AI agents attempted to access a Canadian government website in May and June, according to research firm Transluce, raising fresh questions about the security risks posed by increasingly autonomous artificial intelligence systems.
Canadian authorities said there was no indication that government systems had been compromised.
Also Read: OpenAI AI Agents Built a Secret Society, Exchanged 70,000 Messages and “Sacrificed” Themselves
AI Agents Targeted Library and Archives Canada
The attempts to access Library and Archives Canada took place on 28 May and 9 June. According to Transluce, the attempts involved tactics resembling activity it had previously attributed to OpenAI during a similar period. However, the firm said it could not confidently link the latest attempts to the artificial intelligence company.
The findings were based partly on records captured by arquivo.pt, Portugal’s national web archive, which the Portuguese Foundation for Science and Technology operates.
The archive recorded 899 requests to the Canadian institution’s ‘collection-search’ service. Transluce said these included a series of apparently unsuccessful, basic hacking attempts.
The Canadian Centre for Cyber Security said on Tuesday that it was aware of reports of suspected AI agent activity.
“There is no indication that government systems have been compromised at this time,” the centre said in a statement.
OpenAI said it was aware of reports that its models had attempted to access publicly available information on Canadian government websites.
A company spokesperson said OpenAI was reviewing Transluce’s findings and had provided an initial briefing to Canadian officials conducting the government’s review.
Also Read: OpenAI Halts Training of Latest AI Models After Rogue Agents Hit Government Websites
AI Agents Raise Fresh Cybersecurity Concerns
The reported Canadian incident comes after growing concerns about AI agents’ ability to interact with online systems and carry out tasks with limited human intervention.
Most AI companies have warned about the risks artificial intelligence (AI) could pose, while calling for governments to work together to manage the technology. However, governments have struggled to keep pace with AI’s rapid advances.
The latest findings follow a separate incident in Australia. Last week, the country said an OpenAI agent had breached a government health data portal in June, gaining unauthorised access to files.
That incident was described as the first known instance of an AI agent hacking into a government website. OpenAI apologised on Tuesday for the breach.
The Canadian case adds to scrutiny of how AI systems access public information & whether safeguards can prevent them from crossing security boundaries.
For government agencies and technology companies, the immediate focus remains on understanding how these attempts occurred, what systems were exposed, and how to secure access to public-facing services.
Samarjit Kaur is a journalist and communications professional covering technology & emerging digital trends. With a focus on clarity and context, she reports on developments shaping industries and governance. When not reporting, she chooses to plug-in and relax on her playlists and plan her next bucket-list trips!
