email-writing-frameworks

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md requires pulling personalization and page content via the ColdIQ MCP endpoints (including mcp__coldiq__fetch_page_content which can ingest arbitrary scraped page text) and then slotting that material into drafting prompts, creating an indirect prompt-injection exposure path from outsider-authored web content into the agent’s LLM context.