yutori-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Process" and "Start the research task" steps state the agent will run web research via Yutori's Research API and fetch/synthesize content from open/public sources (news, social, forums, documentation, arbitrary URLs), so untrusted third‑party content is ingested and can influence the agent's subsequent decisions.