lp-optimization

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires a landing page URL as input and the Layer 1 agents' input/output contracts and examples expect the agent to read and report exact page content (headline, CTAs, form fields, social proof) from that public landing page (see "Inputs Required
• Landing page URL" and each agent's "Input Contract" / "Current" sections), which means it will ingest untrusted third‑party web content that can influence subsequent tool use and decisions.