accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed strictly of markdown-based documentation and instructions. It does not perform any network operations, file system modifications, or command executions. All external links point to authoritative and well-known industry sources such as W3C, WebAIM, and MDN.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided UI code and diffs.
- Ingestion points: External code snippets are processed within the Review and Audit modes described in SKILL.md.
- Boundary markers: There are no explicit markers or 'ignore' instructions for the ingested code blocks.
- Capability inventory: The skill has no dangerous capabilities such as shell execution, file-write, or network-send across any of its files.
- Sanitization: No sanitization is performed, but the risk is mitigated by the complete lack of exploitable tools or capabilities.
Audit Metadata