authoring-hi-fi
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external specifications from upstream wireframes and design systems to generate UI code. This establishes an indirect prompt injection surface.
- Ingestion points: SKILL.md (Step 2).
- Boundary markers: No explicit delimiters or warnings provided for external source content.
- Capability inventory: Subprocess calls via agent-browser and UI code generation.
- Sanitization: Not specified. This surface is characteristic of the skill's primary function.
- [COMMAND_EXECUTION]: The skill instructs the agent to use a headless browser for rendering and screenshot capture as part of a visual review loop.
- [EXTERNAL_DOWNLOADS]: The skill references well-known frameworks and tools including Tailwind CSS, shadcn/ui, and axe-core.
Audit Metadata