lead-research-assistant

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 research and ingest information from open/public third-party sources—e.g., company websites, job postings, LinkedIn profiles, public GitHub repos, and recent news—to identify and score leads, which exposes it to untrusted/user-generated content.