prospect-investigation

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to search and ingest untrusted public sources—company websites, job postings, public GitHub repositories, news sites, and LinkedIn profiles—to identify and analyze leads, so the agent will read third-party/user-generated web content that could contain indirect prompt injections.