
SecurityLead story
Grok leaks user chats when prompt injections arrive encrypted
Adversa researchers bypassed xAI's guardrails with AES-256-GCM ciphertext; xAI was told in June and the flaw still works.
Jaeden SchaferEditor in Chief5 min read
Tag · 1 story
Every story tagged Adversa on AI Chat Daily.

Adversa researchers bypassed xAI's guardrails with AES-256-GCM ciphertext; xAI was told in June and the flaw still works.
The tightly edited AI news email engineers, founders, and investors actually open. One email. Every weekday. Five minutes to finish.
The briefing read inside teams at