开源AI安全工具，可在发货前扫描并修复你vibe编码应用中的漏洞。

CLI + AI 代理插件，适用于 Claude Code、Cursor、OpenCode、Codex 及共享代理技能。

预发布安全门——不是完整的渗透测试平台。扫描源代码，分流噪声，修复重要问题，然后发布门。

网站 ·GitHub ·开发文档 ·命令 ·贡献

与我们交流——一般问题 [email protected] ·赞助与合作 [email protected] ·创始人 [email protected]

---

这是什么

AI工具可以在几分钟内构建应用。它们也能在几分钟内发布安全漏洞。

AXguard会在你发布源代码前读取，告诉你攻击者会调用什么。它作为普通CLI运行，作为编码代理内的斜杠命令运行，作为MCP服务器，代理可以直接调用。一切都运行在你的机器上。

它分为四部分发货：

AXguard

Open-source AI security tool to scan and fix vulnerabilities in your vibe-coded apps before you ship.

CLI + AI agent plugin for Claude Code, Cursor, OpenCode, Codex, and shared Agent Skills.

Pre-ship security gate — not a full pentest platform. Scan source, triage noise, fix what matters, and gate releases before you publish.

Website · GitHub · Dev Docs · Commands · Contributing

Talk to us — general questions [email protected] · sponsorship & partnerships [email protected] · founder [email protected]

---

What it is

AI tools can build an app in minutes. They can also ship security bugs in minutes.

AXguard reads your source before you publish it and tells you what an attacker would reach for. It runs as a plain CLI, as slash commands inside your coding agent, and as an MCP server your agent can call directly. Everything runs on your machine.

It ships in four pieces:

Detection is deterministic: 47 rules across 16 JSON packs, plus five dedicated hunters for the classes that need dataflow rather than pattern matching. Everything after that — triage, verification, attack-path chaining, confidence scoring — is post-processing over those findings.

---

Quick start

Open Claude Code and paste this. Claude does the rest.