accessibility-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements proactive safety measures by instructing the agent to treat all processed data (such as DOM text and logs) strictly as evidence, effectively mitigating indirect prompt injection risks.
- [SAFE]: Sensitive data protection is prioritized through explicit instructions to never record credentials, cookies, or tokens during the review process.
- [SAFE]: The skill maintains a narrow operational scope by forbidding the installation of external tooling and unauthorized source code modifications.
- [SAFE]: All external references are limited to authoritative and well-known documentation from the W3C regarding accessibility standards.
Audit Metadata