aria-input-field-name
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely educational and instructional, focusing on best practices for accessibility. It provides standard methods for associating labels with form controls and explains the importance of these practices for assistive technology users.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing and modifying HTML markup provided by the user.
- Ingestion points: The skill instructs the agent to find and review
<input>,<textarea>, and<select>elements in provided markup (SKILL.md). - Boundary markers: None present in the instructions.
- Capability inventory: The skill's capabilities are limited to analyzing text, flagging violations, and suggesting code modifications (adding labels or ARIA attributes). It does not request network access, file system writes, or shell execution.
- Sanitization: Not explicitly defined, but the low-privilege nature of the suggested actions (modifying HTML tags) poses no significant security risk.
Audit Metadata