feat(datasync): add datasync service and check datasync_task_logging_enabled (#5444)

This commit is contained in:
Adrián Jesús Peña Rodríguez
2024-10-17 19:07:18 +02:00
committed by GitHub
parent 12abea371d
commit 26a00a14df
8 changed files with 520 additions and 0 deletions
@@ -0,0 +1,4 @@
from prowler.providers.aws.services.datasync.datasync_service import DataSync
from prowler.providers.common.provider import Provider
datasync_client = DataSync(Provider.get_global_provider())
@@ -0,0 +1,118 @@
from typing import Dict, List, Optional
from botocore.exceptions import ClientError
from pydantic import BaseModel, Field
from prowler.lib.logger import logger
from prowler.lib.scan_filters.scan_filters import is_resource_filtered
from prowler.providers.aws.lib.service.service import AWSService
class DataSync(AWSService):
"""AWS DataSync service class to list tasks, describe them, and list their tags."""
def __init__(self, provider):
"""Initialize the DataSync service.
Args:
provider: The AWS provider instance.
"""
super().__init__(__class__.__name__, provider)
self.tasks = {}
self.__threading_call__(self._list_tasks)
self.__threading_call__(self._describe_tasks, self.tasks.values())
self.__threading_call__(self._list_task_tags, self.tasks.values())
def _list_tasks(self, regional_client):
"""List DataSync tasks in the given region.
Args:
regional_client: The regional AWS client.
"""
logger.info("DataSync - Listing tasks...")
try:
list_tasks_paginator = regional_client.get_paginator("list_tasks")
for page in list_tasks_paginator.paginate():
for task in page.get("Tasks", []):
task_arn = task["TaskArn"]
task_id = task_arn.split("/")[-1]
if not self.audit_resources or (
is_resource_filtered(task_arn, self.audit_resources)
):
self.tasks[task_arn] = DataSyncTask(
id=task_id,
arn=task_arn,
name=task.get("Name"),
region=regional_client.region,
)
except Exception as error:
logger.error(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
def _describe_tasks(self, task):
"""Describe each DataSync task and update task details."""
logger.info("DataSync - Describing tasks...")
try:
regional_client = self.regional_clients[task.region]
response = regional_client.describe_task(TaskArn=task.arn)
task.status = response.get("Status")
task.options = response.get("Options")
task.source_location_arn = response.get("SourceLocationArn")
task.destination_location_arn = response.get("DestinationLocationArn")
task.excludes = response.get("Excludes")
task.schedule = response.get("Schedule")
task.cloudwatch_log_group_arn = response.get("CloudWatchLogGroupArn")
except ClientError as error:
if error.response["Error"]["Code"] == "ResourceNotFoundException":
logger.warning(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
else:
logger.error(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
except Exception as error:
logger.error(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
def _list_task_tags(self, task):
"""List tags for each DataSync task."""
logger.info("DataSync - Listing task tags...")
try:
regional_client = self.regional_clients[task.region]
response = regional_client.list_tags_for_resource(ResourceArn=task.arn)
task.tags = response.get("Tags", [])
except ClientError as error:
if error.response["Error"]["Code"] == "ResourceNotFoundException":
logger.warning(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
else:
logger.error(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
except Exception as error:
logger.error(
f"{regional_client.region} -- {error.__class__.__name__}[{error.__traceback__.tb_lineno}]: {error}"
)
class DataSyncTask(BaseModel):
id: str
name: Optional[str] = None
arn: str
region: str
status: Optional[str] = None
options: Optional[Dict] = None
source_location_arn: Optional[str] = None
destination_location_arn: Optional[str] = None
excludes: Optional[List] = None
schedule: Optional[Dict] = None
cloudwatch_log_group_arn: Optional[str] = None
tags: List[Dict] = Field(default_factory=list)
@@ -0,0 +1,34 @@
{
"Provider": "aws",
"CheckID": "datasync_task_logging_enabled",
"CheckTitle": "DataSync tasks should have logging enabled",
"CheckType": [
"Software and Configuration Checks/AWS Security Best Practices"
],
"ServiceName": "datasync",
"SubServiceName": "",
"ResourceIdTemplate": "arn:aws:datasync:{region}:{account-id}:task/{task-id}",
"Severity": "high",
"ResourceType": "AwsDataSyncTask",
"Description": "This control checks if AWS DataSync tasks have logging enabled. The control fails if the task doesn't have the CloudWatchLogGroupArn property defined.",
"Risk": "Without logging enabled, important operational data may be lost, making it difficult to troubleshoot issues, monitor performance, and ensure compliance with auditing requirements.",
"RelatedUrl": "https://docs.aws.amazon.com/datasync/latest/userguide/monitor-datasync.html#enable-logging",
"Remediation": {
"Code": {
"CLI": "aws datasync update-task --task-arn <task-arn> --cloud-watch-log-group-arn <log-group-arn>",
"NativeIaC": "",
"Other": "https://docs.aws.amazon.com/datasync/latest/userguide/monitor-datasync.html#enable-logging",
"Terraform": ""
},
"Recommendation": {
"Text": "Configure logging for your DataSync tasks to ensure that operational data is captured and available for debugging, monitoring, and auditing purposes.",
"Url": "https://docs.aws.amazon.com/datasync/latest/userguide/monitor-datasync.html#enable-logging"
}
},
"Categories": [
"logging"
],
"DependsOn": [],
"RelatedTo": [],
"Notes": ""
}
@@ -0,0 +1,40 @@
from typing import List
from prowler.lib.check.models import Check, Check_Report_AWS
from prowler.providers.aws.services.datasync.datasync_client import datasync_client
class datasync_task_logging_enabled(Check):
"""Check if AWS DataSync tasks have logging enabled.
This class verifies whether each AWS DataSync task has logging enabled by checking
for the presence of a CloudWatch Log Group ARN in the task's configuration.
"""
def execute(self) -> List[Check_Report_AWS]:
"""Execute the DataSync tasks logging enabled check.
Iterates over all DataSync tasks and generates a report indicating whether
each task has logging enabled.
Returns:
List[Check_Report_AWS]: A list of report objects with the results of the check.
"""
findings = []
for task in datasync_client.tasks.values():
report = Check_Report_AWS(self.metadata())
report.region = task.region
report.resource_id = task.id
report.resource_arn = task.arn
report.resource_tags = task.tags
report.status = "PASS"
report.status_extended = f"DataSync task {task.name} has logging enabled."
if not task.cloudwatch_log_group_arn:
report.status = "FAIL"
report.status_extended = (
f"DataSync task {task.name} does not have logging enabled."
)
findings.append(report)
return findings
@@ -0,0 +1,197 @@
from unittest.mock import MagicMock, patch
import botocore
from botocore.exceptions import ClientError
from prowler.providers.aws.services.datasync.datasync_service import DataSync
from tests.providers.aws.utils import AWS_REGION_EU_WEST_1, set_mocked_aws_provider
make_api_call = botocore.client.BaseClient._make_api_call
def mock_make_api_call(self, operation_name, kwarg):
# Simulate ResourceNotFoundException for specific ARNs
if operation_name in ["DescribeTask", "ListTagsForResource"]:
if "not-found" in kwarg.get("TaskArn", "") or "not-found" in kwarg.get(
"ResourceArn", ""
):
raise ClientError(
{
"Error": {
"Code": "ResourceNotFoundException",
"Message": "Resource not found",
}
},
operation_name,
)
# Simulate other ClientError
if "client-error" in kwarg.get("TaskArn", "") or "client-error" in kwarg.get(
"ResourceArn", ""
):
raise ClientError(
{
"Error": {
"Code": "InternalServerError",
"Message": "Internal server error",
}
},
operation_name,
)
# Simulate generic exception
if "generic-error" in kwarg.get("TaskArn", "") or "generic-error" in kwarg.get(
"ResourceArn", ""
):
raise Exception("Generic error")
if operation_name == "ListTasks":
if kwarg.get("generic_error", False):
raise Exception("Generic error in ListTasks")
return {
"Tasks": [
{
"TaskArn": "arn:aws:datasync:eu-west-1:123456789012:task/task-12345678901234567",
"Name": "test_task",
},
{
"TaskArn": "arn:aws:datasync:eu-west-1:123456789012:task/not-found",
"Name": "not_found_task",
},
{
"TaskArn": "arn:aws:datasync:eu-west-1:123456789012:task/client-error",
"Name": "client_error_task",
},
{
"TaskArn": "arn:aws:datasync:eu-west-1:123456789012:task/generic-error",
"Name": "generic_error_task",
},
]
}
if operation_name == "DescribeTask":
return {
"TaskArn": kwarg["TaskArn"],
"Status": "AVAILABLE",
"Name": "test_task",
"CurrentTaskExecutionArn": "arn:aws:datasync:eu-west-1:123456789012:task/task-12345678901234567/execution/exec-12345678901234567",
"Options": {},
"SourceLocationArn": "arn:aws:datasync:eu-west-1:123456789012:location/loc-12345678901234567",
"DestinationLocationArn": "arn:aws:datasync:eu-west-1:123456789012:location/loc-76543210987654321",
"CloudWatchLogGroupArn": "arn:aws:logs:eu-west-1:123456789012:log-group:/aws/datasync/log-group",
"Tags": [
{"Key": "Name", "Value": "test_task"},
],
}
if operation_name == "ListTagsForResource":
return {
"Tags": [
{"Key": "Name", "Value": "test_task"},
],
}
return make_api_call(self, operation_name, kwarg)
def mock_generate_regional_clients(provider, service):
regional_client = provider._session.current_session.client(
service, region_name=AWS_REGION_EU_WEST_1
)
regional_client.region = AWS_REGION_EU_WEST_1
return {AWS_REGION_EU_WEST_1: regional_client}
@patch(
"prowler.providers.aws.aws_provider.AwsProvider.generate_regional_clients",
new=mock_generate_regional_clients,
)
class Test_DataSync_Service:
# Test DataSync Service initialization
def test_service(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
assert datasync.service == "datasync"
# Test DataSync clients creation
def test_client(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
for reg_client in datasync.regional_clients.values():
assert reg_client.__class__.__name__ == "DataSync"
# Test DataSync session
def test__get_session__(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
assert datasync.session.__class__.__name__ == "Session"
# Test listing DataSync tasks
@patch("botocore.client.BaseClient._make_api_call", new=mock_make_api_call)
def test_list_tasks(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
task_arn = "arn:aws:datasync:eu-west-1:123456789012:task/task-12345678901234567"
found_task = None
for task in datasync.tasks.values():
if task.arn == task_arn:
found_task = task
break
assert found_task
assert found_task.name == "test_task"
assert found_task.region == AWS_REGION_EU_WEST_1
# Test generic exception in list_tasks
def test_list_tasks_generic_exception(self):
aws_provider = set_mocked_aws_provider()
# Mock the regional client's list_tasks method specifically
mock_client = MagicMock()
mock_client.region = AWS_REGION_EU_WEST_1
mock_client.get_paginator.side_effect = Exception("Generic error in ListTasks")
datasync = DataSync(aws_provider)
assert len(datasync.tasks.values()) == 0
# Test describing DataSync tasks with various exceptions
@patch("botocore.client.BaseClient._make_api_call", new=mock_make_api_call)
def test_describe_tasks_with_exceptions(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
# Check all tasks were processed despite exceptions
assert len(datasync.tasks.values()) == 4
# Verify each task type
tasks_by_name = {task.name: task for task in datasync.tasks.values()}
# Normal task
assert "test_task" in tasks_by_name
assert tasks_by_name["test_task"].status == "AVAILABLE"
# ResourceNotFoundException task
assert "not_found_task" in tasks_by_name
assert not tasks_by_name["not_found_task"].status
# ClientError task
assert "client_error_task" in tasks_by_name
assert not tasks_by_name["client_error_task"].status
# Generic error task
assert "generic_error_task" in tasks_by_name
assert not tasks_by_name["generic_error_task"].status
# Test listing task tags with various exceptions
@patch("botocore.client.BaseClient._make_api_call", new=mock_make_api_call)
def test_list_task_tags_with_exceptions(self):
aws_provider = set_mocked_aws_provider()
datasync = DataSync(aws_provider)
tasks_by_name = {task.name: task for task in datasync.tasks.values()}
assert tasks_by_name["test_task"].tags == [
{"Key": "Name", "Value": "test_task"}
]
# Tasks with exceptions should have empty tag lists
assert tasks_by_name["not_found_task"].tags == []
assert tasks_by_name["client_error_task"].tags == []
assert tasks_by_name["generic_error_task"].tags == []
@@ -0,0 +1,127 @@
from unittest.mock import patch
from tests.providers.aws.utils import AWS_REGION_US_EAST_1, set_mocked_aws_provider
TASK_ID = "task-12345"
TASK_ARN = f"arn:aws:datasync:{AWS_REGION_US_EAST_1}:123456789012:task/{TASK_ID}"
class Test_datasync_task_logging_enabled:
def test_no_tasks(self):
from prowler.providers.aws.services.datasync.datasync_service import DataSync
# Set up a mocked AWS provider
mocked_aws_provider = set_mocked_aws_provider([AWS_REGION_US_EAST_1])
# Create a DataSync client with no tasks
datasync_client = DataSync(mocked_aws_provider)
datasync_client.tasks = {}
with patch(
"prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled.datasync_client",
new=datasync_client,
), patch(
"prowler.providers.common.provider.Provider.get_global_provider",
return_value=mocked_aws_provider,
):
from prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled import (
datasync_task_logging_enabled,
)
check = datasync_task_logging_enabled()
result = check.execute()
assert len(result) == 0
def test_task_without_logging(self):
from prowler.providers.aws.services.datasync.datasync_service import (
DataSync,
DataSyncTask,
)
# Set up a mocked AWS provider
mocked_aws_provider = set_mocked_aws_provider([AWS_REGION_US_EAST_1])
# Create a DataSync task without logging enabled
task = DataSyncTask(
id=TASK_ID,
arn=TASK_ARN,
name="TestTask",
region=AWS_REGION_US_EAST_1,
cloudwatch_log_group_arn=None, # Logging not enabled
tags=[],
)
# Create a DataSync client with the task
datasync_client = DataSync(mocked_aws_provider)
datasync_client.tasks[TASK_ARN] = task
with patch(
"prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled.datasync_client",
new=datasync_client,
), patch(
"prowler.providers.common.provider.Provider.get_global_provider",
return_value=mocked_aws_provider,
):
from prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled import (
datasync_task_logging_enabled,
)
check = datasync_task_logging_enabled()
result = check.execute()
assert len(result) == 1
assert result[0].status == "FAIL"
assert (
result[0].status_extended
== f"DataSync task {task.name} does not have logging enabled."
)
assert result[0].resource_id == TASK_ID
assert result[0].resource_arn == TASK_ARN
assert result[0].region == AWS_REGION_US_EAST_1
assert result[0].resource_tags == []
def test_task_with_logging(self):
from prowler.providers.aws.services.datasync.datasync_service import (
DataSync,
DataSyncTask,
)
# Set up a mocked AWS provider
mocked_aws_provider = set_mocked_aws_provider([AWS_REGION_US_EAST_1])
# Create a DataSync task with logging enabled
task = DataSyncTask(
id=TASK_ID,
arn=TASK_ARN,
name="TestTask",
region=AWS_REGION_US_EAST_1,
cloudwatch_log_group_arn=f"arn:aws:logs:{AWS_REGION_US_EAST_1}:123456789012:log-group:datasync-log-group",
tags=[],
)
# Create a DataSync client with the task
datasync_client = DataSync(mocked_aws_provider)
datasync_client.tasks[TASK_ARN] = task
with patch(
"prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled.datasync_client",
new=datasync_client,
), patch(
"prowler.providers.common.provider.Provider.get_global_provider",
return_value=mocked_aws_provider,
):
from prowler.providers.aws.services.datasync.datasync_task_logging_enabled.datasync_task_logging_enabled import (
datasync_task_logging_enabled,
)
check = datasync_task_logging_enabled()
result = check.execute()
assert len(result) == 1
assert result[0].status == "PASS"
assert (
result[0].status_extended
== f"DataSync task {task.name} has logging enabled."
)
assert result[0].resource_id == TASK_ID
assert result[0].resource_arn == TASK_ARN
assert result[0].region == AWS_REGION_US_EAST_1
assert result[0].resource_tags == []