design-brief
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill takes user input to generate design documentation. It uses a strict mapping table (closed vocabulary) to translate natural language into design tokens, which serves as an inherent sanitization layer against prompt injection in the input brief.
- [SAFE]: No network operations, sensitive file access, or remote code execution patterns were detected. The only capability used is
file_writeto output the generatedDESIGN.mdandbrief-preview.htmlfiles.
Audit Metadata