re-engagement

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow can ingest outsider-authored free text via ColdIQ MCP/API calls (e.g., mcp__coldiq__extract_post_engagement and mcp__coldiq__fetch_page_content fetch and read public page/post content at runtime, which the LLM can then use in the drafted email).