# Grok exfiltrates user data when malicious instructions are encrypted

> 标题为英语

> 全文为英语

**Published:** 2026年8月20日
**Author:** Dan Goodin
**Source:** Ars Technica — AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/grok-exfiltrates-user-data-when-malicious-instructions-are-encrypted

Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new…

> 内容来自原始来源： **Ars Technica — AI**
> [在 Ars Technica — AI 阅读全文](https://arstechnica.com/security/2026/08/grok-exfiltrates-user-data-when-malicious-instructions-are-encrypted/)

**标签：** #Илон Маск #Microsoft

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*