The Verge · Technology · 2026-09-12
OpenAI’s rogue AI tried to hack another company in May
In May, hundreds of malicious and spam packages were uploaded to RubyGems. Now independent researchers have said that a swarm of OpenAI agents were responsible for the attack. Not only that, but the AI tried to steal users’ API keys. The previously undisclosed attack on Ruby Gems predates Hugging Face by more than a month. OpenAI did not immediately reply to a request for comment.
Read original on The Verge Get the app
Licensed summary · LicensedSummary
Related briefs
- BRICS emerges as most influential platform for emerging markets : Xi Jinping
- Modi: Global South must shape, not just follow, rules
- Sam Altman says OpenAI going public in 2026 would be ‘ill-advised’
- Grouping eyes mechanism for extradition of eco fugitives
- StarCraft returns in 2030 as an open-world shooter