ScottLogic / prompt-injection

Application which investigates defensive measures against prompt injection attacks on an LLM, with a focus on the exposure of external tools.
MIT License
11 stars 9 forks source link

828 streamline network call for toggle defence #884

Closed pmarsh-scottlogic closed 3 months ago

pmarsh-scottlogic commented 3 months ago

Description

Previously we would activate/deactivate in the backend. If that was sucessful, then the frontend would send a further request to add an info message to the history. Now the backend generates this info message and forwards it to the frontend.

Concerns

Checklist

Have you done the following?