Flagged: installs a background service, sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by clawkwork · Codex Skill · ★ 973
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is clawk safe to install? View the security audit →
Give a coding agent its own disposable Linux machine, not yours. -lightgrey) Install · Quickstart · Why a VM? · How it works · Compared to · FAQ · Docs A coding agent is only useful when you let it actually do things: install packages, run the code it writes, start servers, use the network. On your own machine that leaves two bad options. You approve every command (and babysit a prompt every few seconds), or you run and hope nothing important is one or one leaked token away. clawk is a third option. into a repo, type , and Claude Code (or Codex, or a shell) is working inside a disposable Linux VM (your code mounted in, root in the guest, no permission prompts) while your files, your keychain, and the rest of your machine stay out of reach. The agent ge
| Stars | 973 |
| Forks | 36 |
| Language | Go |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67.1051076037278/100 |
| Last Updated | 2026-08-13 |
| Created | 2026-07-06 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~20k |
These tools work well together with clawk for enhanced workflows:
Looking for a clawk alternative? If you're comparing clawk 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.
Isolated VM environment for running Claude Code and Codex
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t
Fast, red-teaming browser built for AI agents, with direct HTTP traffic control, sandboxed execution, and audi
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C
Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrou
Explore other popular codex skill tools:
clawk is Give coding agents a disposable Linux VM, not your laptop. It is categorized as a Codex Skill with 973 GitHub stars.
clawk is primarily written in Go. It covers topics such as agent-sandbox, ai-agent-sandbox, ai-agents.
You can find installation instructions and usage details in the clawk GitHub repository at github.com/clawkwork/clawk. The project has 973 stars and 36 forks, indicating an active community.
clawk is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to clawk on Agent Skills Hub include coop, sandbox-agent, code-on-incus. 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: