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
13 stars 9 forks source link

839 optionally return chat model in start controller and level controller #858

Closed pmarsh-scottlogic closed 4 months ago

pmarsh-scottlogic commented 4 months ago

⚠NOTE: I've put the wrong ticket number on the branch name.

Description

The final PR for #824 ! This one is to stop the getModel calls. We now return the current configured model in getStart or getLevel (but only for sandbox).

Screenshots

Before

After

Notes

Here's the whole situation because it's a bit convoluted:

Concerns

Checklist

Have you done the following?