LaunchKit · 2026
Back to Skills

arc-skill-sandbox

Test untrusted skills in an isolated environment before installing.

0
600 downloads
by @trypto1019

Setup & Installation

openclaw skills install @trypto1019/arc-skill-sandbox

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install arc-skill-sandbox

Version History

v1.1.0Feb 17, 2026 - Version note by skill developer:

arc-skill-sandbox 1.1.0 - Updated scripts/sandbox.py (details not included). - No user-facing documentation changes.

What This Skill Does

Runs untrusted skills in a monitored environment before installation. Tracks filesystem access, environment variable reads, network connections, and subprocess calls during execution. Produces a JSON report with a safety verdict (SAFE / SUSPICIOUS / DANGEROUS).

Static analysis misses runtime behavior, so executing the skill in a monitored environment reveals what it actually does with your data and credentials.

When to use it

  • Testing a ClawHub skill before installing it on your real agent
  • Checking if a downloaded script reads API keys or tokens
  • Catching outbound network calls made by an unknown skill
  • Running a skill with fake credentials to detect exfiltration attempts
  • Generating a safety report before a team-wide skill rollout

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: sandbox this skill at ~/.openclaw/skills/some-skill/ and tell me if it's safe to install

AGENT
  1. 1Runs sandbox.py against the skill directory with --monitor-network and --fake-env flags
  2. 2Captures all filesystem operations, environment variable accesses, and outbound network requests
  3. 3Injects fake API keys and tokens to observe whether the skill attempts to exfiltrate them
  4. 4Generates a JSON report listing all observed activity and flags suspicious patterns
  5. 5Returns the safety verdict with a summary of findings
OUTPUT

JSON safety report covering filesystem, network, subprocess, and env var activity with a final SAFE / SUSPICIOUS / DANGEROUS verdict