OpenAI wants your next security researcher to be a bot - new Aardvark tool finds and fixes software flaws automatically

Date:
Mon, 03 Nov 2025 18:28:00 +0000

Description:
OpenAI boasts a 92% success rate with its new security bot service.

FULL STORY

OpenAI wants your next security researcher to be a bot - and has launched Aardvark , its very own agentic security researcher, powered by ChatGPT.

Now in private beta, the company describes Aardvark as a breakthrough in AI
and security research - an autonomous agent which helps developers and
security teams discover and fix security flaws at scale.

Each year, tens of thousands of new vulnerabilities are discovered across enterprise and open-source codebases, the company said. Defenders face the daunting tasks of finding and patching vulnerabilities before their
adversaries do.

Mimicking human behavior

In benchmark testing on so-called golden repositories (those that contain well-documented vulnerabilities and are used for testing), Aardvark has apparently had a 92% success rate.

Detailing how it works, OpenAI said Aardvark is not unlike a human - but without the need to rest, eat, use the toilet, or an occasional emotional breakdown.

Aardvark looks for bugs as a human security researcher might: by reading
code, analyzing it, writing and running tests, using tools, and more, it
said. By continuously analyzing source code repositories, it can identify vulnerabilities, assess exploitability, prioritize severity, and then propose targeted patches.

While the company stresses the tool is still in beta, it also says its
already showing commendable results. OpenAI has been running it internally
for several months across its codebases and those of external alpha partners, and managed to surface meaningful vulnerabilities which contributed to
OpenAIs defensive posture.

An AI agent is an autonomous AI program that connects to other apps to
perform various tasks automatically. Their popularity has been growing
lately, with different agents being built for different purposes, such as the AI coding agent Zencoder, the Instagram analysis agent (built on Apify), Compuser (an AI that uses the computer), and others.

======================================================================
Link to news story: https://www.techradar.com/pro/security/openais-new-aardvark-tool-finds-and-fix es-software-flaws-automatically

$$
--- SBBSecho 3.28-Linux
* Origin: Capitol City Online (42:17/1)