ux-ui-maxpro
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions for the AI agent on how to approach UI replication tasks. It does not include any scripts, executables, or code files.
- [SAFE]: The instructions promote best practices such as using semantic tokens, maintaining accessibility (ARIA labels), and avoiding hardcoded fabricated data in favor of real API-derived content.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a methodology for processing external visual data such as screenshots to extract design specifications. This represents a potential attack surface for instructions embedded in images, although the guidelines prioritize mapping to existing project data and tokens.
- Ingestion points: User-provided screenshots and design reference images.
- Boundary markers: The skill relies on following established local repository rules (DESIGN.md) to govern output.
- Capability inventory: Generation of React components and modification of CSS tokens in app/globals.css.
- Sanitization: Not applicable as the process involves manual extraction of style values by the agent.
Audit Metadata