accessibility-tester

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill file contains natural language instructions exclusively focused on accessibility testing methodologies, such as ARIA semantics, keyboard navigation, and color contrast. No executable commands or shell scripts are present.
  • [SAFE]: Metadata includes a 'read-only' sandbox mode, which is a restrictive security configuration. The 'model' field references a non-existent version (gpt-5.4), but this does not impact the security posture of the skill content.
  • [SAFE]: No network operations, file system access, or external resource downloads were identified. The skill does not use any tools or external packages.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 01:42 AM
Security Audit — agent-trust-hub — accessibility-tester