Skip to content
TakoAPI
Back to skills

arc-skill-sandbox

by trypto1019

Health & Fitness
600Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Test untrusted skills in an isolated environment before installing.

Description

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

INPUT

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

AGENT
  1. 1

    Runs sandbox.py against the skill directory with --monitor-network and --fake-env flags

  2. 2

    Captures all filesystem operations, environment variable accesses, and outbound network requests

  3. 3

    Injects fake API keys and tokens to observe whether the skill attempts to exfiltrate them

  4. 4

    Generates a JSON report listing all observed activity and flags suspicious patterns

  5. 5

    Returns 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

Installation

clawhub install trypto1019/arc-skill-sandbox

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links