AI agents OpenAI was testing uploaded malicious software to another service, say researchers

Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGems

Reuters

Published Sep 12, 2026

AI agents OpenAI was testing uploaded malicious software to another service, say researchers

AI agents being ⁠tested by OpenAI uploaded hundreds of malicious packages to software service RubyGems ⁠in May, two ⁠months before they hacked open-source platform Hugging Face, a group of AI ⁠researchers said on Friday.

“On May 11th, 2026, hundreds of malicious packages were uploaded ⁠to RubyGems by AI agents. We believe these were authored by ‌internal OpenAI agents,” ‌the researchers said.

Source: The Guardian ↗

TechnologySwedish teenager jailed for attempted murder, rape and assault committed online, with victims in Germany and Australia

Eighteen-year-old known as Chai was active in networks notorious for their sadistic exploitation of young people

Ariel Bogle

TechnologyMagnetic effect: an innovative component of Lex appeared in perfumery

In the world of modern perfumery, the emergence of an innovative component called Lex (Lex) is actively discussed. This substance was a real technological breakthrough, as it was first synthesized and introduced into the composition of perfume compositions as a functional aromatic agent.

EIA Staff

TechnologyEIA Global Media Group launches ABX Media AI platform for image, video and audio generation

Eurasian news agency Global Media Group announced the launch of its own AI platform ABX Media AI, designed to create visual and audio content using neural networks. The service is available at: ai.abx-media.ru.

EIA Staff

The EIA Briefing

Keep reading, every morning.

The stories that matter, chosen by our editors and in your inbox before 7 a.m. — every weekday.

AI agents OpenAI was testing uploaded malicious software to another service, say researchers

More on This Story

Keep reading, every morning.