frontend-design
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructional guidance for UI/UX design tasks without introducing any security vulnerabilities.
- [COMMAND_EXECUTION]: Visual verification recommends using industry-standard browser automation tools like Playwright, Puppeteer, or Cypress if they are already present in the user's project dependencies. These are legitimate tools for the intended purpose of frontend testing.
- [EXTERNAL_DOWNLOADS]: The skill mentions loading an 'agent-browser' skill as a fallback for visual verification. This is a common modular pattern for AI agents and does not involve downloading untrusted scripts from the internet.
- [PROMPT_INJECTION]: The skill includes an 'Authority Hierarchy' that ensures the agent prioritizes the existing project code and explicit user instructions over the skill's own design defaults, effectively preventing accidental overrides or unexpected behavior.
Audit Metadata