accessibility
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard development tools via
npx(e.g.,playwright,pa11y,lighthouse) to perform accessibility scans on localized environments (e.g.,http://localhost:3000). This is typical and appropriate behavior for an auditing tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web content (HTML/ARIA) to perform audits. While this constitutes an attack surface for indirect prompt injection, the skill's focus on structured metadata analysis (WCAG compliance) and the inclusion of explicit security guardrails regarding scanner sandbox integrity mitigate this risk.
- [REMOTE_CODE_EXECUTION]: The skill references standard NPM packages for its functionality. All identified packages are reputable and widely used in the development community for their stated purposes.
Audit Metadata