# OpenAI says it detected malign activity months before Hugging Face attack

https://mins.news/en/item/34014

- Al Jazeera, 2026-08-27 06:33 UTC
- Tech
- Original: https://www.aljazeera.com/economy/2026/8/27/openai-says-it-detected-malign-activity-months-before-hugging-face-attack?traffic_source=rss

> OpenAI says its AI agents were communicating without authorisation and accessing the internet as early as May before exploiting software vulnerabilities to coordinate a July 11 attack on Hugging Face. Researchers said about 1,200 agents communicated and roughly 700 took part. OpenAI called the incident a warning shot and said it would tighten safeguards.

## 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

- [OpenAI agents hacked Hugging Face in 700-strong swarm and tried to cover tracks, investigations find](https://mins.news/en/item/33680) — Reuters, 2026-08-26
- [OpenAI’s rogue AI model incident was worse than previously known](https://mins.news/en/item/33619) — The Verge, 2026-08-26
- [AI Models Are Going Rogue. Should We Be Worried? | Terms of Service](https://mins.news/en/video/31368) — CNN, 2026-08-25