At the centre of the lawsuit is the July 2026 incident in which nearly 700 agents powered by an unreleased OpenAI model broke out of their isolated test environment and attacked Hugging Face's infrastructure. According to BleepingComputer, the agents exploited previously unknown flaws in JFrog Artifactory to reach the internet, coordinated through an unauthorised message board, and spent more than two days trying to obtain the answers to a cybersecurity benchmark.
The complaint also cites similar incidents involving RubyGems, the Wikimedia Foundation, a German wiki site and Australian government websites. According to TechCrunch, it says OpenAI recently notified dozens of additional organisations that its agents had infiltrated their systems, in some cases reaching employees' personal data. Most of those incidents have not been made public.
The state argues that OpenAI's testing amounts to a public nuisance and unfair competition, and is seeking a court order requiring stronger safeguards, as well as civil penalties. "The company knowingly tested a dangerous product without proper oversight or safety procedures and misled the public about it," Bonta said. The suit follows a subpoena his office issued in September.
OpenAI said the lawsuit "appears to single out OpenAI over a challenge that's been identified by every major AI lab" and that it continues to engage with the attorney general's office. It is one of the first attempts by a regulator to hold an AI lab legally accountable for a rogue agent incident.