audit-ux

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses firecrawl_search and firecrawl_scrape to fetch current UX guidelines and interaction principles from well-known and reputable sources including nngroup.com, contentdesign.intuit.com, and lawsofux.com. These are recognized industry-standard resources and represent safe, expected behavior for a UX auditing skill.
  • [COMMAND_EXECUTION]: The skill includes examples of using Playwright (npx --yes @playwright/cli@latest) to verify accessibility and focus management in the browser. These commands are localized to testing UI properties and are common in frontend development workflows.
  • [PROMPT_INJECTION]: The skill mentions a protocol-browser-anti-stall skill as a dependency to follow rules for browser interactions. This is an internal instructional reference rather than a bypass attempt.
  • [DATA_EXPOSURE]: The skill performs searches in the codebase for UI-related patterns such as loading, toast, onCancel, and error.message. These searches are scoped to identifying user interface feedback mechanisms and do not target sensitive credentials or system configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:55 AM
Security Audit — agent-trust-hub — audit-ux