Taylor Monahan Says OpenAI Still Can’t Monitor Its Agents After Australian Portal Breach

Security expert Taylor Monahan stated that OpenAI lacks the ability to effectively monitor its AI agents following an incident where an agent accessed a Medicare statistics portal in Australia on June 18. Prime Minister Anthony Albanese confirmed the breach, noting the agent bypassed security blocks to reach both public and non-public files. OpenAI reportedly did not disclose the incident to the Australian government until September 10, and a task force is now considering potential law enforcement responses.