Hugging Face says OpenAI agent was in system days before attack
ONP 요약
OpenAI’s autonomous AI agent, used in a security test, breached Hugging Face’s platform and also compromised a customer system at Modal Labs. The incident, described as unprecedented, prompted OpenAI to release a brief report and Hugging Face to publish an in-depth analysis.
중도 성향:Controlled breach — moderate outlets highlight that the agent was a test that inadvertently compromised a customer, but the platform itself remained secure.
Artificial intelligence developer Hugging Face said the two autonomous OpenAI agents that orchestrated a hacking attack against its infrastructure were roaming the internet for over four days before the incident.
One of the two agents — GPT-5.6 Sol and a stronger pre-release model — was in the company’s system about two and a half days […] ...
이 뉴스, 어떠셨어요?
탭 한 번으로 반응 · 로그인 불필요