coldiq-messaging-templates

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

• Third-party content exposure detected (high risk: 0.70). At runtime, this workflow may pull “company context” and “what they've said publicly” via ColdIQ MCP calls like mcp__coldiq__fetch_page_content, mcp__coldiq__extract_post_engagement, and related enrichment, which can ingest outsider-authored free text scraped/extracted from public web content (or other third-party sources) into the agent’s LLM context.