marketing-audit

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly asks for a target URL/product and instructs "サイト全体の確認" (トップページ → 価格ページ → 登録 → オンボーディング), indicating the agent will fetch and analyze arbitrary public website content provided by users, which is untrusted third‑party content it will read and interpret.