enrich-and-score-lead

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

• Third-party content exposure detected (high risk: 0.75). The skill calls mcp__claude_ai_Amplemarket__enrich_person / mcp__claude_ai_Amplemarket__enrich_company with user-provided identifiers (e.g., LinkedIn URL/email/name), and those enrichment tools commonly fetch and return outsider-authored web/profile text (public web/LinkedIn/company pages) that becomes readable LLM context for scoring and summarization.