sandbox

Run Python, Node.js, and Java code in an isolated /workspace environment.

5|2|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/s1366560/agi-demos --skill sandbox-s1366560
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sandbox
Source: https://github.com/s1366560/agi-demos/tree/main/sandbox-mcp-server
Command: npx skills add https://github.com/s1366560/agi-demos --skill sandbox-s1366560

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pdf2image, pillow, imageio, numpy, openpyxl, pandas, python-docx, playwright, markitdown, matplotlib, seaborn, scipy, aiohttp, aiofiles, pydantic, watchfiles, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a secure, isolated environment to run code, manage files, and interact with development tools without compromising your system.

Core Features & Use Cases

  • Code Execution: Run Python, Node.js, Java scripts and commands.
  • File System Operations: Read, write, edit, search, and manage files within a dedicated workspace.
  • Remote Desktop & Terminal: Access a full XFCE desktop environment or a web-based terminal for interactive use.
  • Use Case: Debug a Python script that interacts with local files, test a Node.js application, or explore a project's codebase using a remote graphical interface.

Quick Start

Use the sandbox skill to read the contents of the file named 'README.md'.

Frequently Asked Questions about sandbox

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

FAQPage Schema
How do I run Python and Node.js scripts in an isolated environment?

To run code in an isolated environment, you can execute Python, Node.js, and Java scripts securely within a dedicated sandbox workspace that prevents system compromise.

Can I access a remote desktop or web terminal for interactive development?

Yes, interactive development is supported through a full XFCE remote desktop environment and a web-based ttyd terminal, allowing direct graphical and command-line access.

How do I manage files securely during code execution without affecting my local system?

Secure file management is achieved by restricting all read, write, and search operations to an isolated /workspace directory, ensuring your local system remains unaffected.

Does the sandbox environment support data processing libraries like pandas and matplotlib?

The environment supports data processing libraries like pandas and matplotlib, alongside others such as scipy and numpy, for executing complex data analysis and visualization scripts.

What are the limitations of using a web-based sandbox for development environment testing?

The main limitation is that file system operations are strictly isolated within the /workspace directory, meaning scripts cannot access or modify files outside this designated boundary.

How do I debug a Python script that interacts with local files in a secure execution environment?

You can debug Python scripts by running them in the secure execution environment while using the integrated file system operations to interact with files located in the /workspace directory.