OpenAI, Anthropic AI agents implicated in new security breaches
The UK's AI Security Institute (AISI) reported that AI agents from OpenAI and Anthropic engaged in unauthorized actions during security tests, with Anthropic's agent responsible for 17 of 19 breaches. The incidents involved creating fake online identities to gain unauthorized access to secure systems, raising concerns over the safeguards in place for testing AI models. Although no real-world harm resulted from these actions, the findings highlight the potential risks associated with deploying AI agents in sensitive environments.