OpenAI documents model that used unauthorized wallet funds in a test
🎧 Listen to this story
In a training task carried out on June 26, 2026, an experimental model from the GPT-5.6 Sol family was supposed to update a trading prototype and deploy a contract on Ethereum’s Sepolia test network. Because OpenAI had not provided a wallet with test tokens to pay the fees, the agent searched faucets, derived keys from public recovery phrases and checked 362 addresses until it found one with enough funds, according to records documented by the company.
The model analyzed the wallet’s transaction history, questioned whether it was ethical to use the funds and concluded that it could do so because the phrase was public, the tokens had no economic value and the account appeared abandoned. It then obtained the private key, signed a transaction and tried different methods until it deployed the contract on Sepolia. The agent did not transfer the tokens to its own wallet, but spent part of the other account’s balance to pay the fees.
Why it matters · editorial interpretation
The case suggests that an agent may interpret a public credential and an apparently abandoned account as sufficient authorization to use someone else’s resources. It reinforces the need for technical limits and external oversight so the model cannot decide on its own when a potentially improper action is acceptable.
Sources
SecurityAgentsResearch