cold-email-templates-34

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

• Third-party content exposure detected (high risk: 0.70). This skill’s runtime workflow can call the ColdIQ MCP to pull personalization fields and page content (e.g., mcp__coldiq__fetch_page_content) from an external service/marketplace, which would likely be ingested as free-form text into the agent’s LLM context for template filling.