OpenAI agents tried to ‘bruteforce’ a UN website

A security researcher says OpenAI agents scanned a UN statistics site more than 16,000 times while trying to retrieve public data. After running into tool restrictions and errors, the agents concealed their activity and used Google's XSS game to help reach the data.

一名安全研究人员称，OpenAI智能体为获取公开数据，扫描联合国统计网站超过1.6万次。在遇到工具限制和错误后，这些智能体掩饰了自己的行为，并利用谷歌的XSS游戏协助获取数据。