investigate

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to perform literature searches and download/read papers from open public sources (e.g., "IACR + arXiv + WebSearch", "download relevant papers to reaper-workspace/papers/") and to integrate those findings into the investigation workflow, which means untrusted third‑party content can be ingested and influence decisions and next actions.