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 superagent-ai · Codex Skill · ★ 1.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vibekit safe to install? View the security audit →
VibeKit is the safety layer for your coding agent 🖖 Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in. Website • Docs • Discord 🚀 Quick Start Install the VibeKit CLI globally: Run claude code with enhanced security and tracking ⚡️ Key Features 🐳 Local sandbox - Runs agent output in isolated Docker containers — zero risk to your local setup 🔒 Built-in redaction - Auto-removes secrets, api keys, and other sensitive data completions 📊 Observability - Complete visibility into agent operations with real-time logs, traces, and metrics 🌐 Universal agent support - Works with Claude Code, Gemini CLI, Grok CLI, Codex CLI, OpenCode, and more 💻 Works offline & locally - No cloud dependencies or internet required — works entirely on your machine 📦 Related Packages Looking to integrate VibeKit into your application? Check out these packages: 📚 VibeKit SDK Run coding agents in secure sandboxes with full control and monitoring. Perfect for building applications that need to execute AI-generated co
| Stars | 1,857 |
| Forks | 248 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 60.757722158849/100 |
| Open Issues | 37 |
| Last Updated | 2026-01-13 |
| Created | 2025-05-14 |
| Platforms | claude-code, cli, codex, gemini, node |
| Est. Tokens | ~2187k |
Looking for a vibekit alternative? If you're comparing vibekit 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.
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of toke
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, com
Explore other popular codex skill tools:
vibekit is Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in.. It is categorized as a Codex Skill with 1.9k GitHub stars.
vibekit is primarily written in TypeScript. It covers topics such as agent, ai, claude-code.
You can find installation instructions and usage details in the vibekit GitHub repository at github.com/superagent-ai/vibekit. The project has 1.9k stars and 248 forks, indicating an active community.
vibekit is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to vibekit on Agent Skills Hub include agentsys, cursor-talk-to-figma-mcp, openpencil. 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: