review-accessibility-change
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to evaluate UI and CLI changes for accessibility failures (e.g., labels, roles, keyboard focus). It does not request or use any tools, network access, or file system permissions.
- [NO_CODE]: No scripts (Python, JavaScript, shell) or binary files are included in the skill. The logic is entirely contained within the markdown instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data (the code or UI changes being reviewed). However, because the skill lacks the ability to execute commands, write files, or make network requests, the surface for indirect prompt injection does not lead to any exploitable capabilities.
Audit Metadata