WhatsApp Help Pages Leaked Hidden Instructions for a Meta Chatbot Hidden text instructions intended for a Meta large language model were discovered in the source code of roughly 80 WhatsApp help and FAQ pages. These directives instructed the chatbot to avoid discussing legal matters, data protection regulations, and regulatory authorities. A recent analysis has revealed that approximately 80 help and FAQ pages across the WhatsApp website exposed text instructions specifically designed for a large language model operated by Meta. According to findings from the privacy firm Redact, these instructions appeared directly within the source code of the webpages and contained written directions that were not explicitly visible on the public-facing help pages. Uncovering the Hidden Instructions Among roughly 100 blocks of hidden text, the directives provided guidance to steer the large language model away from answering user questions in unhelpful ways, offering a rare glimpse into how chatbot parameters are structured. For instance, the WhatsApp help page detailing how to delete an account included instructions that advised the model not to recommend contacting any data protection authority, regulator, or supervisory authority regarding the issue. Dan Saltman, the CEO and founder of Redact.dev, noted that the striking element here is the fundamental gap between what human users are told versus what the underlying artificial intelligence is instructed to do. Removal and Technical Explanation The privacy firm routinely scans the websites and privacy policies of major technology corporations, observing that many of the uncovered WhatsApp instructions were straightforward and directed users toward official support channels. However, these guidelines were apparently never meant for public exposure. The hidden instructions surfaced under code blocks carrying the specific heading HelpContentGalaxyLLMInclude. After inquiries were made to Meta, the text was swiftly removed across all affected pages. Handling Legal Matters and Regulations On the webpage addressing reporting and blocking on WhatsApp, the hidden guidelines outlined precise statements to follow whenever a user mentioned legal actions, lawsuits, lawyers, attorneys, courts, or litigation. The instructions explicitly mandated that the system must not cite, quote, interpret, or reference the WhatsApp terms of service, privacy policy, or any related legal documents. Furthermore, the model was barred from making any assertions concerning liability or non-liability on behalf of WhatsApp, or providing independent legal opinions or interpretations. Additional segments of the instructions instructed the chatbot to refrain from referencing or interpreting data protection regulations such as GDPR, LGPD, or CCPA, even if a user raised those topics directly during an interaction. Joshua Breckman, a spokesperson for WhatsApp, explained that the company maintains a commitment to providing users with transparent information regarding their data rights and actionable steps. He emphasized that product support chatbots are optimized to deliver the best possible practical advice about the platform rather than offering formal legal counsel. Additional Operational Constraints Other exposed directives outlined specific protocols for responding when a user indicated they were deaf or hard of hearing, instructing the model to treat that statement merely as background context rather than the core support request. Another instruction strictly prohibited the chatbot from mentioning specific upcoming community features that had not yet been released for general availability. While it remained uncertain whether third-party bots could access the text or how long the code had been visible, the company confirmed that the display was caused by a technical bug that has since been fully resolved. What this means for you This technical leak directly affects users who rely on automated support channels for assistance. • For WhatsApp Users: When users interact with the support chatbot, they will not receive guidance regarding legal disputes, lawsuits, or regulatory authorities. This ensures that automated responses remain strictly focused on standard platform troubleshooting rather than formal counsel. • Regarding Data Privacy: The incident highlights the internal boundaries that major technology firms establish for their artificial intelligence models. Users seeking information on data rights must continue to consult official public documentation directly rather than expecting comprehensive legal interpretations from conversational bots. Why this happened This incident occurred due to an administrative oversight and technical bug that caused internal artificial intelligence directives to appear within webpage source code. • Technical Glitch: A software bug caused internal instructions written for Meta's large language model to be rendered within the underlying code of approximately 80 help pages. • Model Guidance Strategy: These hidden directives were deliberately created by developers to prevent the support chatbot from straying into complex legal territory or data protection interpretations. • External Discovery and Fix: After privacy researchers identified the exposed text in archived versions of the site and inquiries were made, the company resolved the bug and scrubbed the instructions from all affected pages. Questions & Answers 1. What was leaked from the WhatsApp help pages? Hidden text instructions intended for a Meta large language model were exposed within the source code of roughly 80 WhatsApp help and FAQ pages. 2. Who discovered the exposed instructions? The findings were uncovered during an analysis conducted by the privacy firm Redact. 3. What kind of guidance was contained in the hidden text? The directives instructed the chatbot to avoid discussing legal disputes, lawsuits, attorneys, or data protection regulations like GDPR and CCPA. 4. How did WhatsApp respond to the discovery? WhatsApp spokesperson Joshua Breckman stated that the text appeared due to a technical bug which has now been fixed and removed from the pages. 5. Were these instructions meant for public users? No, the company stated that these were instructions intended for their support chatbot to ensure accurate responses rather than direct guidance for users. https://trendkia.com/en/security/whatsapp-ke-help-page-se-leaked-hidden-instructions-for-a-meta-chatbot-49481 TrendKia — Har trend, sabse pehle.