OpenAI Group PBC has introduced Aardvark, a GPT-5-powered autonomous AI agent designed to identify, verify, and help fix software vulnerabilities in real-time.
Aardvark is described as an "AI security researcher" capable of scanning code repositories, reasoning about potential exploits, and generating validated patches.
Aardvark integrates with platforms like GitHub, supporting both open-source and enterprise environments, and works by analyzing entire repositories to build contextual threat models before scanning new code commits for vulnerabilities.
Author's summary: OpenAI's Aardvark hunts software vulnerabilities.