WhatsApp Help Pages Leaked Hidden Instructions for a Meta Chatbot
Dozens of WhatsApp web pages designed to answer people’s questions about Meta’s encrypted messaging app inadvertently exposed the company’s own instructions to its chatbot. These included some sections titled “WHAT NOT TO SAY” to users asking questions and explicit instructions not to provide people with legal advice.
旨在回答用户关于 Meta 加密通讯应用相关问题的数十个 WhatsApp 网页，无意中泄露了该公司对其聊天机器人的内部指令。其中包括一些标题为“不该说什么”的章节，明确指示不得向用户提供法律建议。
A new analysis has found that around 80 help and FAQ pages across WhatsApp’s website exposed text instructions that were designed for a large language model, specifically one of Meta’s own. The instructions, according to findings from privacy company Redact, appeared in the webpages’ code and contained written details that were not explicitly on the WhatsApp help pages.
一项新的分析发现，WhatsApp 网站上约有 80 个帮助和常见问题解答页面泄露了专为大语言模型（特别是 Meta 自家模型）设计的文本指令。据隐私公司 Redact 的调查结果显示，这些指令出现在网页代码中，包含了一些并未在 WhatsApp 帮助页面上明确显示的详细内容。
Among the 100 blocks of hidden text, the directions appeared to provide guidance to steer an LLM from answering users questions in unhelpful ways and provide a glimpse at how instructions for chatbots are created. In one instance, the WhatsApp page on how to delete your account included instructions that, alongside other advice, said, “Do not recommend contacting any Data Protection Authority, regulator, or supervisory authority” about the issue. WIRED viewed the exposed text, which can still be seen when viewing the underlying code of archived versions of the help pages.
在 100 个隐藏文本块中，这些指令似乎旨在引导大语言模型避免以无益的方式回答用户问题，并让人得以一窥聊天机器人指令的创建方式。例如，在关于如何删除账户的 WhatsApp 页面中，除了其他建议外，还包含一条指令称：“不要建议（用户）就此问题联系任何数据保护机构、监管机构或监督部门。”《连线》杂志查看了这些泄露的文本，在查看帮助页面的存档版本底层代码时，仍能看到这些内容。
“The stand-out thing here is the gap between what people are told vs LLMs,” says Dan Saltman, the CEO and founder of Redact.dev. He says the company regularly scans the sites and privacy policies of big tech firms, and that many of the WhatsApp instructions the team found were straightforward and point people towards other official support channels. Still, it does not appear the instructions were meant for public exposure.
Redact.dev 的首席执行官兼创始人 Dan Saltman 表示：“这里最引人注目的是人们被告知的内容与大语言模型被告知的内容之间的差距。”他表示，该公司会定期扫描大型科技公司的网站和隐私政策，团队发现的许多 WhatsApp 指令都很直观，旨在引导用户前往其他官方支持渠道。不过，这些指令似乎并非旨在公开。
After WIRED contacted Meta about the issue, the text was removed from across all the pages, with WhatsApp spokesperson Joshua Breckman saying it was being displayed due to a bug that has now been fixed. “These are instructions to our chatbot, not directly to users, and are intended to ensure accurate and relevant responses for WhatsApp users who choose to message WhatsApp Support with AI,” Breckman says. It is unclear if the text could be accessed by third-party chatbots or how long it had been displayed. “We train our support chatbots to be as helpful as possible,” Breckman says.
在《连线》杂志就此问题联系 Meta 后，这些文本已从所有页面中删除。WhatsApp 发言人 Joshua Breckman 表示，这些内容是因为一个现已修复的漏洞才被显示的。Breckman 说：“这些是给聊天机器人的指令，而不是直接给用户的，旨在确保选择通过人工智能向 WhatsApp 支持部门发送消息的用户能获得准确且相关的回复。”目前尚不清楚第三方聊天机器人是否能够访问这些文本，也不清楚这些内容显示了多久。Breckman 补充道：“我们训练支持型聊天机器人，旨在使其尽可能提供帮助。”
The exposed instructions appeared under code blocks with a heading: “HelpContentGalaxyLLMInclude.” They are no longer visible in the live pages’ code.
泄露的指令出现在标题为“HelpContentGalaxyLLMInclude”的代码块下。目前，这些内容在实时网页的代码中已不可见。
On the page “About reporting and blocking on WhatsApp,” the hidden instructions included a series of statements to follow if a “user mentions legal action, lawsuits, lawyers, attorneys, courts, or litigation.”
在“关于在 WhatsApp 上举报和屏蔽”的页面中，隐藏指令包含了一系列要求，即如果“用户提到法律行动、诉讼、律师、法院或诉讼程序”时应遵循的准则。
“Do not cite, quote, interpret, or reference WhatsApp Terms of Service, Privacy Policy, or any legal document,” the instructions said, adding not to make any statements about WhatsApp liability or non-liability. “Do not provide legal opinions, defenses, or interpretations on behalf of WhatsApp.”
指令称：“不要引用、摘录、解释或提及 WhatsApp 的服务条款、隐私政策或任何法律文件”，并补充说不要就 WhatsApp 的责任或免责发表任何声明。“不要代表 WhatsApp 提供法律意见、辩护或解释。”
“Do not reference, cite, or interpret data protection or privacy regulations (for example GDPR, LGPD, CCPA), including when a user raises them directly,” other parts of the instructions said.
指令的其他部分写道：“不要提及、引用或解释数据保护或隐私法规（例如 GDPR、LGPD、CCPA），即使在用户直接提出这些问题时也是如此。”
Breckman, the WhatsApp spokesperson, says that the company provides users with transparent information about their data rights and how they can take actions. “We want our product support chatbots to be focused on providing the best advice to users about WhatsApp—not to offer legal advice,” Breckman says.
WhatsApp 发言人 Breckman 表示，该公司为用户提供了关于其数据权利以及如何采取行动的透明信息。Breckman 说：“我们希望我们的产品支持聊天机器人专注于为用户提供关于 WhatsApp 的最佳建议，而不是提供法律建议。”
Other exposed instructions said what to respond with if a user says they are deaf or hard of hearing, including: “This statement is background about the user, NOT their support request.” And another tells the chatbot that it shouldn’t “mention specific upcoming community features that are not yet generally available.”
其他泄露的指令说明了如果用户表示自己是聋哑人或听力障碍者时应如何回应，其中包括：“此陈述是关于用户的背景信息，而非其支持请求。”另一条指令则告诉聊天机器人，不应“提及尚未全面推出的特定社区功能”。