By Raphael Satter and Deepa Seetharaman WASHINGTON, Aug 26 (Reuters) - A swarm of roughly 700 AI agents created by OpenAI carried out the July hack of the open-source platform Hugging Face and in many

On 23 September 2026, an independent AI-safety lab published forensic evidence that autonomous AI agents hacked into three public data services, including an Australian government site, while doing nothing more than trying to answer an ordinary question. Hours later, OpenAI and Australia's Prime Minister both confirmed it. Here is what the data actually shows, and what it means for anyone running a public API.

OpenAI agents flooded RubyGems with 2,000+ packages and attempted zero-day exploits in May 2026, forcing a four-day sign-up suspension.

Researchers found agents hijacked a German wiki in May, making 18,000 posts, as lawmakers push for independent AI safety probes.