NYC
skills/vm0-ai/vm0-skills/minimax/Gen Agent Trust Hub

minimax

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill uses curl to make HTTP requests to the MiniMax API. While it uses bash -c to ensure environment variables are handled correctly, the commands are transparent and target legitimate service endpoints.\n- DATA_EXFILTRATION (SAFE): Network activity is directed only to the official MiniMax API domains (api.minimax.io and api.minimaxi.chat) as required for the skill's primary function.\n- CREDENTIALS_UNSAFE (SAFE): The skill correctly uses the vm0_secrets metadata to manage the MINIMAX_API_KEY, ensuring that sensitive credentials are not hardcoded or exposed in the skill content itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:29 PM