arc-skill-sandbox

---
name: skill-sandbox
description: Test untrusted skills in an isolated environment before installing. Monitors network access, filesystem writes, environment variable reads, and subprocess calls. Run any skill safely without risking your agent's data or credentials.
user-invocable: true
metadata: {"openclaw": {"emoji": "🏖️", "os": ["darwin", "linux"], "requires": {"bins": ["python3"]}}}
---

# Skill Sandbox

Run untrusted skills in a monitored environment. See exactly what they do before giving them access to your real system.

## Why This Exists

ClawHub has hundreds of skills. Some are malicious. Even after scanning with arc-skill-scanner, you can't catch everything with static analysis. The sandbox lets you run a skill's scripts and observe their behavior at runtime — what network calls they make, what files they access, what environment variables they read.

## Commands

### Sandbox a skill directory
```bash
python3 {baseDir}/scripts/sandbox.py run --path ~/.openclaw/skills/some-skill/
```

### Run a specific script in sandbox
```bash
python3 {baseDir}/scripts/sandbox.py run --script ~/.openclaw/skills/some-skill/scripts/main.py
```

### Run with network monitoring
```bash
python3 {baseDir}/scripts/sandbox.py run --path ~/.openclaw/skills/some-skill/ --monitor-network
```

### Run with fake environment variables
```bash
python3 {baseDir}/scripts/sandbox.py run --path ~/.openclaw/skills/some-skill/ --fake-env
```

### Run with a time limit
```bash
python3 {baseDir}/scripts/sandbox.py run --path ~/.openclaw/skills/some-skill/ --timeout 30
```

### Generate a safety report
```bash
python3 {baseDir}/scripts/sandbox.py report --path ~/.openclaw/skills/some-skill/
```

## What It Monitors

### Filesystem Access
- Files opened (read/write)
- Directories created
- File deletions
- Permission changes

### Environment Variables
- Which env vars are read
- Whether sensitive keys are accessed (API keys, tokens, passwords)
- Option to inject fake values to see what the s