nansen-alpha-discovery

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the nansen-cli package from the official npm registry. This tool is provided by Nansen, a well-known and reputable blockchain analytics platform.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external data from the Nansen API. 1. Ingestion points: The agent reads data from the stdout of nansen research commands executed via the Bash tool. 2. Boundary markers: No delimiters or instructions are used to separate the external data from the agent's internal prompt logic. 3. Capability inventory: The skill is restricted to calling the nansen CLI tool via Bash. 4. Sanitization: There is no evidence of data validation or sanitization for the API responses before they are returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:23 PM