nemoclaw-user-manage-policy

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute vendor-specific CLI tools, including openshell and nemoclaw, to manage network egress policies and monitor sandbox activity. It also references a local script ./scripts/walkthrough.sh for a guided walkthrough. These operations are consistent with the skill's stated purpose of sandbox policy management.\n- [SAFE]: No malicious patterns, such as prompt injection, obfuscation, or unauthorized data exfiltration, were detected. The use of environment variables like NVIDIA_API_KEY for authentication follows standard and safe practices for development environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:35 PM
Security Audit — agent-trust-hub — nemoclaw-user-manage-policy