cartography 0.107.0rc2__py3-none-any.whl → 0.108.0__py3-none-any.whl

cartography/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.107.0rc2'
-__version_tuple__ = version_tuple = (0, 107, 0, 'rc2')
+__version__ = version = '0.108.0'
+__version_tuple__ = version_tuple = (0, 108, 0)

cartography/cli.py

@@ -264,6 +264,16 @@ class CLI:
                 " If not specified, cartography by default will run all AWS sync modules available."
             ),
         )
+        parser.add_argument(
+            "--aws-guardduty-severity-threshold",
+            type=str,
+            default=None,
+            help=(
+                "GuardDuty severity threshold filter. Only findings at or above this severity level will be synced. "
+                "Valid values: LOW, MEDIUM, HIGH, CRITICAL. If not specified, all findings (except archived) will be synced. "
+                "Example: 'HIGH' will sync only HIGH and CRITICAL findings, filtering out LOW and MEDIUM severity findings."
+            ),
+        )
         parser.add_argument(
             "--analysis-job-directory",
             type=str,

cartography/config.py

@@ -53,6 +53,9 @@ class Config:
     :param entra_client_secret: Client Secret for connecting in a Service Principal Authentication approach. Optional.
     :type aws_requested_syncs: str
     :param aws_requested_syncs: Comma-separated list of AWS resources to sync. Optional.
+    :type aws_guardduty_severity_threshold: str
+    :param aws_guardduty_severity_threshold: GuardDuty severity threshold filter. Only findings at or above this
+        severity level will be synced. Valid values: LOW, MEDIUM, HIGH, CRITICAL. Optional.
     :type analysis_job_directory: str
     :param analysis_job_directory: Path to a directory tree containing analysis jobs to run. Optional.
     :type oci_sync_all_profiles: bool
@@ -185,6 +188,7 @@ class Config:
         entra_client_id=None,
         entra_client_secret=None,
         aws_requested_syncs=None,
+        aws_guardduty_severity_threshold=None,
         analysis_job_directory=None,
         oci_sync_all_profiles=None,
         okta_org_id=None,
@@ -268,6 +272,7 @@ class Config:
         self.entra_client_id = entra_client_id
         self.entra_client_secret = entra_client_secret
         self.aws_requested_syncs = aws_requested_syncs
+        self.aws_guardduty_severity_threshold = aws_guardduty_severity_threshold
         self.analysis_job_directory = analysis_job_directory
         self.oci_sync_all_profiles = oci_sync_all_profiles
         self.okta_org_id = okta_org_id

cartography/data/indexes.cypher

@@ -81,8 +81,6 @@ CREATE INDEX IF NOT EXISTS FOR (n:DODroplet) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:DODroplet) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:DOProject) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:DOProject) ON (n.lastupdated);
-CREATE INDEX IF NOT EXISTS FOR (n:EBSSnapshot) ON (n.id);
-CREATE INDEX IF NOT EXISTS FOR (n:EBSSnapshot) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:EC2KeyPair) ON (n.keyfingerprint);
 CREATE INDEX IF NOT EXISTS FOR (n:EC2ReservedInstance) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:EC2ReservedInstance) ON (n.lastupdated);
@@ -156,14 +154,8 @@ CREATE INDEX IF NOT EXISTS FOR (n:GSuiteUser) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:Ip) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:Ip) ON (n.ip);
 CREATE INDEX IF NOT EXISTS FOR (n:Ip) ON (n.lastupdated);
-CREATE INDEX IF NOT EXISTS FOR (n:IpPermissionInbound) ON (n.ruleid);
-CREATE INDEX IF NOT EXISTS FOR (n:IpPermissionInbound) ON (n.lastupdated);
-CREATE INDEX IF NOT EXISTS FOR (n:IpPermissionsEgress) ON (n.ruleid);
-CREATE INDEX IF NOT EXISTS FOR (n:IpPermissionsEgress) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:IpRange) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:IpRange) ON (n.lastupdated);
-CREATE INDEX IF NOT EXISTS FOR (n:IpRule) ON (n.ruleid);
-CREATE INDEX IF NOT EXISTS FOR (n:IpRule) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:JamfComputerGroup) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:JamfComputerGroup) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:KMSKey) ON (n.id);
@@ -267,8 +259,6 @@ CREATE INDEX IF NOT EXISTS FOR (n:S3Bucket) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:S3Bucket) ON (n.name);
 CREATE INDEX IF NOT EXISTS FOR (n:S3Bucket) ON (n.arn);
 CREATE INDEX IF NOT EXISTS FOR (n:S3Bucket) ON (n.lastupdated);
-CREATE INDEX IF NOT EXISTS FOR (n:SecretsManagerSecret) ON (n.id);
-CREATE INDEX IF NOT EXISTS FOR (n:SecretsManagerSecret) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:SecurityHub) ON (n.id);
 CREATE INDEX IF NOT EXISTS FOR (n:SecurityHub) ON (n.lastupdated);
 CREATE INDEX IF NOT EXISTS FOR (n:SpotlightVulnerability) ON (n.id);

cartography/data/jobs/cleanup/github_repos_cleanup.json

@@ -19,6 +19,7 @@
     "iterative": true,
     "iterationsize": 100
   },
+
   {
     "query": "MATCH (:GitHubBranch)-[r:BRANCH]->(:GitHubRepository) WHERE r.lastupdated <> $UPDATE_TAG WITH r LIMIT $LIMIT_SIZE DELETE (r)",
     "iterative": true,
@@ -39,6 +40,7 @@
     "iterative": true,
     "iterationsize": 100
   },
+
   {
     "query": "MATCH (:GitHubUser)-[r:OUTSIDE_COLLAB_ADMIN]->(:GitHubRepository) WHERE r.lastupdated <> $UPDATE_TAG WITH r LIMIT $LIMIT_SIZE DELETE (r)",
     "iterative": true,

cartography/intel/aws/__init__.py

@@ -310,6 +310,7 @@ def start_aws_ingestion(neo4j_session: neo4j.Session, config: Config) -> None:
     common_job_parameters = {
         "UPDATE_TAG": config.update_tag,
         "permission_relationships_file": config.permission_relationships_file,
+        "aws_guardduty_severity_threshold": config.aws_guardduty_severity_threshold,
         "aws_cloudtrail_management_events_lookback_hours": config.aws_cloudtrail_management_events_lookback_hours,
     }
     try:

cartography/intel/aws/cloudtrail.py

@@ -26,13 +26,25 @@ def get_cloudtrail_trails(
     )
 
     trails = client.describe_trails()["trailList"]
-
-    # CloudTrail multi-region trails are shown in list_trails,
-    # but the get_trail call only works in the home region
     trails_filtered = [trail for trail in trails if trail.get("HomeRegion") == region]
+
     return trails_filtered
 
 
+def transform_cloudtrail_trails(
+    trails: List[Dict[str, Any]], region: str
+) -> List[Dict[str, Any]]:
+    """
+    Transform CloudTrail trail data for ingestion
+    """
+    for trail in trails:
+        arn = trail.get("CloudWatchLogsLogGroupArn")
+        if arn:
+            trail["CloudWatchLogsLogGroupArn"] = arn.split(":*")[0]
+
+    return trails
+
+
 @timeit
 def load_cloudtrail_trails(
     neo4j_session: neo4j.Session,
@@ -79,7 +91,8 @@ def sync(
         logger.info(
             f"Syncing CloudTrail for region '{region}' in account '{current_aws_account_id}'.",
         )
-        trails = get_cloudtrail_trails(boto3_session, region)
+        trails_filtered = get_cloudtrail_trails(boto3_session, region)
+        trails = transform_cloudtrail_trails(trails_filtered, region)
 
         load_cloudtrail_trails(
             neo4j_session,