nemoclaw-user-get-started

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs users to download and execute shell scripts directly by piping remote content to bash or sh. These scripts originate from the vendor's official domain (nvidia.com) and a well-known service provider (ollama.com).
  • [COMMAND_EXECUTION]: Guidance includes commands for system-level configuration, such as using sudo for Docker installation, adding users to the docker group, and utilizing the Invoke-WebRequest command in PowerShell with an -ExecutionPolicy Bypass flag to run a bootstrap script.
  • [EXTERNAL_DOWNLOADS]: Fetches installation assets and configuration scripts from the vendor's GitHub repository and official domains. These downloads are integral to the stated purpose of the skill as an installer.
  • [CREDENTIALS_UNSAFE]: The documentation provides guidance on configuring API keys for various services (OpenAI, Anthropic, Google, etc.). It correctly recommends the use of environment variables and non-interactive setup for credential management rather than hardcoding secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:41 PM
Security Audit — agent-trust-hub — nemoclaw-user-get-started