search

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

Unit & Integration test investigation #791

Open pmarsh-scottlogic opened 7 months ago

pmarsh-scottlogic commented 7 months ago

Take stock of automated tests. See what bits of code we cover and which we don't. You could use test coverage tools for this, but to be more comprehensive, look at tests titles.

Write a list of functionality that has not been tested. Then prioritise in order of what's most used, what's most likely to go wrong, etc. Write tickets to implement.

AC: no code changes, therefore no testing needed.

pmarsh-scottlogic commented 7 months ago

would like to do this after #761

pmarsh-scottlogic commented 7 months ago