skill-creator
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several internal Python scripts (
scripts/run_eval.py,eval-viewer/generate_review.py) which utilizesubprocess.Popenandsubprocess.runto manage testing environments and serve local evaluation reports. These are standard operations for the skill's purpose of testing and benchmarking other skills. - [EXTERNAL_DOWNLOADS]: The evaluation viewer (
viewer.html) loads established technology libraries including Google Fonts and SheetJS (from cdn.sheetjs.com) for rendering and visualization. These are well-known services used for standard UI functionality.
Audit Metadata