OpenAI has released Codex Security CLI, an open-source command-line tool that helps developers find and fix vulnerabilities in code repositories. Licensed under Apache 2.0, the tool automates the process of identifying, confirming, and resolving security issues across codebases. It supports bulk scanning of multiple repositories and integrates with CI/CD pipelines to enhance security workflows.
The Codex Security CLI requires Node.js 22 and Python 3.10 or higher to operate and is currently in beta, with installation available via npm. The tool's documentation provides comprehensive guidance on commands and output formats. According to OpenAI, by April 2026, the system had helped fix more than 3,000 critical vulnerabilities.
Codex Security was previously known internally as 'Aardvark' and launched in March 2026 as a research preview for ChatGPT Enterprise, Business, and Edu customers. The tool 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.
Source: thedecoder
