Skill Development

Pass

Audited by Gen Agent Trust Hub on Jun 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation resource, providing procedural guidance and templates for creating other agent skills. It does not contain any hidden or automatically executed code.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or credential harvesting was found. Mentions of sensitive file paths (e.g., .ssh, .aws) are used only as examples of what to exclude from skills.
  • [SAFE]: Command examples (e.g., mkdir, touch, cc) are provided for the user to follow manually during the development process and are not executed by the skill itself.
  • [SAFE]: The skill correctly implements the 'Progressive Disclosure' principle, keeping the main instructions lean while offloading detailed content to reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 1, 2026, 11:22 AM
Security Audit — agent-trust-hub — Skill Development