nansen-agent-guide
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use
nansen agentfor interpreting external blockchain data and market trends. This creates a surface for indirect prompt injection where malicious blockchain data could attempt to influence the agent's synthesis.\n - Ingestion points: External research data fetched by
nansen agent(SKILL.md).\n - Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the bash command templates.\n
- Capability inventory: Shell command execution restricted to the
nansentoolset viaBash(nansen:*)(SKILL.md).\n - Sanitization: The instructions do not specify any sanitization or filtering of the external data before processing.\n- [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the
nansen-clipackage. This is a standard dependency for accessing the research capabilities described in the guide.
Audit Metadata