nemoclaw-user-deploy-remote

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected within the skill files.
  • [COMMAND_EXECUTION]: The skill provides documented shell commands for deployment, instance management, and sandbox monitoring (e.g., nemoclaw deploy, ssh, openclaw), which are consistent with the stated administrative purpose.
  • [EXTERNAL_DOWNLOADS]: References and links target official NVIDIA and Brev domains (nvidia.com, brev.nvidia.com) for deployment and documentation, which is expected given the skill's authorship.
  • [SAFE]: The skill includes explicit security guidance in the sandbox-hardening.md reference, documenting the use of Linux capability drops, process limits (ulimits), and Landlock filesystem policies to secure the agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:42 PM
Security Audit — agent-trust-hub — nemoclaw-user-deploy-remote