nansen-sm-trend

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using Nansen research commands (e.g., "nansen research token holders", "token dex-trades", "token flow-intelligence") to fetch public third-party data from Nansen which the agent is expected to read and interpret to decide whether smart-money is accumulating or distributing — exposing it to untrusted external content that can influence actions.