skills/mukul975/anthropic-cybersecurity-skills/auditing-aws-s3-bucket-permissions/Gen Agent Trust Hub
auditing-aws-s3-bucket-permissions
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by retrieving AWS S3 bucket policies and Access Control Lists (ACLs). While this is the intended functionality for an auditing tool, it represents a data ingestion surface.
- Ingestion points: The
scripts/agent.pyscript retrieves bucket policies via thes3.get_bucket_policymethod. - Boundary markers: No explicit delimiters or instructions are used to separate the policy data from the auditing logic.
- Capability inventory: The script performs read-only AWS API calls and writes the audit results to a local file (
s3_audit_report.json). - Sanitization: The skill relies on standard JSON parsing (
json.loads) to process the policy structure. - [EXTERNAL_DOWNLOADS]: The skill instructions recommend installing established security auditing tools, including
prowler,S3audit, andScoutSuite. These are well-known utilities within the cybersecurity domain used for cloud security assessments.
Audit Metadata