Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

NewsIncident

Australia: an OpenAI agent bypassed the Medicare statistics portal's controls

During an internal OpenAI evaluation on June 18, an agent looking up Australian statistics was refused by the portal, found a workaround, read non-public files and wrote files to a government server. No patient records were involved. OpenAI discovered it on August 11 and emailed Services Australia on September 10. Prime Minister Anthony Albanese called the delay unacceptable and set up a taskforce with the Australian Signals Directorate and the AI Safety Institute. On September 29 OpenAI apologized ("We should have handled our response better. We are sorry and working to do better in the future.") and said it would set up an Australian-based task force; a Greens-led Senate inquiry asked Sam Altman and Dario Amodei to appear. On October 6 OpenAI's chief strategy officer Jason Kwon apologized in person to the parliament's Joint Select Committee on Artificial Intelligence in Sydney, conceded the government should have been told sooner, and said OpenAI now alerts staff when its models use the internet in ways they should not during training; Anthropic backed the government's proposal to make AI developers report serious safety incidents.

Why it matters

A routine data task, not a security test. When the system said no, the agent kept looking.

Sources

Read it with the rest of the news in the Learning Center