Search

Lybic Sandbox is a cloud sandbox built for agents and automation workflows. Think of it as a disposable cloud computer you can spin up on demand. Agents can perform GUI actions like seeing the screen,

Setup multi-agent sandbox infrastructure with Docker, Discord, SSH, and Tailscale. Use when: (1) creating a sandboxed agent for cross-gateway collaboration,...

--- name: prts-sandbox description: Isolated Kali Linux sandbox for running pentest tools and risky commands safely. metadata: {"openclaw":{"emoji":"🛡️","requires":{"bins":["bash","curl","jq"]}}}

Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini,

Run browser operations and untrusted code in a secure Novita cloud sandbox (Firecracker VM). Use when: (1) browsing any external URL or website, (2) executin...

Run browser operations and untrusted code in a secure PPIO cloud sandbox (Firecracker VM). Use when: (1) browsing any external URL or website, (2) executing...

A generic skill that provides a secure, temporary Docker sandbox for executing generated code (Python, Node.js, bash, etc.). Agents can use this to verify th...

Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.

A desktop sandbox lets OpenClaw run as natively as on a real OS, ensuring full functionality with safe isolation.Run OpenClaw without breaking your PC.

Sandboxed ClawHub skill installation with automated security scanning. Use when: (1) Installing any new skill from ClawHub, (2) Auditing an already-installed...

A generic skill that provides a secure, temporary Docker sandbox for executing generated code (Python, Node.js, bash, etc.). Agents can use this to verify th...

Execute JavaScript code in a secure sandbox for data processing, computation, and quick expression evaluation without network or filesystem access.

Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini,

Set up the initial file system for a new sandbox. Fetches the account's organizations and artists via the Recoup CLI and scaffolds an opinionated folder stru...

Set up the initial file system for a new sandbox. Fetches the account's organizations and artists via the Recoup CLI and scaffolds an opinionated folder stru...

Creates snapshots of critical config files, validates JSON configs for syntax and keys, and generates audit logs without applying changes.

沙盘推演系统：模拟多人物社交对话互动。基于 sessions_spawn 能力实现并行推演， 支持10+人物、5个并行session、分批调度。用户可作为干预者暂停、修改

Test untrusted skills in an isolated environment before installing. Monitors network access, filesystem writes, environment variable reads, and subprocess ca...

Test untrusted skills in an isolated environment before installing. Monitors network access, filesystem writes, environment variable reads, and subprocess ca...

Control E2B Desktop sandboxes (virtual Linux desktops) for computer-use agents. Use when you need to create/manage sandboxed desktop environments, take scree...

--- name: multi-user-workspace description: Multi-user workspace management with sandbox permissions, user profiles, and relationship networks. --- # Friends Configure per-user sessions with sandbox

AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, knowledge bridge, zero-trust security, multi-tier sandboxing...

Scans the skills folder for new, unused, or missing dependencies; fixes requirements.txt; and tests a skill in or out of sandbox.

Use Codex safely for repo-aware coding with explicit approvals, sandbox choices, MCP boundaries, and PR-ready verification workflows.