accessibility-expert
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a specialized persona for accessibility auditing and remediation without introducing any functional risks. It consists entirely of natural language instructions and does not reference any external scripts, binaries, or automated tools for execution.
- [SAFE]: No sensitive data access, network operations, or persistence mechanisms were detected. The skill operates within the standard constraints of the agent's interaction model.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit user-provided code and UI components, which is a potential ingestion point for indirect instructions. However, as the skill provides no additional tools or capabilities beyond advice, the risk is negligible.
- Ingestion points: User-provided HTML, CSS, and JavaScript code snippets for accessibility auditing (SKILL.md).
- Boundary markers: None explicitly defined for untrusted content.
- Capability inventory: None; the skill does not use any external tools or scripts.
- Sanitization: None mentioned.
Audit Metadata