nansen-token-analysis

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., "nansen research token holders" and "nansen research token dex-trades") that fetch public on-chain and user-labeled data from the Nansen service/open web, which the agent reads and uses to drive token-analysis decisions, exposing it to untrusted third‑party content that could carry indirect prompt injection.