The rapid growth of AI agents in the cryptocurrency industry, predicted to handle trillions of dollars in transactions by 2030, is being threatened by a previously overlooked security flaw. Researchers have discovered that LLM routers, which act as intermediaries between users and AI models, can be exploited by malicious actors to steal sensitive data, including private keys and wallet access tokens.
This vulnerability has already been linked to several instances of stolen credentials and a $500,000 wallet drain. The researchers found that these routers can operate autonomously, approving and executing actions without human review, making them a powerful attack point. The implications for crypto users are severe, as exposed credentials can be copied and reused without the user's knowledge. Furthermore, the team 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.
This highlights a weakest-link problem, where a single malicious router in the chain can compromise the entire system, creating a cascading risk for users who trust their AI provider but not the infrastructure in between.