amazing-sandbox — security grade SAFE, quality 75/100

Security audit verdict: SAFE · quality 75/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ashishb · Agent Tool · ★ 167

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is amazing-sandbox safe to install? View the security audit →

About amazing-sandbox

Amazing Sandbox () Amazing Sandbox (AS) is for running various tools inside a Docker sandbox. [x] Prevents malicious packages from having full disk access and stealing data [x] Prevents AI agents from mistakenly deleting all files on your disk [x] Optionally, run packages like linters [air-gapped](https://en.wikipe

developer-toolsdevopssecurity-tools

Quick Facts

Stars167
Forks12
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score74.7256175682062/100
Last Updated2026-09-16
Created2025-12-17
Platformsgo
Est. Tokens~17k

Compatible Skills

These tools work well together with amazing-sandbox for enhanced workflows:

  • clampdown — semantic(0.30)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • hotplex — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)
  • leash — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)

amazing-sandbox alternative? Top 6 similar tools

Looking for a amazing-sandbox alternative? If you're comparing amazing-sandbox with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-code-skills by levnikolaevich · ⭐ 564

    Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.

  • code-abyss by telagod · ⭐ 238

    Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CL

  • lazy-bird by yusufkaraaslan · ⭐ 236

    Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut

  • cc-skills by terrylica · ⭐ 74

    Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse mana

  • mcp-nixos by utensils · ⭐ 823

    MCP-NixOS - Model Context Protocol Server for NixOS resources

  • idea-reality-mcp by mnemox-ai · ⭐ 817

    Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ star

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is amazing-sandbox?

amazing-sandbox is Amazing Sandbox - run third-party tools and AI agents securely on your machine. It is categorized as a Agent Tool with 167 GitHub stars.

What programming language is amazing-sandbox written in?

amazing-sandbox is primarily written in Go. It covers topics such as developer-tools, devops, security-tools.

How do I install or use amazing-sandbox?

You can find installation instructions and usage details in the amazing-sandbox GitHub repository at github.com/ashishb/amazing-sandbox. The project has 167 stars and 12 forks, indicating an active community.

What license does amazing-sandbox use?

amazing-sandbox is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to amazing-sandbox?

The top alternatives to amazing-sandbox on Agent Skills Hub include claude-code-skills, code-abyss, lazy-bird. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools