detecting-aws-guardduty-findings-automation

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where external data is processed and used to perform privileged actions.
  • Ingestion points: The lambda_handler functions in SKILL.md ingest untrusted data from the event['detail'] object originating from AWS GuardDuty findings.
  • Boundary markers: No delimiters or warnings are used to prevent the agent or the script from interpreting embedded instructions within the finding data.
  • Capability inventory: The skill performs high-privilege operations including ec2.create_tags, ec2.modify_instance_attribute, iam.update_access_key, and iam.put_user_policy (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the finding fields (e.g., finding_type, userName) before they are interpolated into AWS API calls or notification messages.
  • [COMMAND_EXECUTION]: The skill provides AWS CLI commands for configuring GuardDuty detectors and EventBridge rules (SKILL.md). These are standard administrative tasks for the skill's stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references official AWS documentation and GitHub repositories for best practices and integration guides. These are from well-known technology services and are considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 10:03 AM
Security Audit — agent-trust-hub — detecting-aws-guardduty-findings-automation