product-showcase-page

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

• Third-party content exposure detected (high risk: 1.00). The skill's required Step 1 ("Gather Product Data" in SKILL.md) explicitly instructs using web_search to fetch product features, pricing, use cases and reviews from public sites (e.g., G2/Capterra and competitor pages), which are untrusted, user-generated/open-web sources that the agent must read and use to drive content, page architecture, and CTAs—allowing indirect prompt injection via third-party pages.