skill-creator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Python subprocess module to interact with the platform's CLI for executing evaluations and optimization loops. It also uses system tools like lsof to manage network ports for its internal review server, ensuring consistent local performance.
  • [EXTERNAL_DOWNLOADS]: The evaluation viewer UI incorporates reputable third-party libraries, specifically Google Fonts and the SheetJS data processing library, which are loaded from their official content delivery networks.
  • [DATA_EXFILTRATION]: The skill launches a local-only web server (binding to the 127.0.0.1 loopback address) to enable the user to review test results in a browser interface, ensuring that evaluation data does not leave the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 12:30 AM
Security Audit — agent-trust-hub — skill-creator