skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python's subprocess module in several scripts (generate_review.py, improve_description.py, run_eval.py) to execute shell commands. These calls are used for project-specific tasks like running the claude CLI for automated evaluations and managing local server ports with lsof. This behavior is expected for a developer automation tool.
  • [EXTERNAL_DOWNLOADS]: The eval-viewer/viewer.html file references the well-known SheetJS library from a Content Delivery Network (CDN) to enable spreadsheet rendering within the evaluation interface. This is a standard practice for web-based data visualization.
  • [DATA_EXFILTRATION]: The skill includes a local web server (generate_review.py) that runs on 127.0.0.1. This server is used to present evaluation results to the user locally and does not transmit data to external third-party servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:08 PM
Security Audit — agent-trust-hub — skill-creator