deep-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to perform web searches, "follow references", and "use web_fetch to read important sources in full" (Phase 2: Deep Dive / "When to Use web_fetch"), which means it ingests open/public third‑party content that the agent must interpret and that can materially influence subsequent actions.