landing-page-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 1: "Use web_search to research the product" in SKILL.md) and its agent config (tools: web_search, web_browse) explicitly fetch and ingest public web content (reviews, pricing pages, competitor sites), which the agent must read and use to decide page content, recommendations, and CTAs — exposing it to untrusted third‑party input that could carry indirect prompt injection.