feat(integrations): implement AWS Security Hub integration (#8365)

This commit is contained in:
Adrián Jesús Peña Rodríguez authored and GitHub committed 2025-08-25 15:53:48 +02:00
1 parent d457166a0c
commit 83242da0ab
15 files changed
+1670 -104

No files matched your search

+269 -1
View File
@@ -2,15 +2,21 @@ import os
from glob import glob
from celery.utils.log import get_task_logger
from config.django.base import DJANGO_FINDINGS_BATCH_SIZE
from tasks.utils import batched
from api.db_utils import rls_transaction
from api.models import Integration
from api.models import Finding, Integration, Provider
from api.utils import initialize_prowler_provider
from prowler.lib.outputs.asff.asff import ASFF
from prowler.lib.outputs.compliance.generic.generic import GenericCompliance
from prowler.lib.outputs.csv.csv import CSV
from prowler.lib.outputs.finding import Finding as FindingOutput
from prowler.lib.outputs.html.html import HTML
from prowler.lib.outputs.ocsf.ocsf import OCSF
from prowler.providers.aws.aws_provider import AwsProvider
from prowler.providers.aws.lib.s3.s3 import S3
from prowler.providers.aws.lib.security_hub.security_hub import SecurityHub
from prowler.providers.common.models import Connection
logger = get_task_logger(__name__)
@@ -154,3 +160,265 @@ def upload_s3_integration(
except Exception as e:
logger.error(f"S3 integrations failed for provider {provider_id}: {str(e)}")
return False
def get_security_hub_client_from_integration(
integration: Integration, tenant_id: str, findings: list
) -> tuple[bool, SecurityHub | Connection]:
"""
Create and return a SecurityHub client using AWS credentials from an integration.
Args:
integration (Integration): The integration to get the Security Hub client from.
tenant_id (str): The tenant identifier.
findings (list): List of findings in ASFF format to send to Security Hub.
Returns:
tuple[bool, SecurityHub | Connection]: A tuple containing a boolean indicating
if the connection was successful and the SecurityHub client or connection object.
"""
# Get the provider associated with this integration
with rls_transaction(tenant_id):
provider_relationship = integration.integrationproviderrelationship_set.first()
if not provider_relationship:
return Connection(
is_connected=False, error="No provider associated with this integration"
)
provider_uid = provider_relationship.provider.uid
provider_secret = provider_relationship.provider.secret.secret
credentials = (
integration.credentials if integration.credentials else provider_secret
)
connection = SecurityHub.test_connection(
aws_account_id=provider_uid,
raise_on_exception=False,
**credentials,
)
if connection.is_connected:
all_security_hub_regions = AwsProvider.get_available_aws_service_regions(
"securityhub", connection.partition
)
# Create regions status dictionary
regions_status = {}
for region in set(all_security_hub_regions):
regions_status[region] = region in connection.enabled_regions
# Save regions information in the integration configuration
with rls_transaction(tenant_id):
integration.configuration["regions"] = regions_status
integration.save()
# Create SecurityHub client with all necessary parameters
security_hub = SecurityHub(
aws_account_id=provider_uid,
findings=findings,
send_only_fails=integration.configuration.get("send_only_fails", False),
aws_security_hub_available_regions=list(connection.enabled_regions),
**credentials,
)
return True, security_hub
return False, connection
def upload_security_hub_integration(
tenant_id: str, provider_id: str, scan_id: str
) -> bool:
"""
Upload findings to AWS Security Hub using configured integrations.
This function retrieves findings from the database, transforms them to ASFF format,
and sends them to AWS Security Hub using the configured integration credentials.
Args:
tenant_id (str): The tenant identifier.
provider_id (str): The provider identifier.
scan_id (str): The scan identifier for which to send findings.
Returns:
bool: True if all integrations executed successfully, False otherwise.
"""
logger.info(f"Processing Security Hub integrations for provider {provider_id}")
try:
with rls_transaction(tenant_id):
# Get Security Hub integrations for this provider
integrations = list(
Integration.objects.filter(
integrationproviderrelationship__provider_id=provider_id,
integration_type=Integration.IntegrationChoices.AWS_SECURITY_HUB,
enabled=True,
)
)
if not integrations:
logger.error(
f"No Security Hub integrations found for provider {provider_id}"
)
return False
# Get the provider object
provider = Provider.objects.get(id=provider_id)
# Initialize prowler provider for finding transformation
prowler_provider = initialize_prowler_provider(provider)
# Process each Security Hub integration
integration_executions = 0
total_findings_sent = {} # Track findings sent per integration
for integration in integrations:
try:
# Initialize Security Hub client for this integration
# We'll create the client once and reuse it for all batches
security_hub_client = None
send_only_fails = integration.configuration.get(
"send_only_fails", False
)
total_findings_sent[integration.id] = 0
# Process findings in batches to avoid memory issues
has_findings = False
batch_number = 0
with rls_transaction(tenant_id):
qs = (
Finding.all_objects.filter(tenant_id=tenant_id, scan_id=scan_id)
.order_by("uid")
.iterator()
)
for batch, _ in batched(qs, DJANGO_FINDINGS_BATCH_SIZE):
batch_number += 1
has_findings = True
# Transform findings for this batch
transformed_findings = [
FindingOutput.transform_api_finding(
finding, prowler_provider
)
for finding in batch
]
# Convert to ASFF format
asff_transformer = ASFF(
findings=transformed_findings,
file_path="",
file_extension="json",
)
asff_transformer.transform(transformed_findings)
# Get the batch of ASFF findings
batch_asff_findings = asff_transformer.data
if batch_asff_findings:
# Create Security Hub client for first batch or reuse existing
if not security_hub_client:
connected, security_hub = (
get_security_hub_client_from_integration(
integration, tenant_id, batch_asff_findings
)
)
if not connected:
logger.error(
f"Security Hub connection failed for integration {integration.id}: {security_hub.error}"
)
integration.connected = False
integration.save()
break # Skip this integration
security_hub_client = security_hub
logger.info(
f"Sending {'fail' if send_only_fails else 'all'} findings to Security Hub via integration {integration.id}"
)
else:
# Update findings in existing client for this batch
security_hub_client._findings_per_region = (
security_hub_client.filter(
batch_asff_findings, send_only_fails
)
)
# Send this batch to Security Hub
try:
findings_sent = (
security_hub_client.batch_send_to_security_hub()
)
total_findings_sent[integration.id] += findings_sent
if findings_sent > 0:
logger.debug(
f"Sent batch {batch_number} with {findings_sent} findings to Security Hub"
)
except Exception as batch_error:
logger.error(
f"Failed to send batch {batch_number} to Security Hub: {str(batch_error)}"
)
# Clear memory after processing each batch
asff_transformer._data.clear()
del batch_asff_findings
del transformed_findings
if not has_findings:
logger.info(
f"No findings to send to Security Hub for scan {scan_id}"
)
integration_executions += 1
elif security_hub_client:
if total_findings_sent[integration.id] > 0:
logger.info(
f"Successfully sent {total_findings_sent[integration.id]} total findings to Security Hub via integration {integration.id}"
)
integration_executions += 1
else:
logger.warning(
f"No findings were sent to Security Hub via integration {integration.id}"
)
# Archive previous findings if configured to do so
if integration.configuration.get(
"archive_previous_findings", False
):
logger.info(
f"Archiving previous findings in Security Hub via integration {integration.id}"
)
try:
findings_archived = (
security_hub_client.archive_previous_findings()
)
logger.info(
f"Successfully archived {findings_archived} previous findings in Security Hub"
)
except Exception as archive_error:
logger.warning(
f"Failed to archive previous findings: {str(archive_error)}"
)
except Exception as e:
logger.error(
f"Security Hub integration {integration.id} failed: {str(e)}"
)
continue
result = integration_executions == len(integrations)
if result:
logger.info(
f"All Security Hub integrations completed successfully for provider {provider_id}"
)
else:
logger.error(
f"Some Security Hub integrations failed for provider {provider_id}"
)
return result
except Exception as e:
logger.error(
f"Security Hub integrations failed for provider {provider_id}: {str(e)}"
)
return False
+44 -4
View File
@@ -21,7 +21,10 @@ from tasks.jobs.export import (
_generate_output_directory,
_upload_to_s3,
)
from tasks.jobs.integrations import upload_s3_integration
from tasks.jobs.integrations import (
upload_s3_integration,
upload_security_hub_integration,
)
from tasks.jobs.scan import (
aggregate_findings,
create_compliance_requirements,
@@ -62,6 +65,7 @@ def _perform_scan_complete_tasks(tenant_id: str, scan_id: str, provider_id: str)
check_integrations_task.si(
tenant_id=tenant_id,
provider_id=provider_id,
scan_id=scan_id,
),
).apply_async()
@@ -323,7 +327,11 @@ def generate_outputs_task(scan_id: str, provider_id: str, tenant_id: str):
ScanSummary.objects.filter(scan_id=scan_id)
)
qs = Finding.all_objects.filter(scan_id=scan_id).order_by("uid").iterator()
qs = (
Finding.all_objects.filter(tenant_id=tenant_id, scan_id=scan_id)
.order_by("uid")
.iterator()
)
for batch, is_last in batched(qs, DJANGO_FINDINGS_BATCH_SIZE):
fos = [FindingOutput.transform_api_finding(f, prowler_provider) for f in batch]
@@ -474,17 +482,19 @@ def check_lighthouse_connection_task(lighthouse_config_id: str, tenant_id: str =
@shared_task(name="integration-check")
def check_integrations_task(tenant_id: str, provider_id: str):
def check_integrations_task(tenant_id: str, provider_id: str, scan_id: str = None):
"""
Check and execute all configured integrations for a provider.
Args:
tenant_id (str): The tenant identifier
provider_id (str): The provider identifier
scan_id (str, optional): The scan identifier for integrations that need scan data
"""
logger.info(f"Checking integrations for provider {provider_id}")
try:
integration_tasks = []
with rls_transaction(tenant_id):
integrations = Integration.objects.filter(
integrationproviderrelationship__provider_id=provider_id,
@@ -495,7 +505,16 @@ def check_integrations_task(tenant_id: str, provider_id: str):
logger.info(f"No integrations configured for provider {provider_id}")
return {"integrations_processed": 0}
integration_tasks = []
# Security Hub integration
security_hub_integrations = integrations.filter(
integration_type=Integration.IntegrationChoices.AWS_SECURITY_HUB
)
if security_hub_integrations.exists():
integration_tasks.append(
security_hub_integration_task.s(
tenant_id=tenant_id, provider_id=provider_id, scan_id=scan_id
)
)
# TODO: Add other integration types here
# slack_integrations = integrations.filter(
@@ -541,3 +560,24 @@ def s3_integration_task(
output_directory (str): Path to the directory containing output files
"""
return upload_s3_integration(tenant_id, provider_id, output_directory)
@shared_task(
base=RLSTask,
name="integration-security-hub",
queue="integrations",
)
def security_hub_integration_task(
tenant_id: str,
provider_id: str,
scan_id: str,
):
"""
Process Security Hub integrations for a provider.
Args:
tenant_id (str): The tenant identifier
provider_id (str): The provider identifier
scan_id (str): The scan identifier
"""
return upload_security_hub_integration(tenant_id, provider_id, scan_id)
File diff suppressed because it is too large. Load diff
+77 -9
View File
@@ -7,6 +7,7 @@ from tasks.tasks import (
check_integrations_task,
generate_outputs_task,
s3_integration_task,
security_hub_integration_task,
)
from api.models import Integration
@@ -521,31 +522,68 @@ class TestCheckIntegrationsTask:
enabled=True,
)
@patch("tasks.tasks.security_hub_integration_task")
@patch("tasks.tasks.group")
@patch("tasks.tasks.rls_transaction")
@patch("tasks.tasks.Integration.objects.filter")
def test_check_integrations_s3_success(
self, mock_integration_filter, mock_rls, mock_group
def test_check_integrations_security_hub_success(
self, mock_integration_filter, mock_rls, mock_group, mock_security_hub_task
):
# Mock that we have some integrations
mock_integration_filter.return_value.exists.return_value = True
"""Test that SecurityHub integrations are processed correctly."""
# Mock that we have SecurityHub integrations
mock_integrations = MagicMock()
mock_integrations.exists.return_value = True
# Mock SecurityHub integrations to return existing integrations
mock_security_hub_integrations = MagicMock()
mock_security_hub_integrations.exists.return_value = True
# Set up the filter chain
mock_integration_filter.return_value = mock_integrations
mock_integrations.filter.return_value = mock_security_hub_integrations
# Mock the task signature
mock_task_signature = MagicMock()
mock_security_hub_task.s.return_value = mock_task_signature
# Mock group job
mock_job = MagicMock()
mock_group.return_value = mock_job
# Ensure rls_transaction is mocked
mock_rls.return_value.__enter__.return_value = None
# Since the current implementation doesn't actually create tasks yet (TODO comment),
# we test that no tasks are created but the function returns the correct count
# Execute the function
result = check_integrations_task(
tenant_id=self.tenant_id,
provider_id=self.provider_id,
scan_id="test-scan-id",
)
assert result == {"integrations_processed": 0}
# Should process 1 SecurityHub integration
assert result == {"integrations_processed": 1}
# Verify the integration filter was called
mock_integration_filter.assert_called_once_with(
integrationproviderrelationship__provider_id=self.provider_id,
enabled=True,
)
# group should not be called since no integration tasks are created yet
mock_group.assert_not_called()
# Verify SecurityHub integrations were filtered
mock_integrations.filter.assert_called_once_with(
integration_type=Integration.IntegrationChoices.AWS_SECURITY_HUB
)
# Verify SecurityHub task was created with correct parameters
mock_security_hub_task.s.assert_called_once_with(
tenant_id=self.tenant_id,
provider_id=self.provider_id,
scan_id="test-scan-id",
)
# Verify group was called and job was executed
mock_group.assert_called_once_with([mock_task_signature])
mock_job.apply_async.assert_called_once()
@patch("tasks.tasks.rls_transaction")
@patch("tasks.tasks.Integration.objects.filter")
@@ -598,3 +636,33 @@ class TestCheckIntegrationsTask:
mock_upload.assert_called_once_with(
self.tenant_id, self.provider_id, output_directory
)
@patch("tasks.tasks.upload_security_hub_integration")
def test_security_hub_integration_task_success(self, mock_upload):
"""Test successful SecurityHub integration task execution."""
mock_upload.return_value = True
scan_id = "test-scan-123"
result = security_hub_integration_task(
tenant_id=self.tenant_id,
provider_id=self.provider_id,
scan_id=scan_id,
)
assert result is True
mock_upload.assert_called_once_with(self.tenant_id, self.provider_id, scan_id)
@patch("tasks.tasks.upload_security_hub_integration")
def test_security_hub_integration_task_failure(self, mock_upload):
"""Test SecurityHub integration task handling failure."""
mock_upload.return_value = False
scan_id = "test-scan-123"
result = security_hub_integration_task(
tenant_id=self.tenant_id,
provider_id=self.provider_id,
scan_id=scan_id,
)
assert result is False
mock_upload.assert_called_once_with(self.tenant_id, self.provider_id, scan_id)