Accessibility Testing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Usage explicitly accepts a URL ("Provide the agent with a URL, a block of HTML, or a React/Vue component") and the Workflow directs running automated scans (axe-core/Lighthouse) and producing remediation actions, so the agent will fetch and interpret arbitrary public/web user-provided content which can materially influence its actions.