code-review
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase being reviewed, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: Processes content from
git diff,git status,rg, andgrep(SKILL.md). - Boundary markers: The skill does not define specific markers or instructions for the agent to ignore content that appears to be instructions within the code files.
- Capability inventory: The skill can perform file-write operations if the user selects the 'Fix all' or 'Fix specific items' workflow (SKILL.md).
- Sanitization: The instructions do not specify any validation or sanitization for the code content being processed.
Audit Metadata