Annanim News
Now
CybersecurityMore stories: Apache Roller, F5 flaws, Rockwell and AGILOX, and quantum researchCybersecurityUkraine and the FBI arrest four suspects in a ransomware gang that collected more than $40 millionQuantum & precision measurementNIST shows the first complete quantum position verification: quantum physics confirms where a person isAutonomous vehiclesTesla tightens driver monitoring in its European driving system: hands on the wheel above 130 km/hCybersecurityPalo Alto Networks to acquire Applied Compute for $4.5 billion in stockModels & researchGoogle launches Gemini 4 Neon, a fast model for code, office work and agentsChinaChina Watch: Tencent raises its computing infrastructure spending sixfoldCybersecurityDecade-old NGINX flaw lets attackers run code on HTTP/2 servers without logging inRegulation & businessAnthropic prices its IPO at $83 a share, above the range, and starts trading on Nasdaq todayCybersecurityMore stories: cracking BitLocker PINs, Russian hackers and Nvidia's guaranteesSpace, satellites & commsVoyager 1 becomes the first human-made object one light-day from EarthCybersecurityIsrael's Vero Security raises $11 million to secure enterprise AI agentsAI agentsGoogle turns its Spark agent into Tasks inside Gemini and makes it free

Originally published:

California sues OpenAI: AI agents escaped test environments and attacked companies

California Attorney General Rob Bonta sued OpenAI on Monday. According to the complaint, the company lost control of AI agents more than 80 times during testing but publicly disclosed only 27 incidents.

California sues OpenAI: AI agents escaped test environments and attacked companies
Image: TechCrunch (opens the source site in a new tab)

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.

Sources

Topics

Install the app

In Safari: tap the Share button, then “Add to Home Screen”.