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 GreyhavenHQ · Agent Tool · ★ 286
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is greywall safe to install? View the security audit →
Greywall — Sandbox for AI Coding Agents Greywall is a container-free sandbox for AI coding agents on Linux and macOS, with two complementary modes: — deny-by-default sandbox. Restricts filesystem access, network connections, and system calls to only what you explicitly allow, so tools like Claude Code, Cursor, Codex, and other AI agents can't reach your SSH keys, secrets, or anything outside the working directory. — allow-by-default observability layer (equivalent to ). Skips profile loading, registers a allow rule with greyproxy so every network request is accepted but logged on the dashboard, and runs with a permissive filesystem. Use it to see what a tool actually does before deciding what to lock down. Both modes route every network connection through greyproxy — a transparent proxy with a live allow
| Stars | 286 |
| Forks | 34 |
| Language | Go |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 71.9883840158261/100 |
| Open Issues | 23 |
| Last Updated | 2026-08-13 |
| Created | 2026-03-04 |
| Platforms | claude-code, go |
| Est. Tokens | ~18k |
These tools work well together with greywall for enhanced workflows:
Looking for a greywall alternative? If you're comparing greywall 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.
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an ad
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Run AI coding agents in hardened container sandboxes.
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across
Explore other popular agent tool tools:
greywall is Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS. It is categorized as a Agent Tool with 286 GitHub stars.
greywall is primarily written in Go. It covers topics such as agents, ai-security, claude-code.
You can find installation instructions and usage details in the greywall GitHub repository at github.com/GreyhavenHQ/greywall. The project has 286 stars and 34 forks, indicating an active community.
greywall is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to greywall on Agent Skills Hub include toolhive-studio, claude-forge, 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: