HOT RADAR
agentHEAT 11.5°

AI CURATED HOT STORY · 11/17/2026

Google Warns Fully Automated AI Cyberattacks Have Arrived

1 reports archived1 independent sourcesupdated 11/17/2026, 03:42:13
Synthesis & Latest Updates
1 Sources Cross-Validated

Google's Threat Intelligence Group (GTIG) has for the first time observed attackers fully automating vulnerability discovery and exploitation with no human in the loop, using an exposed AI framework called exploit_agent that connects to multiple language models. Google rates the activity at Level 5, where AI handles several attack stages, and notes these automated attacks currently trade stealth for speed, leaving forensic traces that make them easier to detect.

LATEST/Google's Threat Intelligence Group (GTIG) has for the first time observed attackers fully automating vulnerability discovery and exploitation with no human in the loop, using an exposed AI framework called exploit_agent that connects to multiple language models. Google rates the activity at Level 5, where AI handles several attack stages, and notes these automated attacks currently trade stealth for speed, leaving forensic traces that make them easier to detect.

Hourly heat curve

3 fully observed hours
Now
11.5
Peak
11.904:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. The DecoderT2·78 pts
    • GTIG found an exposed server running exploit_agent, which diffs pre- and post-patch code, identifies vulnerabilities, builds exploits and runs them automatically
    • Activity is rated Level 5, with AI carrying out several attack stages and minimal human involvement
    • Automated attacks trade stealth for speed, leaving forensic traces; targets appear to be French media, entertainment and education sites