nemoclaw-user-guide

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is authored by a trusted vendor and exclusively references official documentation and tools hosted on the vendor's own infrastructure (nvidia.com).
  • [SAFE]: Instructions include proactive security measures, explicitly forbidding the agent from requesting user secrets or credentials and mandating the use of redacted placeholders in examples.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation indices and content from official NVIDIA domains. These downloads are part of the core functionality and target well-known, trusted sources.
  • [COMMAND_EXECUTION]: The skill provides instructions for configuring MCP servers and assisting with CLI tasks. It includes a specific safety requirement that agents must explain any command and obtain user permission before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 11:29 AM
Security Audit — agent-trust-hub — nemoclaw-user-guide