request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text to guide an agent through a refactor planning process. It does not include executable code, scripts, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user input and repository code to generate a GitHub issue.
- Ingestion points: User interviews (steps 1, 4) and repository exploration (steps 2, 6) in SKILL.md.
- Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: Repository exploration and GitHub issue creation.
- Sanitization: None specified. While this represents a standard surface for indirect prompt injection, the risk is considered minimal due to the human-in-the-loop nature of the refactor planning workflow.
Audit Metadata