Xpersona
P

Python Executor

CLAWHUB · Unverified

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSo... Skill: Python Executor Owner: okaris Summary: Execute Python code in a safe sandboxed environment via $1. Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSo... Tags: latest:0.1.5 Version history: v0.1.5 | 2026-02-18T08:29:06.215Z | auto - Added detailed documentation in SKILL.md, including usage examples, input schema, and pre-installed library list. - Clarified environment specs, supported triggers, and

62
Rank
84
Safety
10k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 10.5K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: medium.

clawhub skill install s1737xapsjy8k5qnagtfyf5nrx85t72x:python-executor
  1. Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-okaris-python-executor-executor-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

16,691 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: python-executor
description: "Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib"
allowed-tools: Bash(infsh *)
---

# Python Code Executor

Execute Python code in a safe, sandboxed environment with 100+ pre-installed libraries.

![Python Code Executor](https://cloud.inference.sh/u/33sqbmzt3mrg2xxphnhw5g5ear/01k8d8b4mckh6z89dhtxh72dsz.png)

## Quick Start

```bash
curl -fsSL https://cli.inference.sh | sh && infsh login

# Run Python code
infsh app run infsh/python-executor --input '{
  "code": "import pandas as pd\nprint(pd.__version__)"
}'
```

> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture, downloads the matching binary from `dist.inference.sh`, and verifies its SHA-256 checksum. No elevated permissions or background processes. [Manual install & verification](https://dist.inference.sh/cli/checksums.txt) available.

## App Details

| Property | Value |
|----------|-------|
| App ID | `infsh/python-executor` |
| Environment | Python 3.10, CPU-only |
| RAM | 8GB (default) / 16GB (high_memory) |
| Timeout | 1-300 seconds (default: 30) |

## Input Schema

```json
{
  "code": "print('Hello World!')",
  "timeout": 30,
  "capture_output": true,
  "working_dir": null
}
```

## Pre-installed Libraries

### Web Scraping & HTTP
- `requests`, `httpx`, `aiohttp` - HTTP clients
- `beautifulsoup4`, `lxml` - HTML/XML parsing
- `selenium`, `playwright` - Browser automation
- `scrapy` - Web scraping framework

### Data Processing
- `numpy`, `pandas`, `scipy` - Numerical computing
- `matplotlib`, `seaborn`, `plotly` - Visualization

### Image Processing
- `pillow`, `opencv-python-headless` - Image manipulation
- `scikit-image`, `imageio` - Image algorithms

### Video & Audio
- `moviepy` - Video editing
- `av` (PyAV), `ffmpeg-python` - Video processing
- `pydub` - Audio manipulation

### 3D Processing
- `trimesh`, `open3d` - 3D mesh processing
- `numpy-stl`, `meshio`, `pyvista` - 3D file formats

### Documents & Graphics
- `svgwrite`, `cairosvg` - SVG creation
- `reportlab`, `pypdf2` - PDF generation

## Examples

### Web Scraping

```bash
infsh app run infsh/python-executor --input '{
  "code": "import requests\nfrom bs4 import BeautifulSoup\n\nresponse = requests.get(\"https://example.com\")\nsoup = BeautifulSoup(response.content, \"html.parser\")\nprint(soup.find(\"title\").text)"
}'
```

### Data Analysis with Visualization

```bash
infsh app run infsh/python-executor --input '{
  "code": "import pandas as pd\nimport matplotl

_meta.json

{
  "ownerId": "kn7c1hgfycdfnrf5w8mp3pf1jd808pjv",
  "slug": "python-executor",
  "version": "0.1.5",
  "publishedAt": 1771403346215
}

skill-card.md

## Description:

Execute Python code through inference.sh in a sandboxed Python 3.10 environment with pre-installed libraries for data processing, web scraping, media processing, document generation, API calls, and automation.

This skill is ready for commercial/non-commercial use.

## Publisher:

[okaris](https://clawhub.ai/user/okaris)

### License/Terms of Use:


## Use Case:

Developers and agents use this skill to run bounded Python scripts for data analysis, scraping, image, video, and 3D processing, PDF generation, API calls, and automation without managing a local Python environment.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The documented quick start pipes a mutable remote installer into a shell.

Mitigation: Download and inspect the CLI installer separately, verify its checksum against the published checksums, and run it only when the inference.sh delivery path is trusted.

Risk: Executed Python code can contact external services or process sensitive data if the submitted script does so.

Mitigation: Review code before execution and avoid passing secrets or private data unless outbound service calls are intended.

Risk: Generated files and captured output may reflect untrusted web, API, or user-provided input.

Mitigation: Review returned files and stdout before using them in downstream workflows.

## Reference(s):

- [Python Executor on ClawHub](https://clawhub.ai/okaris/skills/python-executor)
- [Running Apps](https://inference.sh/docs/apps/running)
- [App Code](https://inference.sh/docs/extend/app-code)
- [Sandboxed Code Execution](https://inference.sh/blog/tools/sandboxed-execution)
- [CLI Checksums](https://dist.inference.sh/cli/checksums.txt)

## Skill Output:

**Output Type(s):** [Text, Code, Shell commands, Files, Configuration]

**Output Format:** [Markdown guidance with inline bash and JSON examples; executed app responses may include stdout text and generated files.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Python code supports a 1-300 second timeout, optional output capture, an optional working directory, and automatic return of files saved under outputs/.]

## Skill Version(s):

0.1.5 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to Python Executor and adjacent AI workflows.