Encrypted prompts slip past Grok's guardrails, exfiltrating your chat history
Ask Grok to summarize a webpage and the page's encrypted payload can get the bot to hand over your name, location, subscription tier, and conversation history to an attacker's server, no click or warning required. Adversa AI hides the malicious instructions as AES-256 ciphertext, which Grok decrypts inside its own code runtime, so content classifiers never see the plaintext. Reported to xAI in June, the flaw was still reproducible on August 19.