refactor-planner

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a professional software engineering methodology featuring distinct operational modes (Map, Design, Execute, Closeout) and standardized reporting formats without any suspicious command patterns.
  • [SAFE]: Instructions for creating artifacts such as Markdown specifications and HTML reports in the scratchpad/ directory are consistent with the skill's purpose as a documentation and planning tool and do not involve unauthorized file access or exfiltration.
  • [SAFE]: The skill's framework for delegating sub-tasks to specific models or parallel workers is part of an intended coordination strategy and does not involve the execution of remote code from untrusted external sources.
  • [SAFE]: No obfuscation techniques, hardcoded credentials, or persistence mechanisms were detected in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:57 PM
Security Audit — agent-trust-hub — refactor-planner