visual-design-system-extractor
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is well-structured and focuses on its primary task of design system extraction without any detected malicious intent.
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to fonts.google.com to fetch font metadata and fonts.googleapis.com to link CSS files in previews. These are well-known and trusted services used for their intended purpose.
- [COMMAND_EXECUTION]: Subprocess calls are limited to the skill's own scripts within the test suite (scripts/tests/test_render_preview.py), which is standard for validating internal functionality.
- [REMOTE_CODE_EXECUTION]: The skill uses uv run to execute scripts with specific dependencies (PyYAML and Playwright). This is a standard and safe way to handle runtime environments.
- [DATA_EXFILTRATION]: No patterns of data exfiltration were found. Access to external networks is specifically for public font data.
Audit Metadata