Email Marketing Engine

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to perform prospect research and personalize outreach using public, user-generated sources (e.g., "Saw [specific thing — blog post, LinkedIn update, company news, job posting]" in the Cold Outreach templates and the Prospect Research Template referencing linkedin_url, website, recent_news, BuiltWith/Wappalyzer and the mxtoolbox check_url), meaning the agent is expected to fetch/read untrusted third‑party web content that could influence subsequent actions.