skill-creator
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several internal Python scripts for workflow automation, including benchmark aggregation, skill packaging, and evaluation review generation.
- [COMMAND_EXECUTION]: The skill invokes the 'claude' CLI tool to perform background evaluations and description optimization loops.
- [EXTERNAL_DOWNLOADS]: The skill downloads and uses a version of the 'xlsx' library (SheetJS) from a well-known technology provider's CDN (cdn.sheetjs.com) for rendering Excel files within the HTML viewer.
Audit Metadata