request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic follows a legitimate software engineering workflow for refactoring planning and RFC creation.
- [COMMAND_EXECUTION]: The skill instructions include exploring the repository to verify state and test coverage. These are routine read-only operations for development agents.
- [DATA_EXFILTRATION]: The skill is designed to submit information to GitHub as an issue. GitHub is a well-known service for software development, and the data being sent (the refactor plan) is intended for public or team visibility within the repository context. No sensitive files or credentials are accessed.
- [PROMPT_INJECTION]: The skill processes untrusted data from user interviews and codebase content. While this creates an indirect prompt injection surface, the risk is mitigated by the structured template used for output and the inherent requirement for human interaction and review in the refactoring process.
Audit Metadata