The cryptocurrency sector is moving towards a future where AI-powered agents manage various tasks, including transactions and payments. However, a recent research paper suggests that the underlying infrastructure may not be secure.
According to the study, a largely overlooked aspect of AI infrastructure, known as LLM routers, can be exploited by malicious actors to intercept sensitive data. These routers act as intermediaries between users and AI models, and they have access to all the data that passes through them.
The researchers found that these routers can be used to steal credentials and even drain crypto wallets. In one instance, a test Ethereum wallet was drained after its private key was exposed. The researchers also demonstrated how easy it is to expand the attack by poisoning parts of the router ecosystem, which could potentially compromise hundreds of downstream systems. The study highlights the need for greater security measures to be implemented in the AI infrastructure that underpins the crypto industry.
As the use of AI agents in crypto transactions becomes more widespread, the risk of security breaches and financial losses could increase if the underlying infrastructure is not secure.