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 Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes AWS S3 bucket policies and Access Control Lists (ACLs) to identify security risks. While these are external data sources that could theoretically contain instructions designed to influence an AI agent, the skill handles them as structured JSON data for configuration analysis.
- Ingestion points: Bucket policies are retrieved via the AWS CLI in SKILL.md and the check_bucket_policy function in scripts/agent.py.
- Boundary markers: Not explicitly implemented in the provided audit logic.
- Capability inventory: The skill has the capability to modify S3 configurations through the remediation commands provided in SKILL.md.
- Sanitization: Data is parsed using standard JSON libraries (json.loads) to ensure it conforms to expected formats.
- [EXTERNAL_DOWNLOADS]: The documentation suggests installing prowler using pip. Prowler is a standard, widely-used open-source security tool for auditing AWS environments and is consistent with the skill's stated purpose.
Audit Metadata