review-clean-code
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and analyze user-supplied source code, creating a surface for untrusted data to enter the agent's context.\n- Ingestion points: Source code files are read during the review process as specified in the review workflow (SKILL.md).\n- Boundary markers: The instructions lack specific delimiters or directions to ignore instructions that might be embedded in code comments or string literals within the reviewed files.\n- Capability inventory: The agent has permissions to read codebase files and write output files, specifically clean-code-review.md and clean-code-review.json.\n- Sanitization: The skill does not define methods for sanitizing the input code to mitigate prompt injection risks or ensure instructions within the data are not executed.
Audit Metadata