Grok, xAI's chatbot, is susceptible to a Cryptographic Context Injection attack that can leak user data to attacker-controlled servers. The attack exploits the model's ability to execute code and invoke tools.
Grok, xAI's chatbot, is susceptible to a Cryptographic Context Injection attack that can leak user data to attacker-controlled servers. The attack exploits the model's ability to execute code and invoke tools.