prospect-research

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 read and synthesize public information from third‑party sources—e.g., "Use whatever public information you can synthesize" and the Pre-Call Checklist items "Reviewed their website" and "Checked LinkedIn profile"—which are untrusted, user-controlled web pages the agent is expected to interpret and that can materially influence its recommendations and next actions.