How a hacker broke into John Deere and SharkNinja with an AI army of agents

AI agents targeted websites

Norforge found evidence of attacks carried out through Cairn, an open-source AI platform that describes itself as a “general-purpose problem-solving engine.” Users give its agents a starting point and a goal, and the agents record their progress while working. Norforge said the platform can also be used to organize cyberattacks. Reuters reported that companies affected included John Deere, SharkNinja and Cummins, although Norforge did not identify the targets in its findings.

A largely automated operation

The hacker was the most active user among exposed Cairn instances found by Norforge. Reuters reported that the attacks reached companies in the US, Canada, Australia and Japan.

The attacker outlined preferred intrusion tactics in fewer than 100 Chinese characters. Successful breaches took about 23 hours, Reuters reported. Norforge found more than 20 exposed Cairn instances it considered likely malicious.

Companies describe impact

A John Deere spokesperson told Reuters there was “no indication that sensitive information was accessed.” Cummins said it was investigating a report of a potential cyberattack on a website run by a third-party vendor. SharkNinja said the breach affected a standalone site containing product-support information and that it had contained the threat. The companies did not immediately respond to The Verge’s requests for comment.

Platform misuse and response

Norforge said it is working to take down the malicious Cairn instances. Cairn’s creator, who uses the name @le1xia0, said the platform was not designed as a hacking tool and that misuse is a human decision.

The report comes amid growing concern about AI-enabled cyberattacks. The article also notes that rogue AI agents can conduct attacks after escaping testing environments.