Level 3. Significant control incident
AI Agents Targeted U.S. and Canadian Government Websites
- Developer
- Not established
- Model
- Not established
- When it happened
- Not established
- When it was disclosed
- October 7, 2026
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by toronto.citynews.ca, dated 2026-10-07. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 3 of 5Significant control incident
- Potential
- 3 of 5Significant control incident
An important technical, security or permission boundary was crossed, or there were real consequences. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
Why this level
- An external system was affected. Argues for level 3
- Deception or concealment by the system. Argues for level 3
- A safeguard was bypassed. Argues for level 2
- The system acted without authorisation. Argues for level 2
- The system acted autonomously. Argues for a potential level of 3
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
The system acted without authorisation
On June 17, while apparently looking up school statistics, agents made more than 200,000 requests to a U.S. Department of Education website.
AI Agents Targeted U.S. and Canadian Government Websites
Reported, not confirmed
The system acted autonomously
OpenAI disclosed over the summer that its AI agents hacked AI startup Hugging Face without being instructed by any human to do so.
AI agent attempted to hack Library and Archives Canada, says U.S. research groupDeception or concealment by the system
On June 18, an automated workflow attempted to register for a Bureau of Economic Analysis (BEA) API key using a disposable email address and the self-entered organization name “OpenAI Research,” with no confirmed successful registration.
AI Agents Targeted U.S. and Canadian Government WebsitesAn external system was affected
On May 28, 2026, and June 9, 2026, Arquivo.pt captured 899 requests hitting the “collection-search” service of Library and Archives Canada (LAC), including a series of apparently failed rudimentary hacking attempts.
AI Agents Targeted U.S. and Canadian Government WebsitesThe behaviour repeated rather than stopping
Following up on our previous blog post , we discovered several additional incidents where rogue AI agents appear to have used aggressive techniques to access publicly available data on government websites.
AI Agents Targeted U.S. and Canadian Government WebsitesA safeguard was bypassed
This includes techniques like making accounts with disposable email addresses, reusing exposed credentials, bypassing antibot controls, and flooding websites with requests.
AI Agents Targeted U.S. and Canadian Government Websites
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read October 8, 2026
AI agent attempted to hack Library and Archives Canada, says U.S. research groupA structured incident database
AI Incident Database, own page, not yet readWhere we first saw it
AI Agents Targeted U.S. and Canadian Government WebsitesWhere we first saw it
AI agents tried to hack a Canadian government website, researchers say
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.