improve
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for a codebase improvement workflow focusing on analysis and planning.- [INDIRECT_PROMPT_INJECTION]: The skill processes external repository data (code, docs, history) which serves as a potential ingestion point for untrusted instructions. * Ingestion points: Repository instructions, design docs, code, tests, and history (SKILL.md). * Boundary markers: None specified. * Capability inventory: File writing to the plans/ directory. * Sanitization: None specified. The potential impact is limited to the analysis and documentation phase.
Audit Metadata