TechPrufer
Get started
OpenAI
OpenAI logoOpenAI · Feature trail

Codex Security

1 post · Aug 2026

What this trail covers

This post continues the evolution of OpenAI's capabilities for enhancing cybersecurity defenses through AI-powered tools and workflows. It details the integration of ChatGPT, Codex Security, and the open-source Codex Security CLI to streamline the process of working through a security backlog. New workflows include investigating findings in ChatGPT, reviewing pull requests with Codex Security Review, conducting repository-wide investigations with the Codex Security plugin, setting up continuous analysis with Codex Security cloud, triaging existing alerts, and generating verified fixes. The post also emphasizes building security checks into existing tools via the CLI and SDK, and introduces a bulk-scanning workflow for multiple repositories and large codebases.

All OpenAI trails
  1. Scaling cyber defenders with Daybreak | OpenAI DevelopersThis post details new workflows and enhancements for OpenAI's Codex Security product, focusing on practical application for "approved defenders." It introduces specific use cases for ChatGPT in security investigations, elaborates on the functionality of Codex Security Review for pull requests, and expands on the capabilities of the Codex Security plugin for repository-wide scans and continuous analysis. The post also highlights the integration of existing alerts into an actionable queue via the triage backlog feature and the process of generating verified fixes with regression tests. Furthermore, it introduces the open-source Codex Security CLI and TypeScript SDK for building security checks into CI/CD pipelines and internal tools, and describes a bulk-scanning workflow for managing security across multiple repositories.