The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the gmgn-cli utility via npm install -g gmgn-cli. This is the primary tool required for the skill's functionality.
[COMMAND_EXECUTION]: The skill relies on executing shell commands via the gmgn-cli tool to query blockchain data. It also uses system diagnostic commands like ifconfig, ip addr show, and curl to verify network configurations (specifically identifying IPv6 vs IPv4 environments).
[INDIRECT_PROMPT_INJECTION]: The skill processes data returned from external API calls via the CLI tool, creating a surface for indirect injection if the API returns malicious content.
Ingestion points: Data is ingested from the output of various gmgn-cli portfolio commands (SKILL.md).
Boundary markers: None explicitly defined in the instructions; the agent is guided to parse specific JSON fields.
Capability inventory: The skill has the ability to execute shell commands (gmgn-cli, ifconfig, ip) and perform network requests via the CLI.
Sanitization: No explicit sanitization or validation of the tool's output is described beyond extracting specific numeric and string fields for presentation.

gmgn-portfolio