skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python's subprocess module to run the claude CLI for evaluation tasks and the lsof utility for local port management.
  • [EXTERNAL_DOWNLOADS]: The evaluation viewer fetches the SheetJS library from cdn.sheetjs.com and fonts from Google CDNs to support the web-based review interface.
  • [SAFE]: Analysis of the source code and scripts confirms the absence of malicious features such as unauthorized data exfiltration, privilege escalation, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 10:37 AM