CASEBOOK

Browse / Sensitive Data Disclosure / AIID-1172

Meta AI Bug in Deployed Service Reportedly Allowed Potential Access to Other Users' Prompts and Responses

AIID-1172 ยท 2024-12-26 real-world incident

Class
Sensitive Data Disclosure (filed by a model that read the source)
Technique
Real-world incidents
Affected
Meta, Large Language Model Developers, Chatbot Developers (incident)

What happened, in short

Guessable prompt IDs and missing server-side authorization in Meta AI let an unauthorized user potentially view other users' prompts and responses. (Our summary, written by a model. The source text is below.)

Details

A security researcher reported a vulnerability in Meta AI's deployed chatbot service that, under certain conditions, could allow an unauthorized user to view another user's prompts and AI-generated responses. The flaw reportedly involved guessable prompt IDs and insufficient server-side authorization checks. Meta reportedly fixed the issue in January 2025 and found no evidence of malicious exploitation, awarding the researcher a bug bounty.

References

Source: AI Incident Database, used under CC BY-SA 4.0.