email-finder-hunter

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

• Third-party content exposure detected (medium risk: 0.65). The skill calls Hunter’s enrichment endpoints (e.g., /v2/people/find, /v2/domain-search, /v2/combined/find) via the Gooseworks/Orthogonal proxy at runtime, and the LLM will ingest the returned enrichment text (person/company details) originating from third-party data sources outside the operating user’s control.