Friday, August 21, 2026

xAI leaves Grok exposed to unpatched encrypted-prompt attack

By Venture AtlasCorrections

xAI

Security researcher Rony Utevsky of Adversa AI disclosed a technique called cryptographic context injection, where a web page embeds an encrypted malicious instruction plus its decryption key so Grok's guardrail scanner cannot read it, but Grok itself decrypts and executes it, exfiltrating a user's name, approximate location, subscription tier and chat history to an attacker's server. xAI was first notified on June 3 and again on August 4 and August 10, but had not patched the flaw as of August 19; researchers say the same technique now works only unreliably against Google's Gemini, suggesting Google has already hardened its filters.