heading-order
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown documentation and accessibility guidelines. It does not include any executable code, shell commands, or network-accessing tools.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze third-party HTML code for accessibility violations. 1. Ingestion points: Rendered HTML and interactive components (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are present for the analyzed data. 3. Capability inventory: The skill specifies only analytical tasks; it does not define or use tools to write files, execute commands, or perform network requests. 4. Sanitization: No input sanitization is described.
Audit Metadata