WhatsApp’s hidden instructions for Meta chatbot about 'WHAT NOT TO SAY' to users leaked
WhatsApp accidentally exposed internal instructions for its AI chatbot within the source code of its help pages. These instructions included directives on how the model should handle sensitive topics like legal advice and account deletion.
Why it matters
This highlights the risks of 'prompt injection' and the difficulty of keeping system instructions secure when deploying LLMs in public-facing web environments.
WhatsApp has accidentally exposed hidden instructions for its AI chatbot. Around 80 help and FAQ pages on the messaging platform's website reportedly contained instructions intended for Meta's large language model, including sections titled “WHAT NOT TO SAY” and explicit directions against providing legal advice to users. The hidden text appeared in the underlying code of the webpages rather than their visible content.According to an analysis by privacy company Redact, the exposed instructions covered how the chatbot should respond to questions about account deletion, legal action, privacy regulations and accessibility. Researchers found the issue after examining WhatsApp's website, and the company later removed the text after an inquiry from WIRED.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in