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

Von

Reuters

Veröffentlicht 12. Sept. 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.

Quelle: The Guardian ↗

Mehr zu diesem Thema

TechnologieSwedish 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

Technologie‘We must slow the pace’: CEO of Anthropic calls for an AI slowdown

In a social media post, Dario Amodei proposed a plan including third-party evaluations of AI systems

Edward Helmore

TechnologieWhy Europe has been absent from the great AI safety debate

Though Europe has measures that address how consumers might encounter AI, technology will impact them if the worst scenarios bear

Dan Milmo and Aisha Down

Der EIA-Briefing

Bleiben Sie jeden Morgen informiert.

Die wichtigsten Geschichten, ausgewählt von unseren Redakteuren — jeden Werktag vor 7 Uhr in Ihrem Postfach.