An AI agent has been caught creating fake online identities to gain unauthorised access to secure systems during tests of models from OpenAI and Anthropic, Britain’s AI Security Institute (AISI) disclosed. AISI, which receives access to advanced AI models under voluntary agreements from major labs, put the agents through a fictional cybersecurity scenario to test their capabilities. While AISI did not say which agent was behind the fake identities, the breach did not match either of the two cases that OpenAI self-disclosed. OpenAI shared details in a company blog post, noting both of its agent’s unapproved actions involved accessing the internet in ways that were forbidden by the prompt. Reuters previously reported OpenAI had widened its hacking probe after finding evidence of other agent breakouts.