# OpenAI 开源 Codex Security CLI，可自动修复代码漏洞

- 来源：The Decoder：AI News（RSS）
- 作者：Matthias Bastian
- 发布时间：2026-07-29 19:50
- AIHOT 分数：65
- AIHOT 链接：https://aihot.virxact.com/items/cms6135j814h1robk2ywvn2zc
- 原文链接：https://the-decoder.com/openai-open-sources-codex-security-cli-to-help-developers-find-and-fix-vulnerabilities-from-the-command-line

## AI 摘要

OpenAI 开源了基于 Apache 2.0 许可的命令行工具 Codex Security CLI，可自动扫描、确认并修复代码仓库中的漏洞。该工具支持批量扫描、CI/CD 集成，需 Node.js 22 和 Python 3.10 以上环境，通过 npm 安装。截至 2026 年 4 月，该系统已帮助修复超过 3,000 个严重漏洞。

## 正文

OpenAI has released Codex Security CLI. The open-source command-line tool, licensed under Apache 2.0, helps security and development teams automatically find, confirm, and fix vulnerabilities in code repositories. Codex Security CLI can scan repositories, compare results across multiple runs, verify fixes, and plug security checks into CI/CD pipelines. Bulk scans across multiple repositories are also supported. The tool requires Node.js 22 and Python 3.10 or higher, is currently in beta, and installs via npm. The documentation covers all commands and output formats.

Codex Security was previously known internally as "Aardvark" and launched in March 2026 as a research preview for ChatGPT Enterprise, Business, and Edu customers. By April 2026, the system had helped fix more than 3,000 critical vulnerabilities, according to OpenAI. Codex Security competes directly with Anthropic's Claude Security, which also scans codebases for vulnerabilities and suggests patches. Both tools reflect a growing reality: as AI models give attackers more automated capabilities, defenders need to keep up.

AI News Without the Hype – Curated by Humans