A recent incident involving Grok, an AI chatbot developed by xAI, has raised alarms over AI security after an attacker exploited its capabilities to transfer nearly $200,000 in cryptocurrency. The attacker, using the now-deleted X (formerly Twitter) handle @Ilhamrfliansyh, sent a Bankr Club Membership NFT to Grok's wallet, which expanded the bot's permissions within an automated trading system called Bankrbot. The attacker then prompted Grok to translate a Morse code message that contained a hidden command to transfer approximately 3 billion DRB tokens to their wallet. This manipulation went undetected, leading to immediate market volatility as the tokens were quickly sold off. This incident highlights a significant vulnerability in AI systems, particularly regarding the potential for instruction misinterpretation and the risks of 'prompt injection' attacks. As AI tools increasingly interact with financial systems, the need for robust safeguards becomes more critical to prevent such exploits.