nansen-core

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the nansen-cli package via npm install -g. This is the official command-line tool provided by the vendor, nansen-ai.
  • [COMMAND_EXECUTION]: The skill executes local system commands to verify environment readiness (which nansen, nansen --version) and manage user authentication (nansen login).
  • [COMMAND_EXECUTION]: The skill utilizes nansen schema to dynamically discover available commands and parameters, which allows the agent to update its toolset based on the vendor's latest API definitions.
  • [PROMPT_INJECTION]: The skill processes data retrieved from the CLI, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is ingested through the outputs of nansen profiler and nansen schema (SKILL.md).
  • Boundary markers: The instructions explicitly direct the agent to use JSON output for data extraction and provide specific rules for resolving token addresses.
  • Capability inventory: The skill has the capability to execute CLI commands and set environment variables (NANSEN_API_KEY).
  • Sanitization: No specific sanitization or filtering logic is described for the CLI output within the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:16 AM