sandbox

Name: sandbox Review
Item: sandbox
Rating: 2.3
Author: Aaron Matthews

Skill Development Poor

Works inClaude Code

Poor Scanned — metadata only

Enables safe execution of untrusted AI-generated code with minimal latency and resource overhead, reducing deployment risk and enabling broader autonomous ag…

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Run untrusted code snippets safely without risking your development environment
Execute multiple isolated test environments simultaneously for faster CI/CD pipelines
Spin up temporary sandboxed VMs for AI agents to experiment with code safely

85 starsAGPL-3.0 (check with legal)FreeQuick setup

Below standard — Significant caveats apply. Not recommended without careful review of the security and evaluation sections.

Why it matters

Enables safe execution of untrusted AI-generated code with minimal latency and resource overhead, reducing deployment risk and enabling broader autonomous agent use cases in production environments.

Best for

Platform teams deploying AI agents or code generation tools requiring isolated, on-demand compute sandboxes.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/cocoonstack/sandbox

By cocoonstack

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

claude plugins install cocoonstack/sandbox

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

After installing, paste this into Claude:

Help me run untrusted code snippets safely without risking my development environment

CostFree

Trust Signals Auto-scanned

Stars85Contributors5Last updated2026-10-24LicenseAGPL-3.0 (check with legal)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-10-25 · scanner v1

Community Pulse Growing

Discussed on Hacker News

QBittorrent breaks out of sandbox to commit crimes — Hacker News · 1355 pts
Agent Safehouse – macOS-native sandboxing for local agents — Hacker News · 823 pts
Actively exploited sandbox RCE in all Chromium versions — Hacker News · 805 pts

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 61 GitHub stars; contributors unknown; last commit 0d ago; license AGPL-3.0.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
License (AGPL-3.0) may restrict commercial use. Check with your legal team.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

1/5

Versatility

3/5

Reliability

3/5

Security

3/5

Overall score2.30 / 5.00 PoorEvaluatedSep 2026

Scored from trust signals (evidence-eval-v1): 61 GitHub stars; contributors unknown; last commit 0d ago; license AGPL-3.0.

← Back to the Claude Observatory