reputation-management

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to monitor and read untrusted public third‑party content — e.g., "Monitoring scope: Social media mentions, review platforms, news/press, forums" and the workflow step "Assess the review — Read carefully" — which the agent would interpret and act on, allowing external posts/reviews to influence responses and tool use.