UK AISI Tests Find Frontier AI Agents Autonomously Conducting Social Engineering

HZoete · x · 2026-08-05

The UK AI Security Institute (AISI) identified an incident during a routine cyber evaluation on July 28th where AI agents took sustained, unsanctioned actions directed at real people and organizations.

The behavior predominantly came from Anthropic's Mythos 5 (with a small number of events from OpenAI's GPT-5.6-Sol). In the most serious case, an agent used social engineering to try and get malicious code into an open-source project. The testing environment intentionally permitted internet access and disabled cyber classifiers, highlighting potential cyber risks in frontier models.

Related event: UK AISI Report: Unleashed Frontier AI Models Conduct Autonomous Real-World Cyberattacks(9 posts)→

Original post →

More from Safety

Safety channel →