codebase-cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate developer utility for code refactoring and cleanup. It does not download external code, access sensitive credentials, or attempt to persist across sessions.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection common to tools that process repository content. 1. Ingestion points: The skill reads authored source code, tests, and scripts (SKILL.md). 2. Boundary markers: None provided. 3. Capability inventory: The skill can modify files and execute existing repository tests and static checks (SKILL.md). 4. Sanitization: None identified. This risk is managed by the skill's requirements for manual review and automated verification of all changes.
Audit Metadata