skills/gmgnai/gmgn-skills/gmgn-track/Gen Agent Trust Hub

gmgn-track

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'gmgn-cli' package from the NPM registry. This tool is provided by the vendor ('gmgnai') to interact with their API and is necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The instructions include running 'ifconfig' or 'ip addr' to identify network interface configurations and 'gmgn-cli' commands to fetch data. These are used for legitimate diagnostics and core functionality.
  • [DATA_EXFILTRATION]: The skill suggests querying 'icanhazip.com' to determine if the user is connecting via IPv6. This is a standard procedure for troubleshooting network routing issues and does not involve the exfiltration of sensitive information.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from the GMGN API (such as token symbols, names, and wallet labels) and displays it to the agent.
  • Ingestion points: Data is received through the 'gmgn-cli' output from the GMGN API.
  • Boundary markers: None are explicitly defined in the instructions to separate API data from the agent's internal reasoning.
  • Capability inventory: The agent can execute 'gmgn-cli' commands, perform network diagnostics, and update its configuration.
  • Sanitization: No explicit sanitization or filtering of API-returned strings is mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 02:47 AM