accessibility-wcag

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily educational and instructional, focusing on frontend accessibility standards (WCAG 2.2). All code examples are for demonstration of good vs. bad accessibility patterns (Semantic HTML, ARIA roles, CSS contrast).
  • [EXTERNAL_DOWNLOADS]: The skill provides installation commands for standard, well-known accessibility tools like @axe-core/react, eslint-plugin-jsx-a11y, and @lhci/cli. These are recognized development dependencies from official registries.
  • [COMMAND_EXECUTION]: While the skill requests 'Bash' permission, this is used legitimately to suggest commands for running accessibility audits (e.g., Lighthouse CI). There is no evidence of unauthorized or hidden command execution.
  • [PROMPT_INJECTION]: No evidence of prompt injection, role-play bypasses, or instructions to ignore safety filters.
  • [DATA_EXFILTRATION]: No network operations or file reads targeting sensitive data were found. External links point to official documentation (W3C) and reputable GitHub repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:44 AM
Security Audit — agent-trust-hub — accessibility-wcag