ecommerce-advertising

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

• Third-party content exposure detected (high risk: 0.95). The skill's required workflow explicitly instructs the agent to perform web_search and web_fetch on open/public sources (e.g., "web_search" in Keyword Research, "web_fetch: https://www.facebook.com/ads/library/?q=[brand]" and web_fetch of Amazon product pages and other sites in Competitor Ad Analysis and Audience Insights), meaning the agent will ingest untrusted, user-generated third-party content and use it to drive strategy and actions.