Google says an attacker's AI agent turned patches into exploits with no human

TL;DR

  • Google Threat Intelligence Group says it saw attackers use LLM frameworks to find and exploit vulnerabilities with no human in the loop, for the first time.
  • An exposed server ran exploit_agent, which compares code before and after patches, drafts exploits and runs them; GTIG says victim telemetry on it points to French media, entertainment and education sites.
  • The findings are Google's own, and GTIG says these tools trade stealth for speed, leaving traces defenders can detect.

Read the full story

Sign in with your email to read AI News. It’s free.

Share this story

Explain like I’m 15