Google: Discovered that attackers are using AI to automatically analyze patches and execute exploits

Nov 16, 2026 22:11:47

According to The Defiant, Google's threat intelligence team discovered that attackers are using an AI framework called exploit_agent to analyze security patches, write, and execute exploit code without human intervention.

Researchers found the framework and data stolen from victims on an exposed relay server. The framework compares the code before and after web application patches are released, identifies potential vulnerabilities, and automatically executes exploits; there are also scripts on the server for internal reconnaissance, brute force attacks, and installing web shells.

Google stated that telemetry data from victims indicates that the operators are interested in websites in the media, entertainment, and education sectors in France. The company did not attribute this framework to any specific organization.

Recent Fundraising

More
Nov 13
$50MNov 10
$11MNov 10

New Tokens

More
Dec 31
Dec 31
SSaturnSTRN
Dec 31

Latest Updates on 𝕏

More
SSolanaFollowedRiftATM
Nov 14
Nov 14