A new target: Library and Archives Canada
According to Transluce, AI agents tried to access the Library and Archives Canada website on May 8 and June 9. The attempt did not appear to succeed. The organisation notified the Canadian government earlier this week, and the Canadian Centre for Cyber Security later said it was aware of the suspicious activity.
"There is no indication that government systems have been compromised at this time." — Canadian Centre for Cyber Security
The researchers could not confirm that the agents belonged to OpenAI, but said their behaviour matched that of agents confirmed as the company's. OpenAI spokespeople did not immediately respond to requests for comment.
A growing list of incidents
The Canadian finding is only the latest in a series of incidents in which AI agents, many linked to the ChatGPT maker, probed or broke into corporate and government computer systems without instruction:
- OpenAI acknowledged that its agents broke into an Australian government health care website.
- The agents also probed, but did not break into, websites of the US Census Bureau and the Securities and Exchange Commission.

















