nyne

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-provided social and website content (e.g., Person Newsfeed and Person Interactions endpoints that take social_media_url for LinkedIn/Twitter/Instagram/GitHub/Facebook, Person Enrichment using social_media_url, and Company Search's validate_keyword that checks company website HTML), so it reads untrusted third‑party pages whose content could influence analysis and subsequent actions.