feat(compliance): add DORA framework for AWS (#11131)

This commit is contained in:
Pedro Martín
2026-06-03 11:43:55 +02:00
committed by GitHub
parent d573af911d
commit f7f8747512
50 changed files with 2357 additions and 38277 deletions
-10
View File
@@ -39,11 +39,6 @@ from prowler.lib.outputs.compliance.cis.cis_oraclecloud import OracleCloudCIS
from prowler.lib.outputs.compliance.cisa_scuba.cisa_scuba_googleworkspace import (
GoogleWorkspaceCISASCuBA,
)
from prowler.lib.outputs.compliance.csa.csa_alibabacloud import AlibabaCloudCSA
from prowler.lib.outputs.compliance.csa.csa_aws import AWSCSA
from prowler.lib.outputs.compliance.csa.csa_azure import AzureCSA
from prowler.lib.outputs.compliance.csa.csa_gcp import GCPCSA
from prowler.lib.outputs.compliance.csa.csa_oraclecloud import OracleCloudCSA
from prowler.lib.outputs.compliance.ens.ens_aws import AWSENS
from prowler.lib.outputs.compliance.ens.ens_azure import AzureENS
from prowler.lib.outputs.compliance.ens.ens_gcp import GCPENS
@@ -102,7 +97,6 @@ COMPLIANCE_CLASS_MAP = {
(lambda name: name == "prowler_threatscore_aws", ProwlerThreatScoreAWS),
(lambda name: name.startswith("ccc_"), CCC_AWS),
(lambda name: name.startswith("c5_"), AWSC5),
(lambda name: name.startswith("csa_"), AWSCSA),
(lambda name: name == "asd_essential_eight_aws", ASDEssentialEightAWS),
],
"azure": [
@@ -113,7 +107,6 @@ COMPLIANCE_CLASS_MAP = {
(lambda name: name.startswith("ccc_"), CCC_Azure),
(lambda name: name == "prowler_threatscore_azure", ProwlerThreatScoreAzure),
(lambda name: name == "c5_azure", AzureC5),
(lambda name: name.startswith("csa_"), AzureCSA),
],
"gcp": [
(lambda name: name.startswith("cis_"), GCPCIS),
@@ -123,7 +116,6 @@ COMPLIANCE_CLASS_MAP = {
(lambda name: name == "prowler_threatscore_gcp", ProwlerThreatScoreGCP),
(lambda name: name.startswith("ccc_"), CCC_GCP),
(lambda name: name == "c5_gcp", GCPC5),
(lambda name: name.startswith("csa_"), GCPCSA),
],
"kubernetes": [
(lambda name: name.startswith("cis_"), KubernetesCIS),
@@ -152,11 +144,9 @@ COMPLIANCE_CLASS_MAP = {
"image": [],
"oraclecloud": [
(lambda name: name.startswith("cis_"), OracleCloudCIS),
(lambda name: name.startswith("csa_"), OracleCloudCSA),
],
"alibabacloud": [
(lambda name: name.startswith("cis_"), AlibabaCloudCIS),
(lambda name: name.startswith("csa_"), AlibabaCloudCSA),
(
lambda name: name == "prowler_threatscore_alibabacloud",
ProwlerThreatScoreAlibaba,
+11 -6
View File
@@ -29,7 +29,10 @@ from api.db_router import READ_REPLICA_ALIAS, MainRouter
from api.db_utils import rls_transaction
from api.models import Provider, Scan, ScanSummary, StateChoices, ThreatScoreSnapshot
from api.utils import initialize_prowler_provider
from prowler.lib.check.compliance_models import Compliance
from prowler.lib.check.compliance_models import (
Compliance,
get_bulk_compliance_frameworks_universal,
)
from prowler.lib.outputs.finding import Finding as FindingOutput
logger = get_task_logger(__name__)
@@ -571,7 +574,7 @@ def generate_csa_report(
Args:
tenant_id: The tenant ID for Row-Level Security context.
scan_id: ID of the scan executed by Prowler.
compliance_id: ID of the compliance framework (e.g., "csa_ccm_4.0_aws").
compliance_id: ID of the compliance framework (e.g., "csa_ccm_4.0").
output_path: Output PDF file path.
provider_id: Provider ID for the scan.
only_failed: If True, only include failed requirements in detailed section.
@@ -883,9 +886,11 @@ def generate_compliance_reports(
frameworks_bulk.get(f"nis2_{provider_type}")
)
if generate_csa:
pending_checks_by_framework["csa"] = _get_compliance_check_ids(
frameworks_bulk.get(f"csa_ccm_4.0_{provider_type}")
)
# csa_ccm_4.0 lives at the top level, not under compliance/{provider}/.
csa_framework = frameworks_bulk.get(
"csa_ccm_4.0"
) or get_bulk_compliance_frameworks_universal(provider_type).get("csa_ccm_4.0")
pending_checks_by_framework["csa"] = _get_compliance_check_ids(csa_framework)
if generate_cis and latest_cis:
pending_checks_by_framework["cis"] = _get_compliance_check_ids(
frameworks_bulk.get(latest_cis)
@@ -1183,7 +1188,7 @@ def generate_compliance_reports(
if generate_csa:
generated_report_keys.append("csa")
csa_path = output_paths["csa"]
compliance_id_csa = f"csa_ccm_4.0_{provider_type}"
compliance_id_csa = "csa_ccm_4.0"
pdf_path_csa = f"{csa_path}_csa_report.pdf"
logger.info("Generating CSA CCM report with compliance %s", compliance_id_csa)
+57 -4
View File
@@ -5,6 +5,7 @@ import time
from abc import ABC, abstractmethod
from contextlib import contextmanager
from dataclasses import dataclass, field
from types import SimpleNamespace
from typing import Any
from celery.utils.log import get_task_logger
@@ -26,7 +27,10 @@ from api.db_router import READ_REPLICA_ALIAS
from api.db_utils import rls_transaction
from api.models import Provider, StatusChoices
from api.utils import initialize_prowler_provider
from prowler.lib.check.compliance_models import Compliance
from prowler.lib.check.compliance_models import (
Compliance,
get_bulk_compliance_frameworks_universal,
)
from prowler.lib.outputs.finding import Finding as FindingOutput
from .components import (
@@ -222,6 +226,46 @@ def get_requirement_metadata(
return None
def _universal_attributes_to_list(attributes) -> list:
"""Flatten a universal requirement's ``attributes`` into a list of objects
with attribute access. MITRE wraps its list under ``_raw_attributes``."""
if isinstance(attributes, dict) and "_raw_attributes" in attributes:
entries = attributes.get("_raw_attributes") or []
return [
SimpleNamespace(**entry) for entry in entries if isinstance(entry, dict)
]
if isinstance(attributes, dict):
return [SimpleNamespace(**attributes)] if attributes else []
return list(attributes or [])
def _adapt_universal_to_legacy(framework, provider_type: str) -> SimpleNamespace:
"""Expose a universal ``ComplianceFramework`` under the legacy ``Compliance``
attribute names used by the PDF pipeline."""
provider_key = (provider_type or "").lower()
requirements = []
for requirement in framework.requirements:
checks_by_provider = (
requirement.checks if isinstance(requirement.checks, dict) else {}
)
requirements.append(
SimpleNamespace(
Id=requirement.id,
Description=requirement.description or "",
Checks=list(checks_by_provider.get(provider_key, [])),
Attributes=_universal_attributes_to_list(requirement.attributes),
)
)
return SimpleNamespace(
Framework=framework.framework,
Name=framework.name,
Version=framework.version or "",
Description=framework.description or "",
Provider=framework.provider or provider_type,
Requirements=requirements,
)
# =============================================================================
# PDF Styles Cache
# =============================================================================
@@ -869,9 +913,18 @@ class BaseComplianceReportGenerator(ABC):
prowler_provider = initialize_prowler_provider(provider_obj)
provider_type = provider_obj.provider
# Load compliance framework
frameworks_bulk = Compliance.get_bulk(provider_type)
compliance_obj = frameworks_bulk.get(compliance_id)
# Load compliance framework — fall back to the universal loader
# for top-level JSONs (e.g. csa_ccm_4.0) that Compliance.get_bulk
# does not scan.
compliance_obj = Compliance.get_bulk(provider_type).get(compliance_id)
if not compliance_obj:
universal_framework = get_bulk_compliance_frameworks_universal(
provider_type
).get(compliance_id)
if universal_framework:
compliance_obj = _adapt_universal_to_legacy(
universal_framework, provider_type
)
if not compliance_obj:
raise ValueError(f"Compliance framework not found: {compliance_id}")
+27 -22
View File
@@ -359,35 +359,40 @@ def _load_findings_for_requirement_checks(
def _get_compliance_check_ids(compliance_obj) -> set[str]:
"""Return the union of all check_ids referenced by a compliance framework.
Used by the master report orchestrator to know which checks each
framework consumes from the shared ``findings_cache``, so that once a
framework finishes the entries no other pending framework needs can be
evicted from the cache (PROWLER-1733).
Used by the master report orchestrator to evict entries from
``findings_cache`` once no pending framework needs them (PROWLER-1733).
Args:
compliance_obj: A loaded Compliance framework object exposing a
``Requirements`` iterable, each requirement carrying ``Checks``.
``None`` is treated as "no checks" rather than raising, so the
caller can pass ``frameworks_bulk.get(...)`` directly without
an extra existence check.
Returns:
Set of check_id strings (empty if ``compliance_obj`` is ``None``).
Accepts the legacy ``Compliance`` shape (``Requirements`` / ``Checks``
lists) and the universal ``ComplianceFramework`` shape (``requirements``
/ ``checks`` dict keyed by provider). ``None`` returns an empty set so
callers can pass ``frameworks_bulk.get(...)`` directly.
"""
if compliance_obj is None:
return set()
checks: set[str] = set()
requirements = getattr(compliance_obj, "Requirements", None) or []
requirements = getattr(compliance_obj, "Requirements", None) or getattr(
compliance_obj, "requirements", None
)
if not requirements:
return set()
check_ids: set[str] = set()
try:
# Defensive: Mock objects (used in unit tests) return another Mock
# for any attribute access, which is truthy but not iterable. Treat
# any non-iterable Requirements value as "no checks".
for req in requirements:
req_checks = getattr(req, "Checks", None) or []
# Mock objects in unit tests return another Mock for any attribute
# access — truthy but not iterable. Treat that as "no checks".
for requirement in requirements:
requirement_checks = getattr(requirement, "Checks", None)
if requirement_checks is None:
checks_by_provider = getattr(requirement, "checks", None) or {}
requirement_checks = [
check_id
for check_ids_list in checks_by_provider.values()
for check_id in check_ids_list
]
try:
checks.update(req_checks)
check_ids.update(requirement_checks)
except TypeError:
continue
except TypeError:
return set()
return checks
return check_ids
+43 -2
View File
@@ -68,7 +68,10 @@ from tasks.utils import (
get_next_execution_datetime,
)
from api.compliance import get_compliance_frameworks
from api.compliance import (
get_compliance_frameworks,
get_prowler_provider_compliance,
)
from api.db_router import READ_REPLICA_ALIAS
from api.db_utils import delete_related_daily_task, rls_transaction
from api.decorators import handle_provider_deletion, set_tenant
@@ -76,6 +79,9 @@ from api.models import Finding, Integration, Provider, Scan, ScanSummary, StateC
from api.utils import initialize_prowler_provider
from api.v1.serializers import ScanTaskSerializer
from prowler.lib.check.compliance_models import Compliance
from prowler.lib.outputs.compliance.compliance import (
process_universal_compliance_frameworks,
)
from prowler.lib.outputs.compliance.generic.generic import GenericCompliance
from prowler.lib.outputs.finding import Finding as FindingOutput
@@ -543,7 +549,16 @@ def generate_outputs_task(scan_id: str, provider_id: str, tenant_id: str):
provider_uid = provider_obj.uid
provider_type = provider_obj.provider
# Per-framework exporters in `COMPLIANCE_CLASS_MAP` consume the legacy bulk.
frameworks_bulk = Compliance.get_bulk(provider_type)
# Universal-only frameworks (top-level JSONs like `dora.json`) are emitted
# via `process_universal_compliance_frameworks` below.
universal_bulk = get_prowler_provider_compliance(provider_type)
universal_only_names = {
name
for name in universal_bulk
if name not in frameworks_bulk and universal_bulk[name].outputs
}
frameworks_avail = get_compliance_frameworks(provider_type)
out_dir, comp_dir = _generate_output_directory(
DJANGO_TMP_OUTPUT_DIRECTORY, provider_uid, tenant_id, scan_id
@@ -568,6 +583,10 @@ def generate_outputs_task(scan_id: str, provider_id: str, tenant_id: str):
output_writers = {}
compliance_writers = {}
# Shared across batches so universal writers are created once and reused.
universal_compliance_state: dict[str, list] = {"compliance": []}
universal_base_dir = os.path.dirname(out_dir)
universal_output_filename = os.path.basename(out_dir)
scan_summary = FindingOutput._transform_findings_stats(
ScanSummary.objects.filter(scan_id=scan_id)
@@ -622,8 +641,30 @@ def generate_outputs_task(scan_id: str, provider_id: str, tenant_id: str):
writer.batch_write_data_to_file(**extra)
writer._data.clear()
# Compliance CSVs
# Universal-only frameworks (e.g. `dora.json`).
if universal_only_names:
process_universal_compliance_frameworks(
input_compliance_frameworks=universal_only_names,
universal_frameworks=universal_bulk,
finding_outputs=fos,
output_directory=universal_base_dir,
output_filename=universal_output_filename,
provider=provider_type,
generated_outputs=universal_compliance_state,
from_cli=False,
is_last=is_last,
)
# Compliance CSVs (per-framework exporters).
for name in frameworks_avail:
if name in universal_only_names:
continue
if name not in frameworks_bulk:
logger.warning(
"Compliance framework '%s' missing from bulk; skipping CSV export",
name,
)
continue
compliance_obj = frameworks_bulk[name]
klass = GenericCompliance
@@ -80,7 +80,7 @@ def basic_csa_compliance_data():
tenant_id="tenant-123",
scan_id="scan-456",
provider_id="provider-789",
compliance_id="csa_ccm_4.0_aws",
compliance_id="csa_ccm_4.0",
framework="CSA-CCM",
name="CSA Cloud Controls Matrix v4.0",
version="4.0",
+10
View File
@@ -323,6 +323,7 @@ class TestGenerateOutputs:
mock_transformed_stats = {"some": "stats"}
with (
patch("tasks.tasks.get_prowler_provider_compliance", return_value={}),
patch(
"tasks.tasks.FindingOutput._transform_findings_stats",
return_value=mock_transformed_stats,
@@ -441,6 +442,7 @@ class TestGenerateOutputs:
mock_provider.uid = "test-provider-uid"
with (
patch("tasks.tasks.get_prowler_provider_compliance", return_value={}),
patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
patch("tasks.tasks.Provider.objects.get", return_value=mock_provider),
patch("tasks.tasks.initialize_prowler_provider"),
@@ -596,6 +598,7 @@ class TestGenerateOutputs:
]
with (
patch("tasks.tasks.get_prowler_provider_compliance", return_value={}),
patch("tasks.tasks.ScanSummary.objects.filter") as mock_summary,
patch(
"tasks.tasks.Provider.objects.get",
@@ -670,6 +673,7 @@ class TestGenerateOutputs:
mock_provider.uid = "test-provider-uid"
with (
patch("tasks.tasks.get_prowler_provider_compliance", return_value={}),
patch("tasks.tasks.ScanSummary.objects.filter") as mock_filter,
patch("tasks.tasks.Provider.objects.get", return_value=mock_provider),
patch("tasks.tasks.initialize_prowler_provider"),
@@ -1113,6 +1117,7 @@ class TestCheckIntegrationsTask:
enabled=True,
)
@patch("tasks.tasks.get_prowler_provider_compliance", return_value={})
@patch("tasks.tasks.s3_integration_task")
@patch("tasks.tasks.Integration.objects.filter")
@patch("tasks.tasks.ScanSummary.objects.filter")
@@ -1145,6 +1150,7 @@ class TestCheckIntegrationsTask:
mock_scan_summary,
mock_integration_filter,
mock_s3_task,
mock_get_prowler_compliance,
):
"""Test that ASFF output is generated for AWS providers with SecurityHub integration."""
# Setup
@@ -1241,6 +1247,7 @@ class TestCheckIntegrationsTask:
assert result == {"upload": True}
@patch("tasks.tasks.get_prowler_provider_compliance", return_value={})
@patch("tasks.tasks.s3_integration_task")
@patch("tasks.tasks.Integration.objects.filter")
@patch("tasks.tasks.ScanSummary.objects.filter")
@@ -1273,6 +1280,7 @@ class TestCheckIntegrationsTask:
mock_scan_summary,
mock_integration_filter,
mock_s3_task,
mock_get_prowler_compliance,
):
"""Test that ASFF output is NOT generated for AWS providers without SecurityHub integration."""
# Setup
@@ -1366,6 +1374,7 @@ class TestCheckIntegrationsTask:
assert result == {"upload": True}
@patch("tasks.tasks.get_prowler_provider_compliance", return_value={})
@patch("tasks.tasks.ScanSummary.objects.filter")
@patch("tasks.tasks.Provider.objects.get")
@patch("tasks.tasks.initialize_prowler_provider")
@@ -1394,6 +1403,7 @@ class TestCheckIntegrationsTask:
mock_initialize_provider,
mock_provider_get,
mock_scan_summary,
mock_get_prowler_compliance,
):
"""Test that ASFF output is NOT generated for non-AWS providers (e.g., Azure, GCP)."""
# Setup