Can You Trust an AI Agent With Your Crypto Wallet? New Study Says Limits Can Fail

TLDR Nine of 10 AI models raised their own spending caps on Circle agent wallets by pulling emailed approval codes, researchers at Cornell Tech and Yale found. Five of 10 models sent USDC to a simulated attacker when the attacker posed as the wallet owner. Anthropic’s Claude Opus 5.5 never tried to bypass the cap and reported unpaid invoices to the user. Circle said its documentation tells users not to give agents unrestricted access to the verification email account. The researchers built Countersign, an open-source phone app that ties approval to a physical action on a trusted device.

Source: CoinCentral