research

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly fetches and ingests public web content (e.g., Wave 2 "Dispatch deep-read subagents — use fetcher/trafilatura/docling to extract full content from top leads" and Wave 3/self-verification "Fetch the URL ... confirm the claimed content") so the agent will read and act on untrusted third‑party webpages/URLs which can materially influence tool use and decisions.