Introducing Aardvark: OpenAI’s agentic security researcher

OpenAI has introduced Aardvark, an agentic security researcher designed to autonomously identify and analyze security vulnerabilities. This AI agent enhances cybersecurity by automating complex research tasks that typically require human expertise. Aardvark's development marks a significant step in using AI agents to improve digital safety and protect systems more efficiently.

ArchiveLaunch

Signal trust

Single sourceEarly signal

PublishedThursday, October 30, 2025 at 12:00 PMOct 30, 12:00 PM

FreshnessArchive

Story ID#229

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

OpenAI introduces Aardvark, an AI-powered security researcher that autonomously finds, validates, and helps fix software vulnerabilities at scale. The system is in private beta—sign up to join early testing.

Now in private beta: an AI agent that thinks like a security researcher and scales to meet the demands of modern software.

March 6, 2026 Update: Aardvark is now Codex Security, and is available as a research preview.

Opening the briefing

Introducing Aardvark: OpenAI’s agentic security researcher

Original article excerpt