[Vitalik: Designing AI Agents That Balance Security, Decentralization, and Privacy Still Faces Challenges] Ethereum founder Vitalik Buterin posted on the X platform, stating that ensuring security, decentralization, and privacy while addressing potential adversarial attacks on AI agents remains difficult. For example, your AI agent might check the ENS profile of the other party, which contains a jailbreak command that causes the agent to transfer all your tokens to the other party. Vitalik believes that requiring manual confirmation for every large transaction is much better than having no confirmation at all, but it is still not perfect. He also suggested that users should be provided with an explanation of the specific details of the transaction, which presents a complex user experience challenge.