nansen-prediction-markets

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md commands (e.g., "nansen research prediction-market event-screener", "market-screener", "top-holders", "trades-by-market") clearly fetch public prediction-market data (market questions, trades, holder info) from open third-party sources (e.g., Polymarket/blockchain-visible markets) which are user-generated and are read and used by the agent as part of its workflow, allowing those external contents to influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 04:12 PM