Execution Isolation

Community

Safely enforce AI tool call policies.

AuthorYapie0
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Enforces filesystem, network, and command policies on all AI tool calls.

Core Features & Use Cases

  • Policy-based enforcement for filesystem, network, and commands across AI tool invocations.
  • Centralized configuration via ~/.openclaw/openclaw.json to define allow/deny rules and precedence.
  • Safe isolation and guardrails to prevent data leakage, unauthorized access, and unintended executions.

Quick Start

Add the execution-isolation plugin settings to ~/.openclaw/openclaw.json and reload the OpenClaw agent to apply policy enforcement.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Execution Isolation
Download link: https://github.com/Yapie0/safe-openclaw/archive/main.zip#execution-isolation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.