skill-creator
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
claudeCLI and system utilities likelsofthrough the Pythonsubprocessmodule. These operations are required for its core functionality and use list-based arguments to avoid shell injection vulnerabilities. - [EXTERNAL_DOWNLOADS]: The evaluation viewer includes references to well-known technology providers, specifically loading fonts from Google and a spreadsheet library from the SheetJS CDN.
- [SAFE]: The skill reads local evaluation outputs and presents them in a local web interface. This workflow is contained within the developer's environment and is intended for manual quality assurance of AI-generated content.
Audit Metadata