landing-page-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires a "Landing page URL" and its workflow asks the agent to evaluate above-fold clarity, trust signals, form friction, page speed and produce "evidence and screenshots/notes", which clearly implies fetching and interpreting public/untrusted web page content that can materially influence recommendations.