nansen-pm-insider-scan

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 running Nansen research commands (e.g., trades-by-address, profiler historical-balances, profiler labels) that fetch public blockchain/trading/label data from a third‑party service, and that external data is directly read and used to compute flags and drive scoring/decisions, so untrusted third‑party content can materially influence behavior.