Change Management",
|
||||
"A secure cloud service provider will continuously educate their employees on cybersecurity measures, testing them regularly": "Cybersecurity Education",
|
||||
"A secure cloud service offering will document, report, and analyze security incidents to ensure regulatory compliance and continuous security improvement": "Incident Reporting",
|
||||
"A secure cloud service offering will monitor, log, and audit all important events, activity, and changes": "Monitoring, Logging, and Auditing",
|
||||
"A secure cloud service offering will have intentional, organized, universal guidance for how every information resource, including personnel, is secured": "Policy and Inventory",
|
||||
"A secure cloud service offering will define, maintain, and test incident response plan(s) and recovery capabilities to ensure minimal service disruption and data loss": "Recovery Planning",
|
||||
"A secure cloud service offering will follow FedRAMP encryption policies, continuously verify information resource integrity, and restrict access to third-party information resources": "Service Configuration",
|
||||
"A secure cloud service offering will understand, monitor, and manage supply chain risks from third-party information resources": "Third-Party Information Resources",
|
||||
}
|
||||
|
||||
# Replace long descriptions with short names - use contains for partial matching
|
||||
if not aux.empty:
|
||||
for long_desc, short_name in ksi_short_names.items():
|
||||
mask = aux["REQUIREMENTS_DESCRIPTION"].str.contains(
|
||||
long_desc, na=False, regex=False
|
||||
)
|
||||
aux.loc[mask, "REQUIREMENTS_DESCRIPTION"] = short_name
|
||||
|
||||
return get_section_containers_cis(
|
||||
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
|
||||
)
|
||||
@@ -1,46 +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()
|
||||
|
||||
# Shorten the long FedRAMP KSI descriptions for better display
|
||||
ksi_short_names = {
|
||||
"A secure cloud service offering will protect user data, control access, and apply zero trust principles": "Identity and Access Management",
|
||||
"A secure cloud service offering will use cloud native architecture and design principles to enforce and enhance the Confidentiality, Integrity and Availability of the system": "Cloud Native Architecture",
|
||||
"A secure cloud service provider will ensure that all system changes are properly documented and configuration baselines are updated accordingly": "Change Management",
|
||||
"A secure cloud service provider will continuously educate their employees on cybersecurity measures, testing them regularly": "Cybersecurity Education",
|
||||
"A secure cloud service offering will document, report, and analyze security incidents to ensure regulatory compliance and continuous security improvement": "Incident Reporting",
|
||||
"A secure cloud service offering will monitor, log, and audit all important events, activity, and changes": "Monitoring, Logging, and Auditing",
|
||||
"A secure cloud service offering will have intentional, organized, universal guidance for how every information resource, including personnel, is secured": "Policy and Inventory",
|
||||
"A secure cloud service offering will define, maintain, and test incident response plan(s) and recovery capabilities to ensure minimal service disruption and data loss": "Recovery Planning",
|
||||
"A secure cloud service offering will follow FedRAMP encryption policies, continuously verify information resource integrity, and restrict access to third-party information resources": "Service Configuration",
|
||||
"A secure cloud service offering will understand, monitor, and manage supply chain risks from third-party information resources": "Third-Party Information Resources",
|
||||
}
|
||||
|
||||
# Replace long descriptions with short names - use contains for partial matching
|
||||
if not aux.empty:
|
||||
for long_desc, short_name in ksi_short_names.items():
|
||||
mask = aux["REQUIREMENTS_DESCRIPTION"].str.contains(
|
||||
long_desc, na=False, regex=False
|
||||
)
|
||||
aux.loc[mask, "REQUIREMENTS_DESCRIPTION"] = short_name
|
||||
|
||||
return get_section_containers_cis(
|
||||
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
|
||||
)
|
||||
@@ -1,46 +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()
|
||||
|
||||
# Shorten the long FedRAMP KSI descriptions for better display
|
||||
ksi_short_names = {
|
||||
"A secure cloud service offering will protect user data, control access, and apply zero trust principles": "Identity and Access Management",
|
||||
"A secure cloud service offering will use cloud native architecture and design principles to enforce and enhance the Confidentiality, Integrity and Availability of the system": "Cloud Native Architecture",
|
||||
"A secure cloud service provider will ensure that all system changes are properly documented and configuration baselines are updated accordingly": "Change Management",
|
||||
"A secure cloud service provider will continuously educate their employees on cybersecurity measures, testing them regularly": "Cybersecurity Education",
|
||||
"A secure cloud service offering will document, report, and analyze security incidents to ensure regulatory compliance and continuous security improvement": "Incident Reporting",
|
||||
"A secure cloud service offering will monitor, log, and audit all important events, activity, and changes": "Monitoring, Logging, and Auditing",
|
||||
"A secure cloud service offering will have intentional, organized, universal guidance for how every information resource, including personnel, is secured": "Policy and Inventory",
|
||||
"A secure cloud service offering will define, maintain, and test incident response plan(s) and recovery capabilities to ensure minimal service disruption and data loss": "Recovery Planning",
|
||||
"A secure cloud service offering will follow FedRAMP encryption policies, continuously verify information resource integrity, and restrict access to third-party information resources": "Service Configuration",
|
||||
"A secure cloud service offering will understand, monitor, and manage supply chain risks from third-party information resources": "Third-Party Information Resources",
|
||||
}
|
||||
|
||||
# Replace long descriptions with short names - use contains for partial matching
|
||||
if not aux.empty:
|
||||
for long_desc, short_name in ksi_short_names.items():
|
||||
mask = aux["REQUIREMENTS_DESCRIPTION"].str.contains(
|
||||
long_desc, na=False, regex=False
|
||||
)
|
||||
aux.loc[mask, "REQUIREMENTS_DESCRIPTION"] = short_name
|
||||
|
||||
return get_section_containers_cis(
|
||||
aux, "REQUIREMENTS_ID", "REQUIREMENTS_ATTRIBUTES_SECTION"
|
||||
)
|
||||
@@ -15,6 +15,7 @@ services:
|
||||
api:
|
||||
hostname: "prowler-api"
|
||||
image: prowlercloud/prowler-api:${PROWLER_API_VERSION:-stable}
|
||||
restart: unless-stopped
|
||||
env_file:
|
||||
- path: .env
|
||||
required: false
|
||||
@@ -44,6 +45,7 @@ services:
|
||||
|
||||
ui:
|
||||
image: prowlercloud/prowler-ui:${PROWLER_UI_VERSION:-stable}
|
||||
restart: unless-stopped
|
||||
env_file:
|
||||
- path: .env
|
||||
required: false
|
||||
@@ -61,6 +63,7 @@ services:
|
||||
|
||||
postgres:
|
||||
image: postgres:16-alpine@sha256:57c72fd2a128e416c7fcc499958864df5301e940bca0a56f58fddf30ffc07777
|
||||
restart: unless-stopped
|
||||
hostname: "postgres-db"
|
||||
volumes:
|
||||
- ./_data/postgres:/var/lib/postgresql/data
|
||||
@@ -81,6 +84,7 @@ services:
|
||||
|
||||
valkey:
|
||||
image: valkey/valkey:8-alpine@sha256:a038175878d66b9d274fbf8be73c0305e93798b83917647f167e18cef3c71eec
|
||||
restart: unless-stopped
|
||||
hostname: "valkey"
|
||||
volumes:
|
||||
- ./_data/valkey:/data
|
||||
@@ -97,6 +101,7 @@ services:
|
||||
|
||||
neo4j:
|
||||
image: graphstack/dozerdb:5.26.27.0@sha256:9b54d6b3a98a76c00bd23e8e78d8c82081ff168162aebd47b25c234e092cb0a0
|
||||
restart: unless-stopped
|
||||
hostname: "neo4j"
|
||||
volumes:
|
||||
- ./_data/neo4j:/data
|
||||
@@ -129,6 +134,7 @@ services:
|
||||
|
||||
worker:
|
||||
image: prowlercloud/prowler-api:${PROWLER_API_VERSION:-stable}
|
||||
restart: unless-stopped
|
||||
# Give Celery soft shutdown time to drain/re-queue in-flight tasks on stop.
|
||||
stop_grace_period: 120s
|
||||
env_file:
|
||||
@@ -149,6 +155,7 @@ services:
|
||||
|
||||
worker-beat:
|
||||
image: prowlercloud/prowler-api:${PROWLER_API_VERSION:-stable}
|
||||
restart: unless-stopped
|
||||
env_file:
|
||||
- path: ./.env
|
||||
required: false
|
||||
@@ -165,6 +172,7 @@ services:
|
||||
|
||||
mcp-server:
|
||||
image: prowlercloud/prowler-mcp:${PROWLER_MCP_VERSION:-stable}
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
- PROWLER_MCP_TRANSPORT_MODE=http
|
||||
env_file:
|
||||
|
||||
+124
-1
@@ -1,9 +1,132 @@
|
||||
---
|
||||
title: "Changelog"
|
||||
description: "New features and improvements in each Prowler release"
|
||||
description: "Track new features, improvements, provider updates, and bug fixes shipped in each Prowler release across CLI, App, Cloud, and MCP products."
|
||||
rss: true
|
||||
---
|
||||
|
||||
<Update label="v5.43.0" description="September 21, 2026">
|
||||
### 🏛️ Compliance — FedRAMP 20x Consolidated Rules 2026
|
||||
|
||||
The FedRAMP 20x Phase One pilot frameworks (`fedramp_20x_ksi_low_aws`, `fedramp_20x_ksi_low_azure` and `fedramp_20x_ksi_low_gcp`) are replaced by two universal frameworks built from the FedRAMP Consolidated Rules for 2026, each covering AWS, Azure, GCP, Kubernetes and Microsoft 365 from a single definition:
|
||||
|
||||
- **FedRAMP 20x KSI** (`fedramp_20x_ksi_2026`): the 46 Key Security Indicators across 10 themes. There is one indicator catalog for every class instead of a separate Low fork; each indicator carries its class applicability and NIST SP 800-53 controls.
|
||||
- **FedRAMP 20x Class C FRR** (`fedramp_20x_frr_class_c_2026`): the 158 FedRAMP Rules of the Class C ruleset that bind cloud service providers. Most are program obligations (reports, notifications, certification package) and stay manual; checks are mapped only where they evidence part of the rule text. Configurable checks carry configuration requirements, so a relaxed `audit_config` cannot turn a requirement green.
|
||||
|
||||
Automation or stored results that reference the pilot framework IDs need to move to `fedramp_20x_ksi_2026`. In Prowler App, both frameworks show the per-provider breakdown in the cross-provider compliance view and can be downloaded as OCSF.
|
||||
|
||||
Read more in the [Compliance documentation](https://docs.prowler.com/user-guide/compliance/tutorials/compliance).
|
||||
|
||||
### 🔎 AWS — Inspector Coverage, CISA KEV and FIPS Checks
|
||||
|
||||
Seven new AWS checks back the vulnerability detection and cryptography rules of FedRAMP 20x Class C:
|
||||
|
||||
- `inspector2_coverage_scan_status_active` and `inspector2_coverage_recently_scanned` report resources Amazon Inspector is not scanning, or last scanned more than `inspector2_max_days_since_last_scan` days ago (default 3).
|
||||
- `inspector2_active_findings_no_known_exploited_vulnerabilities` and `inspector2_active_findings_kev_within_due_date` report active findings whose CVE is in the CISA Known Exploited Vulnerabilities catalog, and those still open past the CISA due date. The KEV data comes from Inspector itself through `inspector2:BatchGetFindingDetails`, so no external feed is needed.
|
||||
- `inspector2_active_findings_within_max_age` reports active findings first observed more than `inspector2_active_finding_max_age_days` days ago (default 192).
|
||||
- `elbv2_listener_fips_tls_enabled` and `transfer_server_fips_security_policy_enabled` report HTTPS/TLS load balancer listeners and Transfer Family servers without a FIPS security policy.
|
||||
|
||||
`inspector2:BatchGetFindingDetails` is not part of `SecurityAudit`, so it is now included in the Prowler additions policy and the CloudFormation scan role. Without it, the KEV checks report `MANUAL` naming the missing permission instead of a false `FAIL`.
|
||||
|
||||
Explore all AWS checks at [Prowler Hub](https://hub.prowler.com/check?provider=aws).
|
||||
|
||||
### ☁️ AWS — Partition Bootstrap Failover
|
||||
|
||||
When `PROWLER_AWS_PARTITION` is set, the bootstrap STS calls (validating credentials, assuming a role and getting an MFA session token) now try up to two more regions of the partition if the first one cannot be reached. A GovCloud host whose configured region belongs to another partition was still sent to `us-gov-east-1`, and on a network that routes only to `us-gov-west-1` the connection check and the scan failed on perfectly valid credentials. Only connection errors and timeouts move on to the next region; credential errors are reported from the first one as before. Later STS calls reuse the region that answered, and nothing changes when `PROWLER_AWS_PARTITION` is unset.
|
||||
|
||||
Read more in the [AWS Regions and Partitions documentation](https://docs.prowler.com/user-guide/providers/aws/regions-and-partitions).
|
||||
|
||||
### 🌐 Azure — Sovereign Cloud Endpoints for Defender and Key Vault
|
||||
|
||||
Defender security contacts and Key Vault key rotation policies now use the endpoints of the cloud selected with `--azure-region` instead of the hardcoded `management.azure.com` and `vault.azure.net` hosts, so both work on `AzureUSGovernment` and `AzureChinaCloud`. Key Vault clients are built from the vault URI that Azure returns for each vault.
|
||||
|
||||
Read more in the [Azure non-default cloud documentation](https://docs.prowler.com/user-guide/providers/azure/use-non-default-cloud).
|
||||
|
||||
### ✉️ Invitations — Expired Invitations No Longer Block Re-Invites
|
||||
|
||||
A pending invitation past its expiry date is now reported as expired, and inviting the same email again marks it as expired and creates the new invitation instead of returning a generic error. The Invitations table disables Edit and Revoke on expired and revoked invitations, and `filter[state__in]` on the invitations endpoint no longer returns a server error.
|
||||
|
||||
In Prowler Cloud, new organizations are offered an **Invite your team** step once the first provider is connected, and Prowler Private Cloud deployments can set `UI_SELF_REGISTRATION_ENABLED=false` to make sign-up invitation-only.
|
||||
|
||||
Read more in the [Invitations documentation](https://docs.prowler.com/user-guide/tutorials/prowler-app-rbac#invitations).
|
||||
|
||||
### 📄 Reports — Downloads on Self-Hosted Storage
|
||||
|
||||
Report downloads no longer depend on the storage host being the same inside and outside the container network. `DJANGO_OUTPUT_S3_AWS_PUBLIC_ENDPOINT_URL` signs the download URL against a browser-reachable host, so a deployment whose object storage answers only on an internal address serves the file instead of a link the browser cannot open. Leaving `DJANGO_OUTPUT_S3_AWS_DEFAULT_REGION` unset, common on S3-compatible storage with no meaningful region, no longer makes the download fail with a server error.
|
||||
|
||||
### 🔍 Checks
|
||||
|
||||
- **Huawei Cloud:** new `smn_topic_subscriptions` check reports SMN topics without any subscription.
|
||||
- **Cloudflare:** the API token links in the provider wizard request the SSL and Certificates, Bot Management and Zone WAF read permissions the checks need, so a token created from the wizard no longer produces failures on permissions it was never granted.
|
||||
- **Microsoft 365:** five Defender malware, anti-phishing and inbound anti-spam checks no longer fail with `KeyError` on tenants that use the Standard or Strict preset security policies, which dropped every finding of those checks. Preset policies are covered by `defender_strict_preset_security_policy_enabled`.
|
||||
- **Google Workspace:** `security_2sv_enforced` reports domain-wide 2-Step Verification failures as `FAIL` even when every failing setting is overridden for a group or organizational unit.
|
||||
|
||||
Explore all checks at [Prowler Hub](https://hub.prowler.com/check).
|
||||
|
||||
### 🔐 Security Updates
|
||||
|
||||
- `libsqlite3-0`, `gzip`, `perl-base`, `libssh2-1t64` and `libpcre2-8-0` upgraded in the SDK and API container images, patching high-severity Debian CVEs.
|
||||
- PowerShell upgraded to 7.5.11 in the SDK and API container images, bundling .NET runtime 9.0.20 and patching CVE-2026-62901.
|
||||
- `anyio` upgraded to 4.14.2 in the SDK, the API and the MCP Server, patching CVE-2026-63374.
|
||||
|
||||
See the [full release notes on GitHub](https://github.com/prowler-cloud/prowler/releases/tag/5.43.0) for the complete list of changes.
|
||||
</Update>
|
||||
|
||||
<Update label="v5.42.0" description="September 11, 2026">
|
||||
### ☁️ AWS — ISO Partitions
|
||||
|
||||
Prowler now resolves regions and services for the AWS ISO partitions (`aws-iso`, `aws-iso-b`, `aws-iso-e` and `aws-iso-f`) the same way it does for the commercial, China, European Sovereign Cloud and GovCloud partitions. The region matrix is filled from the endpoint metadata bundled with botocore, which needs no credentials or network access, so it covers partitions that are air-gapped from the internet. Scanning them no longer requires a hand-edited `aws_regions_by_service.json`: ISO regions such as `us-isob-east-1` are accepted by `--region` and `--excluded-region`.
|
||||
|
||||
Deployments that declare `PROWLER_AWS_PARTITION` also keep their bootstrap STS calls in the configured region when it belongs to that partition. An install in `us-gov-west-1` that reaches AWS only through its own VPC endpoints is no longer sent to `us-gov-east-1`, where the connection check and the scan used to time out.
|
||||
|
||||
Read more in the [AWS Regions and Partitions documentation](https://docs.prowler.com/user-guide/providers/aws/regions-and-partitions).
|
||||
|
||||
### ⏱️ AWS — Configurable Timeouts for Restricted Networks
|
||||
|
||||
Scans from networks with restricted egress (VPC endpoints for only some services, GovCloud or private deployments) could take hours: Boto3 waits 60 seconds to connect by default and retries connection errors, so every service without a reachable endpoint cost up to four 60-second attempts in every region. Prowler now lowers the default connect timeout to 10 seconds, keeps the read timeout at 60 seconds, and exposes both through `--aws-connect-timeout` and `--aws-read-timeout`, or through the `PROWLER_AWS_BOTO3_CONNECT_TIMEOUT` and `PROWLER_AWS_BOTO3_READ_TIMEOUT` environment variables for deployments without a CLI. `--aws-retries-max-attempts 0` now disables retries instead of silently falling back to three, leaving a single attempt per call.
|
||||
|
||||
Read more in the [Boto3 configuration documentation](https://docs.prowler.com/user-guide/providers/aws/boto3-configuration).
|
||||
|
||||
### 🐳 Image Provider — Reusable Vulnerability Database
|
||||
|
||||
The Image provider now honors `TRIVY_CACHE_DIR`. When the variable names a directory, Trivy keeps its vulnerability database there and Prowler leaves the directory in place after the scan, so the database is downloaded once instead of on every scan. Hosts without internet access can now scan images by pointing `TRIVY_CACHE_DIR` at a pre-populated database and setting `TRIVY_SKIP_DB_UPDATE=true`. Without the variable, the temporary cache is created and removed as before.
|
||||
|
||||
Read more in the [Image provider documentation](https://docs.prowler.com/user-guide/providers/image/getting-started-image#vulnerability-database-cache).
|
||||
|
||||
### 🎫 Jira Integration — Faster Connection Test
|
||||
|
||||
Testing a Jira integration no longer reports a false failure on accounts with many projects. The connection test fetched the issue types of every project one request at a time, which could outlast the wait in the UI even when the check was about to succeed. Issue types are now fetched concurrently, a project whose issue types the integration user cannot see is no longer logged as an error, and the Integrations page keeps following the connection test instead of giving up after about a minute.
|
||||
|
||||
Read more in the [Jira integration documentation](https://docs.prowler.com/user-guide/tutorials/prowler-app-jira-integration).
|
||||
|
||||
### 📚 Compliance — Catalog Integrity Fixes
|
||||
|
||||
A new integrity test runs over every compliance framework, asserting unique requirement IDs, no check listed twice within a requirement, and that every referenced check exists for its provider. The fixes it drove span 42 frameworks across AWS, Azure, GCP, GitHub, Kubernetes and Microsoft 365:
|
||||
|
||||
- **Duplicate requirement IDs:** identical copies are removed, and distinct requirements that shared an ID get their own, such as `1.10` in CIS AWS 5.0 and `rc_rp_1` for RC.RP-1 in NIST CSF 1.1. In Prowler ThreatScore for Azure, SQL auditing retention moves from `3.2.1` to `3.2.4`, and requirement `1.2.1` of Prowler ThreatScore for GCP now points to `iam_sa_no_user_managed_keys`.
|
||||
- **Stale check references:** checks that no longer exist are replaced with their current name when there is a direct equivalent, or removed so the requirement reports as manual. Most of these were in the FedRAMP 20x KSI frameworks.
|
||||
|
||||
Renamed requirement IDs appear as new requirements for scans run after the upgrade.
|
||||
|
||||
The compliance overview task that runs after every scan is also faster: ThreatScore mappings are read once from the compliance template instead of from every finding, and rows are inserted with time-ordered `uuid7` IDs grouped by framework and requirement.
|
||||
|
||||
Read more in the [Compliance documentation](https://docs.prowler.com/user-guide/compliance/tutorials/compliance).
|
||||
|
||||
### 🔍 Checks
|
||||
|
||||
`rolesanywhere_profile_restricts_session_permissions`, `iam_role_service_trust_restricts_source_to_account` and `codebuild_project_uses_allowed_github_organizations` no longer crash with `TypeError` when the scanning role is denied `iam:ListRoles`, which dropped every finding of those checks for the account. Without the role inventory, an enabled IAM Roles Anywhere profile without session scoping reports `MANUAL`, and CodeBuild projects whose service role cannot be resolved are skipped.
|
||||
|
||||
Explore all AWS checks at [Prowler Hub](https://hub.prowler.com/check?provider=aws).
|
||||
|
||||
### 🔐 Security Updates
|
||||
|
||||
- `next` upgraded to 16.3.3 in the UI, patching unauthenticated remote code execution through AVIF image optimization ([GHSA-2xp9-vwfh-vxw4](https://github.com/advisories/GHSA-2xp9-vwfh-vxw4)) and on Windows-hosted servers ([GHSA-p293-qw3h-jr36](https://github.com/advisories/GHSA-p293-qw3h-jr36)).
|
||||
- `sharp` upgraded to 0.35.4 in the UI, patching libheif image-decoding vulnerabilities ([GHSA-rgj7-g3m4-5g8c](https://github.com/advisories/GHSA-rgj7-g3m4-5g8c)).
|
||||
- `nanoid`, `js-yaml` and `postcss`, plus eleven transitive UI dependencies, upgraded to patched versions, resolving 40 npm audit advisories (21 high, 15 moderate, 4 low).
|
||||
- `libuuid` upgraded to 2.41.6-r1 in the MCP Server image, patching CVE-2026-53612, CVE-2026-53613, CVE-2026-53614, CVE-2026-76642, CVE-2026-78408 and CVE-2026-78410.
|
||||
|
||||
See the [full release notes on GitHub](https://github.com/prowler-cloud/prowler/releases/tag/5.42.0) for the complete list of changes.
|
||||
</Update>
|
||||
|
||||
<Update label="v5.41.0" description="September 2, 2026">
|
||||
### 📥 Scans — Import Findings from the Browser
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'AI Skills System'
|
||||
title: 'AI Skills System for Prowler Contributors'
|
||||
description: 'Enable AI coding assistants like Claude Code, Cursor, and Copilot to follow Prowler patterns using structured skills, setup scripts, and triggers.'
|
||||
---
|
||||
|
||||
This guide explains the AI Skills system that provides on-demand context and patterns to AI agents working with the Prowler codebase.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Alibaba Cloud Provider'
|
||||
title: 'Alibaba Cloud Provider Implementation'
|
||||
description: 'Explore the Alibaba Cloud provider in Prowler, covering session management, RAM authentication, STS credentials, region discovery, and service classes.'
|
||||
---
|
||||
|
||||
This page details the [Alibaba Cloud](https://www.alibabacloud.com/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Attack Paths Queries"
|
||||
description: "Write and maintain read-only openCypher Attack Paths queries in Prowler that traverse the Cartography cloud graph to detect privilege escalation and exposure."
|
||||
---
|
||||
|
||||
This guide explains how to write and maintain Prowler Attack Paths queries: the read-only openCypher queries that traverse the Cartography-ingested cloud graph to detect privilege escalation chains, network exposure, and other graph-shaped security risks.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'AWS Provider'
|
||||
title: 'AWS Provider Implementation'
|
||||
description: 'Understand the AWS provider internals in Prowler: boto3 sessions, IAM role assumption, region and Organizations discovery, and service base classes.'
|
||||
---
|
||||
|
||||
In this page you can find all the details about [Amazon Web Services (AWS)](https://aws.amazon.com/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Azure Provider'
|
||||
title: 'Azure Provider Implementation'
|
||||
description: 'Learn how the Azure provider in Prowler manages Service Principal, CLI, browser, and Managed Identity auth, subscription discovery, and Entra ID scanning.'
|
||||
---
|
||||
|
||||
In this page you can find all the details about [Microsoft Azure](https://azure.microsoft.com/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Check Metadata Guidelines'
|
||||
title: 'Check Metadata Writing Guidelines'
|
||||
description: 'Follow Prowler conventions for writing check titles, descriptions, risk, remediation, and status_extended fields when authoring check metadata JSON files.'
|
||||
---
|
||||
|
||||
## Introduction
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Prowler Checks'
|
||||
title: 'Creating New Prowler Checks'
|
||||
description: 'Step-by-step guide to add a new security check to Prowler, covering folder structure, naming conventions, metadata files, test scenarios, and CLI validation.'
|
||||
---
|
||||
|
||||
This guide explains how to create new checks in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Configurable Checks in Prowler'
|
||||
title: 'Configurable Checks with audit_config'
|
||||
description: 'Make Prowler checks configurable through the audit_config object and config.yaml, letting users override thresholds, defaults, and check behavior at scan time.'
|
||||
---
|
||||
|
||||
Prowler empowers users to extend and adapt cloud security coverage by making checks configurable through the use of the `audit_config` object. This approach enables customization of checks to meet specific requirements through a configuration file.
|
||||
@@ -154,6 +155,8 @@ Only fields with a numeric range, a fixed value set, or a length cap are listed.
|
||||
| `max_days_secret_unused` | `7..365` days | |
|
||||
| `max_days_secret_unrotated` | `1..180` days | NIST IA-5: rotate quarterly; CIS ≤90 |
|
||||
| `min_kinesis_stream_retention_hours` | `24..8760` h | 1 day .. 1 year |
|
||||
| `inspector2_max_days_since_last_scan` | `1..90` days | |
|
||||
| `inspector2_active_finding_max_age_days` | `1..365` days | Default `192` matches the FedRAMP 20x rule that marks vulnerabilities still open after 192 days as accepted |
|
||||
| `shodan_api_key` | ≤512 chars | |
|
||||
|
||||
### Azure
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Debugging in Prowler'
|
||||
title: 'Debugging Prowler with VSCode'
|
||||
description: 'Set up Visual Studio Code launch configurations and debugpy to step through Prowler checks, services, and provider code for AWS, Azure, GCP, and more.'
|
||||
---
|
||||
|
||||
Debugging in Prowler simplifies the development process, allowing developers to efficiently inspect and resolve unexpected issues during execution.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Contributing to Documentation'
|
||||
title: 'Contributing to Prowler Documentation'
|
||||
description: 'Contribute to Prowler docs built with Mintlify: learn the section structure, AI agent guidelines, local preview setup, and style conventions for MDX pages.'
|
||||
---
|
||||
|
||||
Prowler documentation is built using [Mintlify](https://www.mintlify.com/docs), allowing contributors to easily add or enhance documentation.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'End-2-End Tests for Prowler Local Server'
|
||||
title: 'End-to-End Tests for Prowler App'
|
||||
description: 'Write Playwright end-to-end tests for Prowler App covering user journeys, Page Object Models, storage state reuse, and organizing spec files by feature area.'
|
||||
---
|
||||
|
||||
End-to-end (E2E) tests validate complete user flows in Prowler Local Server (UI + API). These tests are implemented with [Playwright](https://playwright.dev/) under the `ui/tests` folder and are designed to run against a Prowler Local Server environment.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Environment Variable Naming Convention'
|
||||
title: 'Environment Variable Naming Conventions'
|
||||
description: 'Namespace Prowler App, API, SDK, and MCP Server environment variables with component prefixes like UI_ and API_ to avoid conflicts in a shared .env file.'
|
||||
---
|
||||
|
||||
Prowler is a monorepo composed of several runtime components — Prowler Local Server (the web user interface), Prowler API (the backend), Prowler SDK, and Prowler MCP Server (Model Context Protocol) — that frequently share a single `.env` file. To keep that shared configuration unambiguous, each component namespaces its environment variables with a component-specific prefix.
|
||||
@@ -40,6 +41,17 @@ The former build-time variables map to the new runtime variables as follows:
|
||||
|
||||
`UI_CLOUD_ENABLED` is a plain runtime boolean flag that enables Prowler Cloud behavior when set to the exact string `"true"` and defaults to off; unlike the other renamed variables it has no legacy fallback, so `NEXT_PUBLIC_IS_CLOUD_ENV` is no longer read.
|
||||
|
||||
`UI_SELF_REGISTRATION_ENABLED` is a runtime opt-out flag that Prowler Local Server reads only when `UI_CLOUD_ENABLED` is `"true"`. It defaults to on and turns off when set to `"false"`, matched case-insensitively so the same value can be shared with a backend setting written `False`. When it is off, the sign-up page only opens with an invitation token, the sign-in page drops its "Sign up" link, and the profile hides "Create organization"; invited users can still complete their registration. Outside a Prowler Cloud deployment the flag is ignored and account creation stays open.
|
||||
## Registry UI Rollout and Rollback
|
||||
|
||||
`UI_REGISTRY_ENABLED` is an optional runtime flag for Prowler Cloud and Private Cloud. Registry is eligible only when both `UI_CLOUD_ENABLED` and `UI_REGISTRY_ENABLED` are the exact string `"true"` and the current user has the backend-authorized `manage_registry` permission. Unset, `"false"`, or malformed values fail closed. The flag defaults to off and is not a replacement for backend authorization. Registry access is independent of billing; Private Cloud can use it with `CLOUD_BILLING_ENABLED=false`.
|
||||
|
||||
Roll out Registry only after the Registry backend dependency is deployed, intended roles have `manage_registry`, and acceptance with real credentials has exercised installation, provider account creation, credentials, connection, and scan launch. Deploy the UI with `UI_REGISTRY_ENABLED` unset or `"false"`; set it to `"true"` only in the prepared process environment, then restart or otherwise apply the environment update required by the platform. A Registry key must belong to the configured Registry environment; a production key does not authenticate against a development Registry.
|
||||
|
||||
The catalog displays all artifacts, including built-ins and packages containing only checks or compliance frameworks. Only external provider artifacts support Add. After confirmed installation, open Providers and select the option labeled Registry to configure an account. Creating accounts and running scans also require the corresponding provider and scan permissions. Removing an artifact keeps existing provider accounts, but future connections or scans can fail until the artifact is installed again.
|
||||
|
||||
To roll back, set `UI_REGISTRY_ENABLED=false` or remove it and apply the environment update. Proxy, page, and action checks deny on their next request. Navigation refreshes from server-authorized access when the page is requested again. Rollback does not delete Registry credentials, tenant artifact records, or provider accounts.
|
||||
|
||||
The build-time-only Sentry variables used for source-map upload — `SENTRY_ORG`, `SENTRY_PROJECT`, `SENTRY_AUTH_TOKEN`, and `SENTRY_RELEASE` — keep their names, as they are not part of Prowler Local Server's runtime configuration.
|
||||
|
||||
## Enabling Third-Party Integrations
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Google Cloud Provider'
|
||||
title: 'Google Cloud (GCP) Provider Implementation'
|
||||
description: 'Dive into the GCP provider in Prowler: Application Default Credentials, service accounts, OAuth, impersonation, and multi-project and organization discovery.'
|
||||
---
|
||||
|
||||
This page details the [Google Cloud Platform (GCP)](https://cloud.google.com/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'GitHub Provider'
|
||||
title: 'GitHub Provider Implementation'
|
||||
description: 'See how the GitHub provider in Prowler handles Personal Access Token, OAuth App, and GitHub App authentication to audit repositories and organizations.'
|
||||
---
|
||||
|
||||
This page details the [GitHub](https://github.com/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Integration Tests'
|
||||
title: 'Integration Tests for Prowler'
|
||||
description: 'Placeholder page tracking upcoming guidance on Prowler integration tests, covering how to validate multi-component flows across the SDK, API, and UI.'
|
||||
---
|
||||
|
||||
Coming soon ...
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Creating a New Integration'
|
||||
title: 'Creating New Prowler Integrations'
|
||||
description: 'Build integrations that ship Prowler findings to Slack, Jira, AWS Security Hub, and other platforms by scripting API calls and configuring output pipelines.'
|
||||
---
|
||||
|
||||
## Introduction
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Introduction to developing in Prowler'
|
||||
title: 'Introduction to Developing in Prowler'
|
||||
description: 'Get started as a Prowler contributor: pick a good first issue, extend checks, services, or integrations, and follow the AI-driven contribution workflow.'
|
||||
---
|
||||
|
||||
Thanks for your interest in contributing to Prowler!
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Kubernetes Provider'
|
||||
title: 'Kubernetes Provider Implementation'
|
||||
description: 'Explore the Kubernetes provider in Prowler, including kubeconfig context loading, namespace discovery, in-cluster execution, and service class scaffolding.'
|
||||
---
|
||||
|
||||
This page details the [Kubernetes](https://kubernetes.io/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Lighthouse AI Architecture'
|
||||
title: 'Prowler Lighthouse AI Architecture'
|
||||
description: 'Inside Prowler Lighthouse AI: a three-tier Next.js, API route, and Langchain agent design that connects LLMs to security data through MCP tool calls.'
|
||||
---
|
||||
|
||||
This document describes the internal architecture of Prowler Lighthouse AI, enabling developers to understand how components interact and where to add new functionality.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'LLM Provider'
|
||||
title: 'LLM Provider Implementation'
|
||||
description: 'Learn how the Prowler LLM provider uses promptfoo to run red team security tests against OpenAI and other large language models with reusable test suites.'
|
||||
---
|
||||
|
||||
This page details the [Large Language Model (LLM)](https://en.wikipedia.org/wiki/Large_language_model) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Microsoft 365 (M365) Provider'
|
||||
title: 'Microsoft 365 (M365) Provider Implementation'
|
||||
description: 'Understand the Microsoft 365 provider in Prowler, PowerShell 7.4+ requirements, Exchange Online and Teams modules, and Entra ID tenant scanning.'
|
||||
---
|
||||
|
||||
This page details the [Microsoft 365 (M365)](https://www.microsoft.com/en-us/microsoft-365) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Extending the MCP Server'
|
||||
title: 'Extending the Prowler MCP Server'
|
||||
description: 'Add new tools and sub-servers to the Prowler MCP Server so AI assistants like Claude Desktop and Cursor can query Prowler App, Hub, and documentation content.'
|
||||
---
|
||||
|
||||
This guide explains how to extend the Prowler MCP Server with new tools and features.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Create a Custom Output Format'
|
||||
title: 'Creating Custom Prowler Output Formats'
|
||||
description: 'Add a new output format to Prowler by subclassing the Output class, defining the schema, and generating JSON, CSV, HTML, or SARIF-style reports from findings.'
|
||||
---
|
||||
|
||||
## Introduction
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Prowler Providers'
|
||||
title: 'Creating New Prowler Providers'
|
||||
description: 'Design and implement new Prowler providers across cloud, SaaS, and container platforms, following the base Provider class patterns, models, and CLI wiring.'
|
||||
---
|
||||
|
||||
## Introduction
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Prowler Studio'
|
||||
title: 'Prowler Studio AI Check Workflow'
|
||||
description: 'Prowler Studio is a Claude Code workflow that generates consistent, tested Prowler security checks by enforcing skills, guardrails, and provider conventions.'
|
||||
---
|
||||
|
||||
**Prowler Studio is an AI workflow that ensures Claude Code follows Prowler's skills, guardrails, and best practices when creating new security checks.** What lands in the resulting pull request is consistent, tested, and ready for human review — not half-correct boilerplate that needs to be rewritten.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Renaming Checks in Prowler'
|
||||
title: 'Renaming Existing Prowler Checks'
|
||||
description: 'Safely rename a Prowler check by updating folder paths, class names, metadata JSON, CheckAliases, and compliance mappings without breaking existing users.'
|
||||
---
|
||||
|
||||
To rename a check in Prowler, follow these steps when aligning with Check ID structure, fixing typos, or updating check logic that requires a new name.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Secret-Scanning Checks'
|
||||
title: 'Building Secret-Scanning Checks'
|
||||
description: 'Author efficient secret-scanning checks in Prowler using the Kingfisher engine and detect_secrets_scan_batch helper to scan payloads in chunked subprocesses.'
|
||||
---
|
||||
|
||||
import { VersionBadge } from "/snippets/version-badge.mdx"
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Creating a New Security Compliance Framework in Prowler'
|
||||
title: 'Adding New Compliance Frameworks to Prowler'
|
||||
description: 'Map catalogs like CIS, NIST 800-53, PCI DSS, or DORA into Prowler by defining JSON schemas, Pydantic models, check mappings, and validation tests.'
|
||||
---
|
||||
|
||||
import { VersionBadge } from "/snippets/version-badge.mdx"
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Server-Sent Events (SSE)'
|
||||
title: 'Adding Server-Sent Events (SSE) Endpoints'
|
||||
description: 'Stream real-time updates from the Prowler API using Server-Sent Events with django-eventstream, including scan progress and streamed LLM token output.'
|
||||
---
|
||||
|
||||
import { VersionBadge } from "/snippets/version-badge.mdx"
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Prowler Services'
|
||||
title: 'Creating New Prowler Services'
|
||||
description: 'Add new services like EC2 or Exchange Online to a Prowler provider by scaffolding the service class, data models, API client calls, and shared client instances.'
|
||||
---
|
||||
|
||||
Here you can find how to create a new service, or to complement an existing one, for a [Prowler Provider](/developer-guide/provider).
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'StackIT Provider'
|
||||
title: 'StackIT Cloud Provider Implementation'
|
||||
description: 'Discover how the StackIT provider in Prowler authenticates using service account keys, manages token refresh via the SDK, and audits a single StackIT project.'
|
||||
---
|
||||
|
||||
This page details the [StackIT Cloud](https://www.stackit.de/) provider implementation in Prowler.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Test Impact Analysis'
|
||||
title: 'Test Impact Analysis in CI'
|
||||
description: 'Prowler test impact analysis maps changed files to relevant SDK, API, and Playwright E2E tests through a GitHub Actions workflow and configurable path rules.'
|
||||
---
|
||||
|
||||
Test impact analysis (TIA) determines which tests to run based on the files changed in a pull request. Instead of running the full test suite on every pull request, TIA maps changed files to the specific Prowler SDK, API, and end-to-end (E2E) tests that cover them. This approach reduces continuous integration (CI) time and resource usage while maintaining confidence that relevant code paths are tested.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Unit Tests for Prowler Checks'
|
||||
title: 'Writing Unit Tests for Prowler Checks'
|
||||
description: 'Write robust unit tests for Prowler checks with pytest and mock, covering zero-finding, PASS, FAIL, and multi-resource scenarios across every provider.'
|
||||
---
|
||||
|
||||
Unit tests for Prowler checks vary based on the provider being evaluated.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Basic Usage'
|
||||
title: 'Get started with the Prowler App web interface'
|
||||
description: 'Sign up, add a cloud provider, launch a scan, and review findings in the Prowler App web UI for AWS, Azure, GCP, Kubernetes, and Microsoft 365.'
|
||||
---
|
||||
|
||||
## Access Prowler Local Server
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
---
|
||||
title: 'Basic Usage'
|
||||
title: 'Run scans with the Prowler CLI'
|
||||
description: 'Learn the essential Prowler CLI commands to run multi-cloud security scans, list checks and services, and export CSV, JSON-OCSF, and HTML reports.'
|
||||
---
|
||||
|
||||
import { VersionBadge } from "/snippets/version-badge.mdx"
|
||||
|
||||
## Running Prowler
|
||||
|
||||
Running Prowler requires specifying the provider (e.g. `aws`, `gcp`, `azure`, `kubernetes`, `m365`, `github`, `iac` or `mongodbatlas`):
|
||||
@@ -91,6 +94,18 @@ By default, `prowler` will scan all AWS regions.
|
||||
</Note>
|
||||
See more details about AWS Authentication in the [Authentication Section](/user-guide/providers/aws/authentication) section.
|
||||
|
||||
- **AWS Retrier and Timeout Configuration**
|
||||
|
||||
<VersionBadge version="5.42.0" />
|
||||
|
||||
Tune the Boto3 standard retrier and the endpoint timeouts when AWS throttles the scan or when some endpoints are unreachable from the network Prowler runs in:
|
||||
|
||||
```console
|
||||
prowler aws --aws-retries-max-attempts 5 --aws-connect-timeout 5 --aws-read-timeout 30
|
||||
```
|
||||
|
||||
See the [Boto3 configuration](/user-guide/providers/aws/boto3-configuration) page for defaults and environment variables.
|
||||
|
||||
## Azure
|
||||
|
||||
Azure requires specifying the auth method:
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Tools Reference"
|
||||
title: 'Prowler MCP Server tools reference'
|
||||
description: 'Complete reference for Prowler MCP Server tools, grouped by namespace: Prowler Hub catalog, documentation search, and Prowler Cloud or App management.'
|
||||
---
|
||||
|
||||
Complete reference guide for all tools available in the Prowler MCP Server. Tools are organized by namespace.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Configuration"
|
||||
title: 'Configure the Prowler MCP Server for AI clients'
|
||||
description: 'Connect Claude Desktop, Cursor, and other MCP clients to Prowler MCP Server using HTTP or STDIO mode, and set up API key authentication for Prowler Cloud.'
|
||||
---
|
||||
|
||||
Configure your MCP client to connect to Prowler MCP Server.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'AWS Security Hub'
|
||||
title: 'Prowler vs AWS Security Hub'
|
||||
description: 'Compare Prowler with AWS Security Hub for cloud security posture management, multi-account scanning, compliance checks, and multi-cloud coverage beyond AWS.'
|
||||
---
|
||||
|
||||
AWS Security Hub remains a managed service designed for centralizing security alerts and compliance status within AWS environments. It integrates with various AWS security services and provides a consolidated view of security findings.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'GCP Cloud Security Command Center (Cloud SCC)'
|
||||
title: 'Prowler vs Google Cloud Security Command Center'
|
||||
description: 'Compare Prowler with GCP Cloud Security Command Center for asset visibility, threat detection, compliance monitoring, and cloud-agnostic security scanning.'
|
||||
---
|
||||
|
||||
Google Cloud Security Command Center (Cloud SCC) is a centralized security and risk management platform for Google Cloud Platform (GCP). It provides visibility into assets, vulnerabilities, and threats across GCP environments, helping organizations to manage and improve their security posture.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Comparison'
|
||||
title: 'Prowler vs other cloud security platforms'
|
||||
description: 'Compare Prowler with AWS Security Hub, Microsoft Sentinel, Microsoft Defender for Cloud, and Google Cloud Security Command Center for cloud security posture.'
|
||||
---
|
||||
|
||||
Click to learn more about each cloud security provider and learn how Prowler is differentiated.
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Microsoft Defender for Cloud'
|
||||
title: 'Prowler vs Microsoft Defender for Cloud'
|
||||
description: 'Use Prowler open-source scans alongside Microsoft Defender for Cloud to validate Azure posture, customize checks, and extend coverage to AWS, GCP, and K8s.'
|
||||
---
|
||||
|
||||
**Use open-source scanning to validate and extend Microsoft Defender for Cloud**
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: 'Microsoft Sentinel'
|
||||
title: 'Prowler vs Microsoft Sentinel'
|
||||
description: 'Compare Prowler with Microsoft Sentinel SIEM and SOAR for threat detection, log ingestion, compliance scanning, and multi-cloud security posture management.'
|
||||
---
|
||||
|
||||
Microsoft Sentinel is a scalable, cloud-native security information and event management (SIEM) and security orchestration automated response (SOAR) solution. It's designed to collect, detect, investigate, and respond to threats across the enterprise, primarily within the Azure cloud environment but also extending to on-premises and other cloud environments through various connectors.
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
---
|
||||
title: "Prowler API Reference"
|
||||
title: 'Prowler API reference'
|
||||
description: 'Open the interactive Prowler Cloud API v1 reference to explore endpoints for scans, findings, providers, compliance, and integrations with auth details.'
|
||||
url: "https://api.prowler.com/api/v1/docs"
|
||||
---
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user