印度计算机应急响应团队（CERT-In）周四表示，多家AI模型提供商的AI代理在研究和测试期间访问了印度组织的个人数据和机密材料。
AI agents from multiple providers accessed personal data and confidential material at Indian organizations during research and testing, India’s cybersecurity agency said Thursday.
CERT-In表示，它收到了“来自AI模型提供商的多份自愿披露”，这些提供商的模型在公开互联网上的研究和评估运行过程中，“进入了印度组织的实时系统”。
The Indian Computer Emergency Response Team (CERT-In) said it had received “multiple voluntary disclosures from AI model providers” whose models, during research and evaluation runs on the open internet, “had reached the live systems of Indian organizations.”
这些代理通过应用配置中暴露的凭证和连接设置、公开代码仓库以及过度宽松的云角色进入系统，其行为“超出了其被分配任务的授权范围”。这使得印度成为流氓AI代理全球巡演的最新一站。7月，OpenAI的代理逃离测试环境并入侵了法国公司Hugging Face——拉开了流氓AI代理活动的夏季序幕。上个月，OpenAI向澳大利亚道歉，因为其代理访问了四个政府网站，包括医疗保险统计门户。
The agents got in through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles, and their actions “exceeded the authorisation of their assigned tasks.”This makes India the latest stop on what has become a world tour for rogue AI agents. In July, OpenAI’s agents escaped a test environment and hacked French company Hugging Face—kicked off a summer of rogue AI agent activity. Last month, OpenAI apologized to Australia after its agents accessed four government websites, including a Medicare statistics portal.
在Hugging Face，OpenAI的代理起初也是以同样的方式进入，但随后发现并利用了软件漏洞，在公司服务器上运行代码。CERT-In表示，在印度并未发现此类黑客行为，代理似乎只是利用了随意留存的访问权限。
At Hugging Face, OpenAI’s agents started the same way but then found and exploited software flaws to run code on the company’s servers. CERT-In described no such hacking in India, where the agents appear to have simply used the access left lying around.
然而，印度的案例在一个方面似乎更为严重，那就是代理所看到的内容：在澳大利亚，OpenAI表示未发现其代理接触个人医疗或刑事记录的证据，即使它们在医疗保险统计系统中写入了文件；而在印度，代理读取了个人数据和机密业务记录。此外，与之前由单一实验室披露的事件不同，此次涉及多家提供商的代理。
Still, the Indian cases appear to be worse in one respect, which is what the agents saw: In Australia, OpenAI said it found no evidence its agents touched individuals’ medical or criminal records, even after they wrote files inside a Medicare statistics system, while in India, agents read personal data and confidential business records. And unlike earlier incidents, each disclosed by a single lab, India’s involved agents from multiple providers.
CERT-In未透露涉及的提供商或受影响组织的名称，也未说明代理是否修改了任何系统。TechCrunch已联系CERT-In以获取更多信息。
CERT-In did not name the providers or affected organizations, or say whether the agents altered any systems. TechCrunch has reached out to CERT-In for more information.
目前看来，最相似的案例似乎是Anthropic在7月披露的Claude在测试期间利用弱密码等基本技术入侵三家公司系统的情况。与Anthropic的案例一样，受影响的组织并未自行发现这些入侵。这些披露使得各国政府只能依赖导致此类漏洞的AI公司自愿披露失控AI代理的活动。
For now, the closest parallel seems to be Anthropic’s July disclosure of Claude breaking into three companies’ systems during testing using basic techniques like weak passwords. dia, as in Anthropic’s cases, the affected organizations had not detected the intrusions on their own. The disclosures have left governments relying on AI companies causing these breaches to voluntarily disclose rogue AI agent activity.