deep-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow (Step 3: "Evidence Collection (Deepresearch Tool)") requires running the deepresearch tool to collect evidence and citations from external sources and build an evidence table that includes "URL or reference", so the agent will fetch and read untrusted public web/user-generated content that can influence report drafting and actions.