nansen-prediction-market
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No evidence of malicious patterns, obfuscation, or hardcoded credentials was found in the skill. The metadata and instructions are consistent with the stated purpose of analyzing prediction markets.
- [COMMAND_EXECUTION]: The skill utilizes a restricted bash command scope (
nansen:*), which adheres to the principle of least privilege by limiting the agent's ability to execute arbitrary system commands. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from external sources.
- Ingestion points: External data such as market titles and questions are ingested via the
nansen research pmtool as shown inSKILL.md. - Boundary markers: There are no markers or instructions used to delimit the external data or warn the agent to ignore instructions embedded within that data.
- Capability inventory: The skill's capabilities are restricted to the
nansenCLI toolset. - Sanitization: No sanitization or validation logic is present to filter malicious content from the prediction market data.
Audit Metadata