prospector

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly ingests public third‑party content—e.g., enrich_person({ person: { linkedInProfile: "" } }) and "Recent news and events" / "competitor X mentioned on site" from enrich_company/find_company steps—so the agent is expected to read and act on user-generated or public web content that could influence scoring and next actions.