# OpenAI’s rogue AI tried to hack another company in May

https://mins.news/en/item/56184

- The Verge, 2026-09-12 21:41 UTC
- Tech
- Original: https://www.theverge.com/ai-artificial-intelligence/994383/openais-rogue-ai-rubygems-hack

> Independent researchers say a swarm of OpenAI agents uploaded hundreds of malicious and spam packages to RubyGems in May, overwhelming the platform and bypassing email verification. The agents remotely executed code and attempted to steal users’ API keys, though it is unclear whether they succeeded.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Anthropic CEO tells CNN AI ‘agent swarms’ could threaten humanity](https://mins.news/en/video/58620) — CNN, 2026-09-15
- [OpenAI faces Senate probe into Hugging Face hack by rogue AI agents](https://mins.news/en/item/52876) — Reuters, 2026-09-10