Skip to main content
See every side of every news story
Published • loading... • Updated

Google Finds Adverse AI Framework Designed to Automate Exploits

Summary by TechInformed
An exposed staging server held the software alongside stolen victim data, but Google did not establish whether the two were connected
DisclaimerThis story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.

4 Articles

“Imagine a hacker who doesn’t eat, doesn’t sleep, doesn’t get tired, and never stops looking for a way to attack.” The article Google’s dramatic discovery: AI cyberattacks have become autonomous for the first time appeared first on Documento.

Google's threat researchers have identified exploit_agent, an AI tool that exploits software vulnerabilities without human intervention. Jason Wei has joined Mercor as a principal scientist.

Google has discovered for the first time an unattended AI vulnerability exploit pipeline where the AI agent automatically analyzes patches and generates and executes attack code.

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • There is no tracked Bias information for the sources covering this story.

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

unsafe.sh broke the news on Wednesday, November 18, 2026.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal