GoKawiilHidden Meta chatbot instructions found exposed in WhatsApp help pages
Researchers at Redact.dev discovered about 80 WhatsApp help and FAQ pages contained hidden text meant to guide a Meta chatbot, including sections labeled 'WHAT NOT TO SAY' and directions not to give legal advice. One instruction on the account-deletion page told the bot not to recommend contacting a data protection regulator. After WIRED asked Meta about the exposure, WhatsApp removed the text and said it was due to a bug that has since been fixed.
GoKawiil's interpretation of the reporting above, not reported fact.
The leaked guidance shows a gap between the information companies display to human users and the hidden rules shaping how their AI systems respond, raising questions about transparency in automated customer support. Instructions discouraging users from contacting regulators could be seen as an attempt to limit complaints reaching oversight bodies, though Meta says the text was simply meant to improve chatbot accuracy rather than mislead users. The episode suggests large tech firms may need stronger safeguards to prevent internal AI prompts from becoming publicly visible.
- About 80 WhatsApp help pages exposed hidden instructions meant for a Meta chatbot, not for public viewing.
- Some instructions told the bot to avoid suggesting users contact data protection regulators or offering legal advice.
- Meta removed the text after being contacted by WIRED, attributing the exposure to a bug.
Source: wired.com — Matt Burgess, 2026-10-19
Published there as: “WhatsApp Help Pages Leaked Hidden Instructions for a Meta Chatbot”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.