The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to wrap the nansen CLI binary, executing subcommands such as token screener, token holders, and token pnl to retrieve blockchain data.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface, as it interpolates user-provided token addresses, symbols, and date ranges into shell commands.
Ingestion points: User-supplied values for the --token, --search, and --date parameters defined in SKILL.md.
Boundary markers: There are no explicit delimiters used to isolate user-provided data within the command strings.
Capability inventory: The skill can execute the nansen binary and utilize curl for network requests to the vendor's API.
Sanitization: No input sanitization or validation logic is present in the skill definition to filter malicious inputs.
[EXTERNAL_DOWNLOADS]: The skill references the official Nansen API (api.nansen.ai) for token information and requires the nansen binary to be present on the system, which are legitimate vendor resources.

nansen-token