skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the subprocess module to execute the claude CLI for automated testing and description optimization. This aligns with the skill's purpose as a meta-development tool.
  • [EXTERNAL_DOWNLOADS]: The evaluation viewer (viewer.html) loads the SheetJS library from cdn.sheetjs.com, which is a well-known and trusted technology service.
  • [DATA_EXFILTRATION]: The skill starts a local web server on 127.0.0.1 to provide a human-in-the-loop review interface. This server is appropriately restricted to the local loopback interface and is used to manage local feedback data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 04:50 AM