nansen-prediction-markets
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
nansen-clipackage via the Node.js package manager as part of its setup process inSKILL.md. - [COMMAND_EXECUTION]: The skill uses the
nansenbinary to execute research commands for prediction market screening, such asnansen research pm market-screener. - [CREDENTIALS_UNSAFE]: The skill requires a
NANSEN_API_KEY. This is correctly defined as a required environment variable in the metadata, following best practices for secret management. - [DATA_EXPOSURE]: The skill retrieves and displays prediction market data including volume, liquidity, and market questions from external sources via the Nansen API.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external market titles and questions (untrusted data) retrieved via the CLI tool.
- Ingestion points: Command output from
nansen research pm market-screener(question, event_title). - Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: Restricted to
Bash(nansen:*)operations. - Sanitization: Not explicitly implemented in the instructions.
Audit Metadata