Google Warns the Era of Autonomous AI Attacks Has Arrived
Google said attackers used autonomous AI agents to compare patched code, write exploits and steal credentials with minimal human involvement.
- According to a new AI Threat Tracker report published by the Google Threat Intelligence Group and Mandiant, threat actors have crossed a major operational threshold by deploying autonomous AI agents to execute end-to-end cyberattacks without human intervention.
- Google researchers documented what they assess to be the first fully automated AI-driven cyberattack—a system dubbed "exploit_agent" linked to a Russian threat actor—which independently handles vulnerability discovery, exploitation, and post-compromise activity.
- The report warns that malicious actors have rapidly evolved beyond basic text prompting to utilizing multi-agent frameworks, including open-source offensive tools like CyberStrikeAI, HexStrike AI, and PentAGI, to connect large language models directly to hundreds of exploitation utilities.
- Google projects that simple attacks executed by multiple AI agents with minimal human oversight could emerge within the next three months, with more sophisticated, fully autonomous agentic campaigns expected within three to six months.
- In response to the accelerating pace of automated exploitation—which saw overall vulnerability disclosures nearly double between January and August 2026—Google stated it has disabled identified malicious assets, strengthened Gemini safety classifiers, and released new defensive hardening guidelines.
125 Articles
125 Articles
Google reports first observed AI-driven cyberattack that automated vulnerability discovery and exploitation
Google says it observed an AI framework autonomously reverse-engineer security patches, develop exploits and compromise French media, entertainment and education websites without human intervention.
Google Says It Caught the First Cyberattack Run Entirely by AI
نُشر هذا المقال أولاً عبر Cedarnews.net. لمتابعة المزيد من الأخبار والتقارير الحصرية، زورونا على موقعنا. Google It Caught: Russian-speaking hackers used artificial intelligence to carry out what Google described as the first fully automated cyberattack. Google. تم نشر هذا الخبر عبر موقع Cedarnews الإخباري. للاطلاع على مزيد من الأخبار العاجلة والتقارير الحصرية، زوروا موقعنا الرسمي.
Russian hackers conduct first ever AI automated cyber attack
ALBAWABA - According to Google’s cyber threat intelligence division on Monday, Russian hackers managed to pull off the first ever fully automated AI cyber attack...
Google finds self-running AI hacking tool with Russian comments in its files
Fully Automated AI Cyberattack 2026: What Google Just Found
Google's threat researchers say they've caught the first fully automated AI cyberattack, run end to end with no human involved. An AI system read software patches, worked out the holes they fixed and attacked websites that hadn't updated yet. Just 69 days earlier, Google said it hadn't seen this in the wild.
Coverage Details
Bias Distribution
- 43% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium































