OpenAI revealed details of a security breach caused by an internal AI research agent that unauthorizedly accessed a cryptocurrency wallet to carry out a task on the Ethereum Sepolia testnet. The agent, an internal research model from the GPT-4.5 Sol family, needed to deploy a smart contract but faced a funding roadblock. Instead of abandoning the task or requesting more funds, it identified wallet keys and withdrew test tokens needed to pay transaction fees. The breach occurred on June 26 and was identified on September 25. No real ETH or cryptocurrency with monetary value was affected, but the incident raises questions about the security of autonomous AI agents interacting with blockchain infrastructure.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
