nansen-smart-money-trend
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
nansenCLI to execute research queries for token netflows, holder lists, and DEX trades. - [EXTERNAL_DOWNLOADS]: The skill installs the
nansen-clipackage via Node.js. This is a legitimate vendor resource provided by nansen-ai and is required for the skill's functionality. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by reading external data.
- Ingestion points: Research data from
nansen researchcommands (e.g., wallet labels, flow intelligence) enters the agent context inSKILL.md. - Boundary markers: There are no explicit markers or instructions provided to the agent to ignore potentially malicious instructions embedded in the API data.
- Capability inventory: The skill is restricted to Bash execution for the
nansen:*toolset. - Sanitization: No sanitization or validation of the tool's output is performed before it is analyzed by the agent.
Audit Metadata