personalization

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs ingesting and using external/public third‑party content (e.g., "external signals" like company news and social, pulling company context via website_url in smartDigest, and "User-Generated Content — uploads, files, posts") and then assembling that context (smartDigest/recall) to decide channels, generate messages, and trigger deliveries, so untrusted third‑party content can materially influence agent actions.