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
15 stars 10 forks source link

741 transformed messages not showing correctly #800

Closed pmarsh-scottlogic closed 7 months ago

pmarsh-scottlogic commented 7 months ago

Description

Fixes a bug where transformed messages would appear differently after page refresh. A user's transformed message stays shown with the original message in bold, and the info message "xml tagging enabled, your message has been transformed" remains.

Screenshots

image

Notes

main ticket changes

testing

refactoring

Concerns

Checklist

Have you done the following?