refactoring-suggester
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill consists exclusively of markdown documentation and YAML configuration files. No executable scripts (.py, .js, .sh) or binaries are included.- INDIRECT_PROMPT_INJECTION (LOW):- Ingestion points: Untrusted content is ingested through the source_code input in skill.yaml.- Boundary markers: No specific delimiters or safety warnings for the LLM regarding input processing are defined.- Capability inventory: The skill definitions contain no executable capabilities such as shell access, network requests, or file system modifications.- Sanitization: No input sanitization is present.- Risk Assessment: While malicious code could be passed to the agent, the skill itself provides no tools or permissions for that code to execute or affect the system.
Audit Metadata