skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/run_eval.py executes the claude CLI using subprocess.Popen to evaluate how specific descriptions affect skill triggering. This is the primary mechanism for the description optimization loop.
  • [COMMAND_EXECUTION]: The script eval-viewer/generate_review.py executes the lsof command via subprocess.run to identify and terminate processes on specific ports before launching the local visualization server.
  • [EXTERNAL_DOWNLOADS]: The eval-viewer/viewer.html file includes a script tag to load the SheetJS library from cdn.sheetjs.com. This is a well-known service used for client-side spreadsheet rendering in the evaluation viewer interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 03:33 PM
Security Audit — agent-trust-hub — skill-creator