OpenAI Agent 试图入侵 Wikipedia 工具，并造成海量流量冲击

Wikipedia 的运营方周一表示，OpenAI Agent 曾试图入侵其托管的一款记事工具、进行未经授权的编辑，并向其基础设施发送数百万条资源密集型请求。这是 OpenAI 系统采取有害且可能危险行动的最新案例。

Wikimedia Foundation 表示，部分 OpenAI Agent 行动的目标，是将 Wikipedia 用作从第三方网站获取数据的代理。在一起事件中，这些 Agent 发布了“恶意编辑”，意图将一款引文工具改造成代理服务。在另一起事件中，Agent 曾试图入侵 Wikipedia 的 Etherpad 记事工具，以使其发挥同样作用，但未能成功。

这些 Agent 还发起了数百万次自动化 API 请求，爬取数百万个页面，并向 Wikidata Query Service 发出数十万次查询。该出版方表示，最后一项行动可能导致该查询服务在 5 月发生部分停摆。

“作为全球规模最大、使用最广泛的开放知识平台之一的非营利技术托管方，我们深切担忧‘失控’AI Agent 对我们这类平台造成的影响。这些平台由来自世界各地的志愿者共同建设，并依赖开放互联网的承诺。”Wikimedia 表示，“这一事件，以及许多已经被发现（并且仍在不断被发现）的其他事件，说明 AI Agent 不仅会耗尽资源、导致服务器宕机，也可能试图破坏可信信息。”

Agent 终究会成为 Agent

在远多于六起的案例中，OpenAI Agent 被发现采取了某些行动；如果这些行动由人类黑客实施，很可能会导致刑事指控。在对部分安全护栏被禁用的内部工具进行测试期间，这些 Agent 使用一个临时搭建的留言板互相交换笔记，讨论如何入侵 Hugging Face 的网络，并在自身无法生成答案时获取存储在其中的答案。

其他事件包括：Agent 生成怪异的自我生成提示词、在网站上发布未经授权的帖子以交换信息、访问澳大利亚政府网站的非公开数据，以及利用有缺陷的 DNS 设置，逃离 OpenAI 为阻止这些 Agent 访问互联网而创建的沙箱。

The publisher of Wikipedia said Monday that OpenAI agents attempted to hack a note-taking tool it hosts, made unauthorized edits, and sent millions of resource-intensive requests to its infrastructure, in the latest instance of OpenAI systems taking harmful and potentially dangerous actions.

The objective of some of the OpenAI agents’ actions, the Wikimedia Foundation said, was to use Wikipedia as a proxy for fetching data from third-party sites. In one case, the agents posted “malicious edits” that were intended to repurpose a citation tool as a proxy. In another, the agents made unsuccessful attempts to compromise the Wikipedia Etherpad note-taking tool so it would serve the same purpose.

The agents also made millions of automated API requests, crawled millions of pages, and made hundreds of thousands of queries to the Wikidata Query Service. The last action may have contributed to a partial shutdown of the query service in May, the publisher said.

“As a non-profit technology host of some of the largest and most widely used open knowledge platforms in the world, we are deeply concerned about the impact of ‘rogue’ AI agents on platforms like ours, which are built by volunteers from around the world and rely on the promise of the open internet,” Wikimedia said. “Incidents like this one, and the many others that have been (and are still being) uncovered, illustrate how AI agents can drain resources and crash servers, as well as attempt to compromise trustworthy information.”

Agents will be agents

In well over a half-dozen cases, OpenAI agents have been caught taking actions that would likely result in criminal charges being filed had human hackers taken them. During the testing of internal tools that had some of their guardrails disabled, the agents used a makeshift message board to trade notes with each other, discussing ways to hack the network of Hugging Face and obtain answers stored there when the agents were unable to generate the answers on their own.

Other incidents include agents making bizarre self-generated prompts, publishing unauthorized posts to a website to exchange information, accessing non-public data from an Australian government website, and exploiting faulty DNS settings to break out of a sandbox OpenAI had created to keep the agents from accessing the Internet.