Skills
skills/caomeiyouren/cmyr-skills-agents/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates testing by programmatically invoking the claude CLI via Node.js spawn in scripts such as run_eval.mjs and improve_description.mjs. This is used to test skill triggering and optimize descriptions.
  • [COMMAND_EXECUTION]: The eval-viewer component starts a local HTTP server to host a visualization dashboard and uses system commands (open, start, or xdg-open) to launch the default web browser.
  • [SAFE]: The skill follows secure patterns by using standard Node.js built-in modules for file and process management. It operates exclusively on local project data and does not perform unauthorized network requests or data exfiltration.
  • [SAFE]: The frontmatter and instructions are focused on development productivity and provide helpful security guidance to users, such as the use of allowed-tools to restrict agent capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 11:54 AM