iam-policy-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review IAM policies and security configurations, which are external data sources that could theoretically contain embedded prompt injection payloads.
- Ingestion points: Processes user-provided IAM policies and security pattern descriptions (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed data are defined.
- Capability inventory: The skill is configured to use Read, Write, Edit, and arbitrary Bash commands (SKILL.md).
- Sanitization: There are no documented sanitization or validation routines for the content of the policies being reviewed.
Audit Metadata