nansen-prediction-markets

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the nansen-cli package from the Node package registry as part of its installation process.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted market data, creating a potential injection surface. 1. Ingestion points: Prediction market data including event titles and market questions fetched via the nansen research tool. 2. Boundary markers: Not present; external content is interpolated directly into the context without specific delimiters. 3. Capability inventory: The agent's actions are scoped to the nansen command-line interface. 4. Sanitization: No specific filtering or validation of the market data is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 02:14 AM
Security Audit — agent-trust-hub — nansen-prediction-markets