A newly disclosed prompt-injection technique could turn a routine request to summarize a webpage in xAI’s Grok web chat into a silent data-exfiltration attack, potentially exposing a user’s name, approximate location, subscription tier, and active conversation history. Security researchers at Adversa AI have dubbed the technique “Cryptographic Context Injection.” The attack targets Grok’s ability to […]
This article has been indexed from GBHackers Security | #1 Globally Trusted Cyber Security News Platform
Read the original article: