lp-optimization

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires fetching or ingesting a landing page URL (see "Pre-Dispatch" and "Inputs Required" / Warm Start: "Page itself: fetch URL or read paste"), so the agent will read arbitrary public web content and use it to drive audits and downstream agent actions, which can materially influence behavior and enable indirect prompt injection.