sandvault: Run AI agents isolated in a macOS user account and sandbox-exec

by webcoyote · Codex Skill · ★ 455

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

How to install sandvault

brew install sandvault
git clone https://github.com/webcoyote/sandvault

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 73/100

Flagged: sudo usage. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

claude-codemacosopenai-codexsandbox

Quick Facts

Stars455
Forks31
LanguageShell
CategoryCodex Skill
LicenseApache-2.0
Quality Score73/100
Open Issues3
Last Updated2026-11-12
Created2025-09-12
Platformsclaude-code, cli, codex, gemini
Est. Tokens~13k

About sandvault

SandVault - Run Claude Code, OpenAI Codex, Google Gemini and shell commands safely in a sandboxed macOS user account SandVault () manages a limited user account to sandbox shell commands and AI agents, providing a lightweight alternative to application isolation using virtual machines.

sandvault alternative? Top 6 similar tools

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

  • open-cowork by OpenCoworkAI · ⭐ 2.3k

    Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — w

  • kicad-happy by aklofas · ⭐ 1.7k

    AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schemati

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • agents by rivet-dev · ⭐ 1.6k

    A durable process per agent, with memory that survives restarts

  • okou by okou-ai · ⭐ 1.2k

    Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, an

  • Mysti by DeepMyst · ⭐ 1.2k

    AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Shell Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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 Codex Skill tools