lead-sources-guide

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

• Third-party content exposure detected (high risk: 0.70). The required workflow has a “fallback only (no ColdIQ)” manual source/scraper stack (Apollo/LinkedIn/LeadMagic/Prospeo/Vayne, etc.), which at runtime would involve outsider-authored web-scraped content or scraped third-party pages/messages being ingested into the LLM context; however, the prompt also gates this fallback on “no ColdIQ access.”