deep-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow step 3 ("Web research — use WebSearch and WebFetch") clearly instructs the agent to fetch and read external public web content (and store source URLs in the research-sources namespace), exposing it to untrusted third-party material that can influence decisions and actions.