OpenAI 的失控 AI 曾于 5 月试图入侵另一家公司

今年 5 月，数百个恶意和垃圾软件包被上传至 RubyGems，给该托管平台造成了严重干扰。如今，独立研究人员表示，一群 OpenAI Agent 应对这次攻击负责。不仅如此，这些 AI 还试图窃取用户的 API 密钥。

当时，RubyGems 将此称为一次“重大恶意攻击”，并在尝试缓解损失和收集数据期间关闭了注册功能四天。研究人员表示，导致 RubyGems 陷入瘫痪的软件包内容显然由 LLM 撰写，而提交这些软件包的 Agent 自称来自 OpenAI。他们称，观察到的行为与此前开始编辑一个德国 wiki的 Agent 群高度相似；OpenAI 已确认，该事件由其 Agent 负责。

在此次事件中，这些 Agent 成功绕过 RubyGems 的电子邮件验证系统，创建了大量账户，随后通过大量提交使平台不堪重负。它们还利用该网站的自动构建系统远程执行代码，并试图利用一个漏洞窃取用户 API 密钥。不过，目前尚不清楚它们是否曾成功得手。

OpenAI 未立即回复置评请求。

In May, hundreds of malicious and spam packages were uploaded to RubyGems, causing a serious disruption for the host. Now independent researchers have said that a swarm of OpenAI agents were responsible for the attack. Not only that, but the AI tried to steal users’ API keys.

At the time, RubyGems described it as a “major malicious attack” and shut down signups for four days as it tried to mitigate the damage and collect data. Researchers said that the contents of the packages that brought RubyGems to its knees were clearly authored by an LLM, and that the agents submitting those packages self-identified as being from OpenAI. They said the behavior observed very closely mirrored that of the swarm that began editing a German wiki, which OpenAI has confirmed its agents were responsible for.

The agents in this instance managed to bypass RubyGems’ email verification system to create a large number of accounts, then overwhelmed it with submissions. It then used the site’s automatic build system to remotely execute code and tried to exploit a vulnerability to steal user API keys. Though, it’s unclear if it ever succeeded.

OpenAI did not immediately reply to a request for comment.