Introducing Aardvark: OpenAI’s agentic security researcher

OpenAI introduced Aardvark, an autonomous security researcher powered by GPT-5.

It scans repositories, prioritizes and validates vulnerabilities, and suggests patches through Codex integration.

The tool was later renamed Codex Security and is available as a research preview for ChatGPT Enterprise, Business, and Edu customers.

It could help developers and security teams find and fix vulnerabilities faster across large codebases.