Google: AI agent turned a security patch into a working exploit with no human help
MentionsGoogle
A suspected Russian-speaking operator used an AI agent to turn security patches into working exploits with no human in the loop – a first such occurrence, according to the Google Threat Intelligence Group (GTIG) – before ultimately stealing data from victim organizations.
Summary from The Register Security.
Explained
The technology and terms in this story. Learn more
More in Vulnerabilities
Phishing Collects MX Records; Java4Shell OpenJDK RCE (CVE-2026-114938); Optimizely Magecart Compromise (Nov 18 2026)
Podcast8 minSANS Internet Storm Center StormCastjust nowVulnerabilitiesThreat IntelAppSecCVE-2026-114938