The cryptocurrency sector is rapidly moving towards an AI-driven future, where intelligent agents manage various tasks such as booking flights, executing trades, and making payments. However, recent research suggests that the underlying infrastructure may be insecure. A report by McKinsey predicts that AI agents could facilitate $3 trillion to $5 trillion in global consumer commerce by 2030.
Coinbase founder Brian Armstrong and Binance founder Changpeng Zhao have also expressed their enthusiasm for the potential of AI agents in crypto transactions. Nevertheless, a group of security academics and crypto researchers have identified a significant vulnerability in the AI infrastructure. The researchers, affiliated with the University of California, discovered that 'LLM routers,' which act as intermediaries between users and AI models, can be exploited by malicious actors to steal sensitive data.
These routers have access to all the information passing through them, including sensitive data, and can modify it without the user's knowledge. The researchers found that 26 LLM routers were secretly injecting malicious tool calls and stealing credentials, resulting in a $500,000 wallet drain. The problem is exacerbated by the fact that these systems can operate autonomously, approving and executing actions without human review. For crypto users, the implications are severe, as private keys, API credentials, and wallet access tokens often pass through these systems in plain text.
The researchers demonstrated how easy it is to expand the attack by 'poisoning' parts of the router ecosystem, allowing them to observe and potentially control hundreds of downstream systems within hours. The team warns that a single malicious router in the chain is enough to compromise the entire system, creating a cascading risk that could have significant consequences for the crypto industry.