naming-6-gates

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to perform open-web and social-media checks and interpret their results (e.g., Google searches, Namechk/social-handle scans, TikTok/Douyin/RedNote trend checks and other public trademark/domain searches), which are untrusted, user-generated or public third‑party sources and thus expose the agent to indirect prompt injection risk.