# Introducing Aardvark: OpenAI's agentic security researcher

DevFeed: [Introducing Aardvark: OpenAI's agentic security researcher](<https://devfeed.tech/articles/introducing-aardvark-openai-s-agentic-security-researcher-6475.md>)

Original publisher: [Read original article](<https://openai.com/index/introducing-aardvark>)

Published: 2025-10-30T11:00:00Z

Content type: article

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Security](<https://devfeed.tech/topics/security.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [Software](<https://devfeed.tech/topics/software.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [ai](<https://devfeed.tech/tags/ai.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [llm](<https://devfeed.tech/tags/llm.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [openai](<https://devfeed.tech/tags/openai.md>), [security](<https://devfeed.tech/tags/security.md>), [testing](<https://devfeed.tech/tags/testing.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

## AI overview

OpenAI introduces Aardvark, an autonomous security researcher powered by GPT-5. It continuously analyzes code repositories and commits to identify vulnerabilities, assess exploitability, prioritize severity, explain findings, and propose targeted patches. Aardvark uses LLM-powered reasoning and tool use rather than traditional fuzzing or software composition analysis, and validates potential vulnerabilities in an isolated sandbox. The article says Aardvark is available in private beta, with an update stating that it is now Codex Security and available as a research preview.

## Source excerpt

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.