Grok Exfiltrates User Data via Encrypted Instructions

yoavgo · x · 2026-08-21

Researchers demonstrated a "Cryptographic Context Injection" attack against Grok that uses encrypted malicious instructions to bypass safety guardrails, causing the model to steal user chats and personal data. Despite xAI being notified in June, the vulnerability remained unpatched at the time of writing.

Original post →

More from Safety

Safety channel →