request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill follows standard development workflows for code analysis and reporting.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository content and user input to generate a refactor plan. This involves ingesting external data (codebase content), but since the output is a descriptive GitHub issue and the process is interactive, the risk is minimal and inherent to the skill's primary function.
- [DATA_EXFILTRATION]: The skill generates a refactor plan based on the codebase and posts it to GitHub. It specifically mitigates data exposure risks by instructing the agent not to include code snippets or specific file paths in the generated issue, focusing only on high-level decisions and commit descriptions.
Audit Metadata