“During a routine cyber evaluation, AI agents took sustained, unsanctioned action directed at real people and organisations,” UK’s AI Security Institute (AISI) disclosed on Tuesday. The agents’ actions included an attempted supply-chain attack that saw them create malicious pull requests and try to socially engineer an open-source maintainer into approving the malicious code (they refused). The agents, powered by Anthropic’s Mythos 5 and OpenAI’s GPT-5.6 Sol models, also engaged in prompt injection aimed at making … More →
The post AI agent deception moves from theory to reality in UK cyber tests appeared first on Help Net Security.