nansen-holder-quality

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch token holder/flow/who-bought-sold data from Nansen's public endpoints (e.g., the "nansen research token holders/flow/who-bought-sold" commands), and the agent is expected to read those third-party labels and flows and use them to decide red/green flags, so untrusted external content can directly influence behavior.