refactor-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions focus entirely on legitimate code analysis and refactoring tasks. It utilizes standard developer tools (
grep,rg) to scan files for specific patterns (e.g., long functions, nested loops), which is expected behavior for its stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes external code files which are considered untrusted data.
- Ingestion points: The skill uses search tools to read code from target directories to identify "bad smells."
- Boundary markers: There are no explicit delimiters or specific warnings provided to the agent to disregard instructions potentially embedded within the code comments of the files being analyzed.
- Capability inventory: The skill utilizes read-only search capabilities via subprocess calls (
grep,rg). It does not specify any file-writing, network operations, or code execution capabilities. - Sanitization: No sanitization or filtering of the code content is specified before processing.
Audit Metadata