Secure Python Code Sandbox

SKILL.md

---
name: secure-python-code-sandbox
description: "Secure Python Code Sandbox: Execute arbitrary Python code in an isolated sandbox with pre-installed libraries (requests, NumPy, pandas). Returns stdout, stderr, and execution results. Use when an agent needs secure python code sandbox, dynamic code execution, data manipulation, on the fly calculation, api integration, invoke, code, timeout seconds through AgentPMT-hosted remote tool calls. Discovery terms: secure python code sandbox, dynamic code execution, data manipulation."
version: 1.0.0
homepage: https://www.agentpmt.com/marketplace/secure-python-code-sandbox
compatibility: "Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared."
metadata: {"author":"agentpmt","openclaw":{"homepage":"https://www.agentpmt.com/marketplace/secure-python-code-sandbox"}}
---
# Secure Python Code Sandbox

## Freshness
Last updated: `2026-06-10`.

If the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.

## What This Tool Does
For safely executing arbitrary Python code snippets within an isolated, secure environment. The sandbox comes pre-installed with common data science and web request libraries, including requests, NumPy, and pandas. It is ideal for performing quick computations, data transformations, or dynamic API calls without requiring external infrastructure.

## When To Use
- Use this skill for `Secure Python Code Sandbox` on AgentPMT.
- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.
- Search and activation keywords: secure python code sandbox, dynamic code execution, data manipulation, on the fly calculation, api integration, invoke, code, timeout seconds.
- Supported action names: `invoke`.

## Use Cases
- Dynamic Code Execution
- Data Manipulation
- On-the-fly Calculation
- API Integration
- Data Analysis
- Custom Scripting
- Algorithmic Tasks
- Web Scraping

## Categories And Industries
No categories or industry tags are published for this tool.

## Actions And Schema
Complete generated action schema: `./schema.md`.
Supported action count: `1`.
x402 availability: not enabled for this product.

- `invoke` (action slug: `invoke`): For safely executing arbitrary Python code snippets within an isolated, secure environment. The sandbox comes pre-installed with common data science and web request libraries, including requests, NumPy, and pandas. It is ideal for performing quick computations, data transformations, or dynamic API calls without requiring external infrastructure. Price: `10` credits. Parameters: `code`, `timeout_seconds`.

## Live Schema And Examples
Use the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.

- Exact schema: call `agentpmt-tool-search-and-execution` with `action: "get_schema"`, and `tool_id: "secure-python-code-sandbox"`.
- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: "get_instructions"` and `tool_id: "secure-python-code-sandbox"`, or call this product with `action: "get_instructions"` when the product tool is already selected.
- Treat returned live schema and instructions as more specific than this generated summary.

MCP schema lookup through the main AgentPMT MCP server:

```json
{
  "method": "tools/call",
  "params": {
    "name": "AgentPMT-Tool-Search-and-Execution",
    "arguments": {
      "action": "get_schema",
      "tool_id": "secure-python-code-sandbox"
    }
  }
}
```

For live examples, keep the same MCP tool and use these arguments:

```json
{
  "action": "get_instructions",
  "tool_id": "secure-python-code-sandbox"
}
```

Authenticated AgentPMT REST schema lookup body:

```json
{
  "name": "agentpmt-tool-search-and-execution",
  "parameters": {
    "action": "get_schema",
    "tool_id": "secure-python-code-sandbox"
  }
}
```

Authenticated AgentPMT REST live examples body:

```json
{
  "name": "agentpmt-tool-search-and-execution",
  "parameters": {
    "action": "get_instructions",
    "tool_id": "secure-python-code-sandbox"
  }
}
```

## Call This Tool
Product slug: `secure-python-code-sandbox`

Marketplace page: https://www.agentpmt.com/marketplace/secure-python-code-sandbox

- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.
- x402 route: not enabled for this product.
- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.

If those setup skills are not installed beside this product skill, use the downloads below.

Core AgentPMT setup skills:
- What AgentPMT is: ../what-is-agentpmt
  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt
  - OpenClaw install: `openclaw skills install what-is-agentpmt`
  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup
  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup
  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`
  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`

skills.sh install script:

```bash
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
```

MCP call shape after the main AgentPMT MCP server is connected:

```json
{
  "method": "tools/call",
  "params": {
    "name": "Secure-Python-Code-Sandbox",
    "arguments": {
      "action": "invoke",
      "code": "example code",
      "timeout_seconds": 10
    }
  }
}
```

Use the exact tool name returned by `tools/list`; the name above is the expected readable form.

Authenticated AgentPMT REST call body:

```json
{
  "name": "secure-python-code-sandbox",
  "parameters": {
    "action": "invoke",
    "code": "example code",
    "timeout_seconds": 10
  }
}
```

Use the setup skill for the account connection details before making REST calls.

## Response Handling
- Treat the returned JSON as the source of truth for this tool call.
- If the response includes warnings or correction targets, apply them before retrying.
- If the response includes a `passed` or success-style boolean, use it as the workflow gate.
- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.
- If `invoke` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.

## Security
- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.
- Keep tool inputs scoped to the minimum content needed for the task.
- Use the setup skills for credential handling; this product skill only defines product-specific behavior.

## AgentPMT Reference
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/secure-python-code-sandbox
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase