build-targeted-lead-list

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

• Third-party content exposure detected (medium risk: 0.65). The workflow calls mcp__claude_ai_Amplemarket__search_people and then ingests the returned prospect fields (e.g., names/titles/LinkedIn URLs) into the agent context for preview and list creation; these results are sourced from Amplemarket’s external dataset (outsider-authored content) rather than user-provided text.