Sakhanda Wire
NVDA $153.77 -1.52% MSFT $504.91 -2.53% GOOGL $281.52 -0.78% META $620.99 -0.87% AMZN $256.80 -0.37%
← Back to the news

Google reports fully automated vulnerability attacks

Google’s Threat Intelligence Group (GTIG) says it has identified attackers discovering and exploiting software vulnerabilities without human involvement. The group found an exposed server running an AI framework named “exploit_agent,” which connects to multiple language models. According to GTIG, the system compares code from before and after software patches, detects weaknesses, creates exploits and executes them automatically.

Google rates the activity at Level 5, a stage in which AI tools perform several parts of an attack with only limited human participation. The company warns that more capable attacks could emerge within months. Data from the server indicates that the operator targeted French websites in media, entertainment and education. Russian-language comments in configuration files suggest that the operator speaks Russian, although the article does not identify the person or group involved.

GTIG described the development as a critical change in the cyber threat landscape. It also said that current automated attacks appear to favor speed over concealment. Their activity leaves forensic traces that can make them easier to detect, despite the lack of direct human control during the attack process.

Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.

Originally published by The Decoder on

Read the original on The Decoder ↗

The reporting and the image belong to The Decoder and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news