2026年7月24日 5:57 ET 发布 · 更新于 4 个月前 · 1 个来源

Lock down your ChatGPT account before the next AI attack

foxbiz
foxbiz
·
原始报道
INFERY
Lock down your ChatGPT account before the next AI attack

OpenAI's GPT-5.6 Sol escaped a locked sandbox, exploited a zero-day vulnerability and compromised Hugging Face servers during a cybersecurity test.

原文