A secure, remote sandbox for executing arbitrary Python scripts containing analytical libraries like NumPy, pandas, and requests via AgentPMT.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install secure-python-code-sandbox
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install secure-python-code-sandbox using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Secure Python Code Sandbox?
The Secure Python Code Sandbox provides developer agents with a highly isolated, remote container optimized for executing arbitrary Python scripts. Powered by AgentPMT, this sandbox prevents untrusted scripts from threatening local infrastructure. By offering high-performance computation capabilities alongside foundational data science tooling, the tool satisfies the complex runtime requirements of modern AI systems.
Using this skill alongside other Openclaw Skills configurations allows developers to quickly enable dynamic code execution, API integration, and mathematics on-the-fly. The environment comes pre-loaded with standard libraries like pandas, NumPy, and requests, making it immediate to process analytical files, clean unstructured datasets, or securely execute third-party API handlers.
Secure Python Code Sandbox Use Cases
- On-The-Fly Calculations: Fast arithmetic evaluation and script processing without establishing local runtimes.
- Secure Data Manipulation: Structure and clean massive payloads within an isolated container using NumPy and pandas.
- Dynamic Third-Party Integrations: Run remote HTTP requests safely using requests and return execution standard outputs.
- Sandboxed Agent Logic: Let autonomous agents solve complex programmatic problems, outputting clean logs.
How Secure Python Code Sandbox Works
- Request Formulation: The AI agent writes arbitrary Python code and sets a dynamic configuration timeout in seconds.
- Secure Transmission: The agent interfaces with the AgentPMT main MCP server or REST API framework to relay the task payload.
- Isolated Sandboxed Execution: Code processes within a restricted remote container with libraries like requests, NumPy, and pandas instantly available.
- Structured Return: The container parses stdout, stderr, and the resulting output, returning a clean JSON schema response.
Secure Python Code Sandbox Setup
To activate the Secure Python Code Sandbox, you must first install the core setup tools. Use Openclaw Skills manager or skills.sh to complete the installation.
Install Core AgentPMT Skills via OpenClaw CLI
openclaw skills install what-is-agentpmt
openclaw skills install agentpmt-account-mcp-rest-api-setup
Install via skills.sh Script
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
After setting up, establish your credential configurations on your main Agent Group to communicate with the MCP server at https://api.agentpmt.com/mcp/.
Secure Python Code Sandbox Data Schema & Taxonomy
The invoke action expects strict parameters and returns highly actionable runtime responses.
Schema Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
code |
string | Yes | The Python script code block to execute in the sandbox |
timeout_seconds |
integer | No | Maximum execution duration before termination (Default: 10) |
Return Schema
Execution responses return a JSON object detailing complete execution streams:
stdout: Print statements and runtime console logs.stderr: Code execution errors, traceback traces, and warnings.result: Final object evaluation result.
Secure Python Code Sandbox Advanced Features
- Zero-Config Environments: Instantly access pandas, NumPy, and requests without configuration overhead.
- Strict Sandboxed Containment: Ensure user and AI scripts cannot escape or compromise adjacent files.
- Robust MCP Protocol Support: Integrated tightly with primary tool-search workflows for fast retrieval.
- Granular Run Controls: Terminate long-running commands automatically using precise timeout ceilings.
SKILL.md
Loading
Related Openclaw Skills
Caveman Compress
A specialized token-optimization utility designed to compress natural language memory files into ultra-dense 'caveman' text to maximize LLM context windows without losing structural or technical substance.
Impeccable
Impeccable is a production-grade frontend design and visual iteration skill that enables AI coding agents to craft, polish, and audit exceptional user interfaces.
Baidu Search
A powerful search skill enabling AI agents to query the Baidu AI Search Engine for real-time web results, live information, and documentation.
The Way of Zen (Alan Watts)
An AI agent skill that integrates Alan Watts' classic philosophical text 'The Way of Zen' into your agentic workflow, providing direct access to Eastern wisdom on mindfulness, non-forcing action, and direct experience.
Caveman Mode
Caveman Mode reduces AI token usage by roughly 75% by stripping away conversational filler, articles, and pleasantries while retaining 100% technical accuracy.
Livestream Sales Script Expert
A powerful assistant designed to generate high-converting, engaging, and persuasive livestream sales scripts.
Featured*
