Introducing Aardvark: OpenAI’s agentic security researcher - openai.com

OpenAI has introduced Aardvark, an agentic AI security researcher powered by GPT-5, designed to autonomously identify, validate, and propose fixes for security vulnerabilities at scale. This system has already discovered numerous vulnerabilities, leading to the responsible disclosure of ten issues that received Common Vulnerabilities and Exposures (CVE) identifiers.