Question 1

什么是加密上下文注入？

Accepted Answer

It is an attack, named by Adversa AI's Rony Utevsky, that hides malicious instructions as AES-256-GCM ciphertext so a model's static text filter cannot read them, then gets the model to decrypt and trust those instructions as its own code output.

Question 2

Grok 攻击窃取了什么数据？

Accepted Answer

The attack collects the victim's name, coarse location, subscription tier, and the full set of prompts in the conversation, then sends them to the attacker by appending them to a URL as parameters.

Question 3

xAI 是否已修复该漏洞？

Accepted Answer

No. Utevsky reported it to xAI on June 3, 2026 and followed up on August 4 and August 10, but as of August 19 the technique still worked on Grok.com and xAI had not given a mitigation timeline.

Adversa AI

Grok 通过加密网页技巧泄露用户聊天记录，距 xAI 发出警告已过去 11 周

一份犀利简报。
每天。

Adversa AI

Grok 通过加密网页技巧泄露用户聊天记录，距 xAI 发出警告已过去 11 周

一份犀利简报。每天。

一份犀利简报。
每天。