88Z AI, 17 November — Google’s Threat Intelligence Group has detected fully automated cyberattacks requiring no human intervention. An AI framework named “exploit_agent” automatically compares patch code, builds exploits, and executes them. This milestone signals a new era of cyber threats with rapidly escalating risks.
At a glance
- Google detects first fully automated vulnerability exploitation without human input
- AI framework “exploit_agent” autonomously compares code and executes attacks

First Detection of Fully Automated Attacks
Google’s Threat Intelligence Group has identified the first instance of vulnerability discovery and exploitation conducted entirely without human involvement. The attack chain was driven independently by AI, marking a significant shift in offensive cyber capabilities.
AI Agent Builds Exploits Autonomously
The AI framework, identified as “exploit_agent,” was found on an exposed server. It automatically compared code versions before and after patches to identify vulnerabilities, then constructed and executed exploits on its own. This end-to-end automation significantly accelerates attack timelines.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- the-decoder.comSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.