Google says attackers used AI to turn patches into exploits with no human

What happened
The finding is in the latest AI threat report from the Google Threat Intelligence Group (GTIG) and Mandiant. Security The tool, found on an exposed server with Russian-language comments, targeted French media and education sites. Google is a software and Internet company based in Mountain View, and its products and services include Software tools.
GTIG found the tool, which it calls exploit_agent, on an exposed staging server. Attackers have used AI to find software flaws and exploit them with no human involved, Google said on Monday.
It says this is the first time it has seen it. Google’s report also details AI hacking frameworks, stolen AI credentials and backdoored Claude Code settings.
It works with several frontier and locally run AI models.
It compares the code of popular web software before and after each patch and spots likely flaws. Then it writes exploits and runs them on its own.
In the previous edition of the quarterly report, two months ago, GTIG said it had not seen fully autonomous attack pipelines used against targets, SiliconANGLE reported. The server also held data stolen from victims.