code-simplification
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function of analyzing external, untrusted code and diffs creates a potential injection surface.
- Ingestion points: The workflow involves the agent inspecting specific file paths, uncommitted local changes, and git diffs as part of its audit process.
- Boundary markers: The instructions do not explicitly direct the agent to ignore or isolate instructions that may be embedded within the comments or documentation of the code being reviewed.
- Capability inventory: The agent is permitted to use
git,rg(ripgrep),grep, and any project-configured non-mutating linters (such as eslint, ruff, or terraform validation) to assist its analysis. - Sanitization: There are no specific instructions for the agent to sanitize or filter out potential instructions found within the code artifacts it processes.
Audit Metadata