frontend-a11y
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and metadata. It does not include any scripts, commands, or executable logic that could be used for malicious purposes.
- [SAFE]: All external links point to authoritative and well-known documentation repositories, specifically the W3C (World Wide Web Consortium) and MDN (Mozilla Developer Network), which are standard for web development and accessibility guidelines.
- [SAFE]: The skill references other internal guidelines (e.g., apca-contrast, wcag-contrast) using relative paths, which is a standard method for organizing related documentation within a skill set.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze rendered surfaces (screenshots and live pages), which could theoretically contain malicious hidden text. However, this is a necessary part of the skill's primary function of auditing external content, and the skill provides structured criteria (measured values, specific WCAG success criteria) that help focus the agent's analysis on objective data rather than arbitrary instructions.
Audit Metadata