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