accessibility-compliance-accessibility-audit

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

• Third-party content exposure detected (high risk: 0.70). The required workflow can fetch and analyze arbitrary runtime web pages (e.g., runFullAudit(url) with page.goto(url)), and the resulting page-derived text/HTML (e.g., n.html, n.failureSummary, v.description/help) is then used to generate audit findings that are fed into the agent’s LLM context, creating an indirect prompt-injection risk from outsider-authored page content.