The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gmgn-cli tool for its primary operations. It also executes system diagnostic commands such as ifconfig and ip addr show to troubleshoot network connectivity issues related to IPv6 support.
[EXTERNAL_DOWNLOADS]: The skill directs the installation of the gmgn-cli package globally via npm to provide the necessary execution environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the GMGN API, including wallet tags, token symbols, and social media metadata, which could be used as a vector for indirect prompt injection.
Ingestion points: Data is retrieved from the GMGN API via several sub-commands like track follow-wallet, track kol, and track smartmoney as specified in SKILL.md.
Boundary markers: The instructions do not define any specific delimiters or clear instructions for the agent to ignore potentially malicious content within the fetched data.
Capability inventory: The agent has the capability to execute shell commands through the CLI tool, perform network requests, and manage local configuration files.
Sanitization: No data validation or sanitization mechanisms are described for handling the content received from the external API.

gmgn-track