accessibility-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and analytical, focusing on mapping code patterns to WCAG criteria.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted UI code provided by the user to perform audits. This presents a theoretical surface for indirect prompt injection if the audited code contains malicious instructions; however, the risk is negligible as the skill has no access to sensitive data or dangerous tools (e.g., shell or network access).
- [SAFE]: All references are local to the skill package (e.g.,
references/wcag-checklist.md), and no remote code or external packages are downloaded.
Audit Metadata