The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the nansen CLI binary to perform complex trading queries, which is a standard operational requirement for this vendor-provided skill.
[EXTERNAL_DOWNLOADS]: Data is retrieved from the official Nansen API (api.nansen.ai) using authenticated HTTP requests. This is a trusted vendor service.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface (Category 8). 1. Ingestion points: External data enters the agent context via the nansen CLI output and API JSON responses. 2. Boundary markers: The skill does not define specific delimiters to isolate external data. 3. Capability inventory: The agent can execute system commands using the nansen binary. 4. Sanitization: No explicit data sanitization or validation logic is provided in the skill definition.

nansen-hyperliquid