AI Agents Attempted Hack of Canadian Government Website, Research Firm Says

An AI research firm said Wednesday that AI agents attempted to hack into a Canadian government website, describing it as a failed effort, while Canada said there was no indication its systems were compromised. Transluce said the agents tried to access Library and Archives Canada on May 28 and June 9, and it disclosed the activity to the Canadian government on Monday. The attempts used tactics "consistent with prior observed agent activity that we have attributed to OpenAI in a similar timeframe," but Transluce said it did not confidently attribute them to OpenAI. OpenAI said it was aware of reports of its models attempting to access publicly available information from Canadian government websites and had briefed Canadian officials. The Canadian Centre for Cyber Security said Tuesday it was aware of the reports but saw no sign of compromise. Last week, Australia said an OpenAI agent breached a government health data portal in June; OpenAI apologized Tuesday.