Skills
skills/psenger/ai-agent-skills/create-a-skill/Gen Agent Trust Hub

create-a-skill

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Several utility scripts execute the claude CLI via the Python subprocess module to run skill evaluations and perform description optimizations. This is the core mechanism of the skill's evaluation loop.
  • [COMMAND_EXECUTION]: The eval-viewer/generate_review.py script executes the lsof command and uses os.kill to manage local network ports when starting the evaluation viewer's internal web server.
  • [EXTERNAL_DOWNLOADS]: The evaluation viewer (eval-viewer/viewer.html) loads the SheetJS library from a well-known CDN (cdn.sheetjs.com) to enable spreadsheet rendering within the review interface.
  • [SAFE]: The skill implements the evaluation loop by creating temporary command files in the .claude/commands/ directory, which is standard practice for testing skills within the Claude Code environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 04:06 AM
Security Audit — agent-trust-hub — create-a-skill