OpenAI Challenges Anthropic with Open Source Codex Security CLI
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisis ton rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
OpenAI Challenges Anthropic with Open Source Codex Security CLI
OpenAI has released Codex Security CLI. This open-source command-line tool, licensed under Apache 2.0, helps security and development teams to automatically find, confirm, and fix vulnerabilities in code repositories.
Codex Security CLI can:
- Scan repositories
- Compare results across multiple runs
- Verify fixes
- Integrate security checks into CI/CD pipelines
Bulk analysis across multiple repositories is also supported. The tool requires Node.js 22 and Python 3.10 or higher, is currently in beta, and is installed via npm. The documentation covers all commands and output formats.
Codex Security was previously known internally as "Aardvark" and was launched in March 2026 as a research preview for ChatGPT Enterprise, Business, and Edu customers. In April 2026, the system had helped fix over 3,000 critical vulnerabilities, according to OpenAI. Codex Security directly competes with Claude Security from Anthropic, which also scans codebases for vulnerabilities and suggests fixes.
Both tools reflect a growing reality: as AI models provide attackers with more automated capabilities, defenders must adapt.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.