Google reveals AI agents can now automatically turn patches into exploits
Original headline: Google: AI agent turned a security patch into a working exploit with no human help — theregister.com
More in Cybersecurity news
Google's Threat Intelligence Group has documented what they call a 'first': a suspected Russian-speaking threat actor successfully using a fully autonomous AI agent to turn security patches into working exploits without any human involvement. The framework, dubbed 'exploit_agent,' was found on an exposed staging server. It was configured to continuously analyze popular web application software by comparing code before and after security updates, identifying vulnerabilities, developing exploits, and then automatically executing them.
The AI agent successfully stole data from victim organizations, with evidence suggesting a focus on French media, entertainment, and education websites. This marks a significant escalation from previous quarters, moving beyond simple LLM prompting to fully autonomous, multi-agent offensive frameworks. The development lowers the barrier to entry for sophisticated attacks, meaning defenders must now prepare for automated, AI-driven exploitation cycles that can react to patches in near real-time.
Read the original at theregister.com
Satirical commentary on real tech news, summarised with AI. Read the original source for the facts. How ZeroDaily works
