accessibility-requirements
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed to facilitate the creation of accessibility documentation (WCAG, EAA, etc.) and does not contain any commands for network exfiltration, credential theft, or persistence.
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted user data regarding products and features.
- Ingestion points: User-supplied strings via the
argument-hintand interactive dialogue (Phase 1). - Boundary markers: None provided in the instructions to delimit user input from the system prompt.
- Capability inventory: The skill generates markdown files and utilizes a
diagram-renderingmixin to create Mermaid diagrams, which are written to the local file system. - Sanitization: No explicit sanitization or validation of the user-provided product description is performed before interpolation into the output templates.
Audit Metadata