refactor-assistant

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides high-level architectural and refactoring guidelines without any risky commands, file access, or network operations.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) as it is designed to process and refactor external codebases which could contain hidden instructions.
  • Ingestion points: Reads project code and legacy files (SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: Generates code suggestions and architectural changes.
  • Sanitization: No sanitization of code comments or strings is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:58 AM
Security Audit — agent-trust-hub — refactor-assistant