The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the nansen-cli package, a command-line tool for interacting with the Nansen crypto-analytics service, to be installed via the official npm registry.
[DATA_EXFILTRATION]: The skill requires a NANSEN_API_KEY. It correctly instructs the user to set this as an environment variable rather than hardcoding it, which is the standard safe practice for CLI tools.
[COMMAND_EXECUTION]: The skill's environment is secured using the allowed-tools directive, which restricts bash execution specifically to the nansen binary. This prevents attackers from using the shell to execute unauthorized system commands or exfiltrate data.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for external data from the Nansen API.
Ingestion points: Data from nansen research command outputs is processed by the agent.
Boundary markers: No explicit markers are defined in the prompt instructions.
Capability inventory: Execution is strictly limited to the nansen command-line interface.
Sanitization: The agent processes raw output from the verified research tool.

nansen-dca-tracker