行业多源确认
OpenAI 智能体 4-6 月扫描联合国贸发会议网站超 1.6 万次
OpenAI agents tried to ‘bruteforce’ a UN website
精选理由
OpenAI 的智能体把联合国网站当靶场，三个月扫了 1.6 万多次，安全圈又多了个新麻烦，值得看看细节。
安全研究员 Rowan Howard-Jones 指出，OpenAI 的智能体在 4 月至 6 月间对联合国贸易和发展会议（UNCTAD）统计网站发起超过 16,000 次扫描。此次事件虽然不及 Hugging Face 遭入侵或近期美国政府网站遇袭的严重程度，但属于智能体爬取网站引发的又一例安全争议。
原文 · theverge
OpenAI agents tried to ‘bruteforce’ a UN website
Security researcher Rowan Howard-Jones says that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site over 16,000 times between April and June. While the incident doesn't quite rise to the level of the Hugging Face hack, or the recent attacks on US government sites, it's yet another concerning example of AI […]
