The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands including gmgn-cli for data retrieval, openssl for key generation during setup, and filesystem utilities (mkdir, echo, chmod) for configuration management.
[EXTERNAL_DOWNLOADS]: Instructions recommend installing the gmgn-cli package globally via npm if it is not already present. This is a vendor-provided tool necessary for the skill's operation.
[DATA_EXFILTRATION]: Contains instructions to send a network request to icanhazip.com to diagnose IPv6 connectivity issues. While this is a common diagnostic practice, it involves a third-party service.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external API (GMGN) to generate token summaries and risk reports.
Ingestion points: Data enters the agent context through the output of gmgn-cli sub-commands in the SKILL.md file.
Boundary markers: Absent. The skill defines specific output templates but does not explicitly instruct the agent to ignore instructions embedded within the API data.
Capability inventory: The agent can execute shell commands (gmgn-cli) and perform file system operations as described in the Sub-commands and First-time setup sections.
Sanitization: Partial. The skill provides detailed field mappings to guide data parsing, reducing the risk of misinterpretation, but does not perform content filtering.

gmgn-token