accessibility-lead
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from web UI code and various document formats during accessibility reviews.\n
- Ingestion points: Processes web UI code (HTML, JSX, CSS, React, templates) and Office/PDF documents as identified in the skill body.\n
- Boundary markers: No explicit markers or instructions are provided to separate user-supplied content from the agent's core instructions.\n
- Capability inventory: The skill is designed for coordination and report generation; it is explicitly restricted from performing direct source file edits.\n
- Sanitization: The instructions do not describe any mechanisms for validating or sanitizing the data processed from external sources.
Audit Metadata