design
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: The skill reads
tailwind.config.*, global CSS files, and component source files (JSX/TSX) to extract design tokens (documented inSKILL.md). - Boundary markers: Absent; the instructions do not specify the use of delimiters or safety instructions when ingesting external file content.
- Capability inventory: The skill performs file system read operations across the codebase and writes to
.planning/design-manifest.md. - Sanitization: Absent; the skill does not explicitly validate or sanitize the input from the files it scans.
Audit Metadata