The Agent Skills Directory

[SAFE]: The skill installs and uses the nansen-cli Node.js package, which is a legitimate vendor resource provided by the author to interface with their services.
[SAFE]: Credential management follows best practices by utilizing the NANSEN_API_KEY environment variable for authentication, preventing the exposure of hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from blockchain analysis APIs, which represents a standard data ingestion surface.
Ingestion points: The output of nansen research commands (labels, trades, and positions) is loaded into the agent's context within SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded content are specified for the API output.
Capability inventory: The skill is limited to executing nansen CLI research commands via the Bash tool.
Sanitization: The skill relies on the integrity of the vendor's own API responses and the agent's internal safety filters.

nansen-perp-trader-profile