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
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — accessibility-lead