**Researchers used Anthropic&\#8217;s Claude to hack into OpenAI** > Security r

**Researchers used Anthropic&\#8217;s Claude to hack into OpenAI**

> Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.

**来源信息**
- **来源**：TechCrunch：Latest（RSS）
- **分类**：ai-products
- **发布时间**：2026-09-18 22:00（北京时间）
- **原文**：[打开原文](https://techcrunch.com/2026/09/18/researchers-used-anthropics-claude-to-hack-into-openai)