AIToday
Large Language ModelsAI Safety & AlignmentOpen-Source AIThe Verge AIPublished: Oct 20, 2026, 01:00 JST

Norforge: AI agents breached more than 100 websites

Norforge: AI agents breached more than 100 websites

3 Key Points

  1. What happened

    Norforge says one hacker used Cairn, an open-source AI platform, to direct largely autonomous agents against more than 100 websites in the US, Canada, Australia, and Japan, with successful breaches taking about 23 hours.

  2. Why it matters

    The intrusion shows that off-the-shelf open-source tooling can be repurposed to orchestrate cyberattacks at scale, with the attacker needing only a brief written set of intrusion tactics.

WHO IT HITSSecurity teams at companies running public-facing websites, especially those using third-party vendors for product support pages, may need to review whether open-source AI orchestration tools are being abused against their sites.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

The attacks came to light because Norforge was scanning for exposed instances of Cairn, an open-source platform that lets users set a start and end point for AI agents and watch them document their progress. That same design, meant for general problem-solving, can be pointed at corporate websites. Norforge found more than 20 exposed Cairn instances it describes as likely malicious, and the one behind the 100-plus breaches was the most active among them.

The victims span the US, Canada, Australia, and Japan, and the companies' responses suggest the damage was limited: John Deere said it saw no indication of sensitive information being accessed, SharkNinja said the affected site was a standalone product-support page and that it contained the threat, and Cummins said it is investigating a potential attack on a third-party vendor's site. Cairn's creator, who goes by @le1xia0, pushed back earlier this month, saying the platform was never a hacking tool and that misuse is a human decision rather than a feature of the engine. Norforge says it is working to get the malicious instances taken down.

FAQ
Which companies were affected?
Reuters reports that the victims included John Deere, SharkNinja, and Cummins. Norforge itself did not name the targets.
How did the hacker carry out the attacks?
The hacker used Cairn, an open-source AI platform, to orchestrate AI agents that mostly operated on their own. The attacker laid out preferred intrusion tactics using fewer than 100 Chinese characters, and successful breaches took about 23 hours.
What did the companies say?
John Deere said there is no indication that sensitive information was accessed. Cummins said it is investigating a potential cyberattack on a website operated by a third-party vendor, and SharkNinja said the breach impacted a standalone product-support site and that it has contained the threat.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMotive Technologies launches AI Agents to automate fleet management