nansen-exit-signal

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly runs "nansen research" commands that fetch public blockchain/trade and address-label data from the third-party Nansen service (e.g., token flow, who-bought-sold, dex-trades), which the agent is expected to read and use (see the "Red flag" logic) to make decisions.