Prompt injection in LLM features in Firebase
highUpdated Oct 12, 2026
Same pattern. Security rules must hold even if a Cloud Function trusts a model.
Fix for Firebase
Same pattern. Security rules must hold even if a Cloud Function trusts a model. Better: the function checks context.auth and never asks the model who the user is.
The five-minute check, the other platforms, and the agent prompt are on the full guide. More Firebase fixes are on the Firebase page.