cold-email-4-sequence

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

• Third-party content exposure detected (high risk: 0.85). The required workflow pulls “their site/announcements” and “what they’ve said publicly” via ColdIQ MCP calls (e.g., mcp__coldiq__fetch_page_content, mcp__coldiq__extract_post_engagement) which are read into the agent and thus introduce outsider-authored free text from a target’s public web content.