airlock — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 airlock-hq · Codex Skill · ★ 86

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

🔒 Is airlock safe to install? View the security audit →

About airlock

Airlock [!WARNING] This project is deprecated. Development has moved to kunchenguid/no-mistakes. Please use that repository instead. This repo is no longer actively maintained. []() All slop must die. Airlock is where every git push turns into a slop-free PR. Airlock is a local Git proxy that intercepts , runs your code through a customizable validation pipeline, and lets you approve before anything is pushed to remote. Think of it as an airlock between your local repo and the outside world. mermaid flowchart LR subgraph before[" Before "] direction TB A["Local Repo"] -- "git push" -- B["Remote Branch"] B -- "dirty pull request" -- C["CI + Code Review"] C -- "fail / request changes" -- A end subgrap

agentic-engineeringagentsaicicicdclaude-codecodexlocal

Quick Facts

Stars86
Forks6
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score63.9250419994617/100
Open Issues3
Last Updated2026-05-09
Created2026-02-24
Platformsclaude-code, codex, rust
Est. Tokens~936k

airlock alternative? Top 6 similar tools

Looking for a airlock alternative? If you're comparing airlock 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.

  • kindly-web-search-mcp-server by Shelpuk-AI-Technology-Consulting · ⭐ 388

    Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • turbo-flow by marcuspat · ⭐ 174

    SUPERSEDED by Turbo Rig (marcuspat/rig) — retained as the DevPod/Codespaces devcontainer seed. Was: one-comman

  • codex-cli-hooks by shanraisshan · ⭐ 66

    codex cli hooks - adding voice on each hook

  • codebase-argus by AaronZ345 · ⭐ 58

    Multi-agent codebase review for PRs, CI, and downstream fork syncs.

  • ai-skills by sanjay3290 · ⭐ 422

    24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is airlock?

airlock is All slop must die. Airlock is where every git push turns into a slop-free PR.. It is categorized as a Codex Skill with 86 GitHub stars.

What programming language is airlock written in?

airlock is primarily written in Rust. It covers topics such as agentic-engineering, agents, ai.

How do I install or use airlock?

You can find installation instructions and usage details in the airlock GitHub repository at github.com/airlock-hq/airlock. The project has 86 stars and 6 forks, indicating an active community.

What license does airlock use?

airlock is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to airlock?

The top alternatives to airlock on Agent Skills Hub include kindly-web-search-mcp-server, deepcontext-mcp, turbo-flow. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools