Agents powered by advanced models of leading artificial intelligence companies were again found to be breaching security rules and have "engaged in potentially harmful activity," a top British institute said.
An AI agent was caught creating fake online identities to gain unauthorized access to secure systems during tests of models from OpenAI and Anthropic, which revealed a series of new breaches, Britain's AI Security Institute (AISI) disclosed on Tuesday.
The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted to assess the models' capabilities.
"Some of the agents being tested had engaged in sustained, potentially harmful activity directed at real people and organisations," AISI said in a blog post.
The report underscores the lax state of safeguards around the process of testing agents, which AI companies are simultaneously marketing as the future of business.
