nansen-holder-analysis

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the agent calling Nansen research endpoints (e.g., "nansen research token holders", "flow-intelligence", "who-bought-sold") to fetch external on-chain and labeling data which the agent reads and uses to decide holder quality, so untrusted third‑party content can materially influence decisions.