cc-refactoring-guidance
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code and comments to provide refactoring guidance, which creates a potential surface for instructions embedded in that code to influence agent actions.
- Ingestion points: Project source code and module conventions analyzed for refactoring in
SKILL.mdand thechecklists.mdfile. - Boundary markers: No explicit delimiters or boundary instructions are provided to separate data (code) from instructions for the agent.
- Capability inventory: The skill guides the agent to perform file modifications (refactoring), execute version control commands (git), and run regression tests.
- Sanitization: The instructions do not define methods for sanitizing or ignoring potential instructions hidden within the source code or comments being processed.
Audit Metadata