nemoclaw-user-manage-policy

Approve or deny blocked sandbox network requests via the OpenShell terminal UI.

22.1k|3.0k|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-manage-policy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nemoclaw-user-manage-policy
Source: https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-user-manage-policy
Command: npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-manage-policy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Operators and developers need a safe, auditable way to handle agent outbound network requests that are blocked by a sandbox policy; this Skill describes how to review those requests in the OpenShell TUI and either allow or deny them and how to update sandbox policies accordingly.

Core Features & Use Cases

  • Interactive approvals: Use the OpenShell terminal UI to inspect blocked requests (host, port, binary, HTTP method/path) and approve or deny them for the running session.
  • Dynamic policy updates: Apply policy YAML files to a live sandbox with the OpenShell CLI to add endpoints without restarting the sandbox.
  • Static baseline edits & presets: Edit the NemoClaw blueprint policy file or merge built-in presets to make persistent changes that survive sandbox restarts.
  • Use Case: Temporarily approve access to an internal API for debugging, then merge the approved endpoint into the baseline policy if it should remain allowed.

Quick Start

Open the OpenShell terminal UI, inspect a blocked request, and approve or deny it to update the running sandbox policy.

Frequently Asked Questions about nemoclaw-user-manage-policy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I approve blocked sandbox network requests for an agent?

To approve blocked sandbox network requests, open the OpenShell terminal UI to inspect the host, port, binary, and HTTP method of the blocked egress, then interactively allow or deny the request for the running session.

What is an OpenShell TUI policy update?

An OpenShell TUI policy update is an interactive process where operators review blocked outbound network requests in a terminal UI and apply dynamic allow or deny decisions that update the running sandbox policy without a restart.

Can I apply policy YAML files to a live sandbox without restarting?

Yes, you can apply policy YAML files to a live sandbox using the OpenShell CLI to dynamically add endpoints to the egress policy without needing to restart the running session.

How do I make persistent baseline egress policy edits in a NemoClaw blueprint?

To make persistent baseline egress policy edits in a NemoClaw blueprint, directly edit the static YAML policy file or merge built-in policy presets to ensure changes survive sandbox restarts.

Does NemoClaw support built-in network policy presets for sandbox onboarding?

Yes, NemoClaw supports built-in network policy presets that can be merged into the baseline YAML blueprint during sandbox onboarding to establish declarative egress control.

When should I use dynamic TUI approvals versus static YAML policy formatting?

Use dynamic TUI approvals for temporary debugging access to endpoints during a live session, and use static YAML policy formatting to permanently add allowed endpoints to the baseline blueprint for future restarts.