hot-topics

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly gathers and analyzes public, user-generated content from "finance YouTubers" (via steps/tools like list_tickers and search_viewpoints to collect mentions and viewpoints), so the agent will ingest untrusted third‑party material that could contain indirect prompt injection.