code-review-and-quality
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides instructional guidelines for code quality and does not contain executable code, shell commands, or malicious logic.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose involves processing untrusted code and developer comments as ingestion points. It explicitly instructs the agent to treat this content as data rather than instructions as a boundary marker, notes that no dangerous tools are invoked by the skill itself in its capability inventory, and requires that external data be validated at system boundaries for sanitization.
- [EXTERNAL_DOWNLOADS]: The skill references external checklists from a public GitHub repository. It includes a safety protocol requiring the agent to verify the existence and contents of these files before use, preventing the fabrication of scripts or the execution of unverified procedures.
Audit Metadata