Mlq.Ai Google Reports First Fully Autonomous AI Cyberattack Using exploit_agent
Article Content
- •First observed case of fully autonomous AI exploitation without human oversight.
- •The exploit_agent framework automates vulnerability discovery and exploitation targeting n-day vulnerabilities.
- •Attackers are leveraging AI to significantly reduce the time organizations have to apply security patches.
Google's Threat Intelligence Group (GTIG) has identified the first instance of an autonomous AI framework, named exploit_agent, that can fully automate the process of discovering and exploiting software vulnerabilities without human intervention. This framework continuously compares code before and after security patches to identify vulnerabilities, drafts exploits, and executes them automatically. The attack has primarily targeted French websites in the media, entertainment, and education sectors. The report highlights a significant shift in cyberattack methodologies, with attackers leveraging AI to exploit known vulnerabilities, referred to as n-day vulnerabilities, at speeds. The GTIG report indicates that the patch window for organizations is shrinking, as attackers can now weaponize vulnerabilities faster than patches can be applied. The framework was discovered on an exposed staging server, which also contained stolen data and scripts for post-compromise activities. GTIG warns that this trend may lead to more sophisticated attacks in the near future.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (41)
Following this threat?
Track APT42, Sombermeme and Google in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Common questions
What is the exploit_agent framework?
Which sectors are primarily targeted by these attacks?
How does this affect the patching process for organizations?
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…