solo-landing-gen

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 4 "Competitor landing analysis" and MCP tool list instruct the agent to use web_search to fetch and analyze top competitor landing pages (public websites), which the agent will read and use to shape headlines/CTAs, allowing untrusted third‑party content to influence its outputs.