Flagged: reads sensitive env vars. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by afshinm · MCP Server · ★ 698
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is zerobox safe to install? View the security audit →
🫙 Zerobox Sandbox any command with file, network, and credential controls. Lightweight, cross-platform process sandboxing powered by OpenAI Codex's sandbox runtime. Deny by default: Writes, network, and environment variables are blocked unless you
| Stars | 698 |
| Forks | 40 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 70.1556521566221/100 |
| Open Issues | 9 |
| Last Updated | 2026-05-17 |
| Created | 2026-03-17 |
| Platforms | cli, codex, mcp, rust |
| Est. Tokens | ~168k |
Looking for a zerobox alternative? If you're comparing zerobox with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
nono - a capability-based, multiplexing sandbox tool, built for developers - lift'n'shift seamless path to pro
A security scanner for your LLM agentic workflows
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi
Explore other popular mcp server tools:
zerobox is Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.. It is categorized as a MCP Server with 698 GitHub stars.
zerobox is primarily written in Rust. It covers topics such as ai-agents, cli, llm.
You can find installation instructions and usage details in the zerobox GitHub repository at github.com/afshinm/zerobox. The project has 698 stars and 40 forks, indicating an active community.
zerobox is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to zerobox on Agent Skills Hub include onecli, agentseal, nono. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: