outbound-prospecting-engine

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run external signal-collection skills that fetch public, user-generated sources (e.g., "linkedin-post-research", "linkedin-commenter-extractor", "job-posting-intent", "funding-signal-monitor" listed under "Define Signal Sources") and then uses that content in "Run Signal Detection" and subsequent personalization/launch steps to make scoring and outreach decisions, so untrusted third‑party content can materially influence agent behavior.