OpenAI releases its security CLI Codex to make AI code reviews accessible for all
The OpenAI team announced the release of their new open source tool called Codex Security CLI, which can help automatically detect and fix vulnerabilities in your repos. So far, it’s fixed over 3,000 critical bugs!
The OpenAI team released Codex Security CLI, an open source command line interface (CLI) for automatically detecting and fixing vulnerabilities in code repositories. The tool is licensed under Apache 2.0 and available through npm. As of April 2026, the tool has already addressed over 3,000 critical vulnerabilities in OpenAI’s internal repositories. This tool is a rival to Anthropic’s Claude Security.
AI security audits are moving from proprietary solutions to becoming a routine part of the development process. Especially important given how much code AI agents are generating these days, and how many bugs they introduce as they do so.
Source: the-decoder.com
Free course
Stop reading about AI — start building with it
The free Claude Code course: your first site, tool or game — no coding. No upsells, no cross-sells — nothing to buy here.
Start free →
Author
Evgenii Arsentev
PhD · Chief Executive Officer, digital health
Articles · Latest articles