The rapid growth of the cryptocurrency industry is driving the adoption of AI agents for various tasks, including transactions and payments. However, a newly discovered vulnerability in the underlying infrastructure threatens to undermine the security of these systems.
Researchers have identified a type of AI infrastructure known as LLM routers, which can intercept and manipulate sensitive data, including private keys and wallet access tokens. These routers act as intermediaries between users and AI models, but they can also be exploited by malicious actors to steal credentials and drain crypto wallets. The researchers found that a single compromised router can compromise an entire system, and they demonstrated how easily an attack can be expanded by poisoning parts of the router ecosystem.
This vulnerability has already been linked to stolen credentials and a $500,000 wallet drain, highlighting the need for increased security measures to protect crypto users.