accessibility-checker
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): This skill contains no executable scripts (Python, JavaScript, Shell, etc.). It consists entirely of markdown instructions and a decision framework for the AI agent to follow during its reasoning process.
- INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to ingest and process untrusted user content (HTML/CSS code snippets). While this is an attack surface, the skill has no capabilities to execute code, write files, or perform network requests, effectively neutralizing the risk of side effects from malicious input data.
- EXTERNAL_DOWNLOADS (SAFE): The skill contains links to reputable accessibility resources (W3.org, WebAIM). These are provided as reference links for the agent and do not involve automated downloading or execution of remote assets.
Audit Metadata