research-paper

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 4 "Research the Topic") explicitly instructs the agent to use WebSearch and gather web-based sources (public research, whitepapers, data, perspectives) as part of its canonical research step, meaning it fetches and ingests untrusted public third‑party content that will be interpreted and used to shape outputs.