I copied the html verbatim and pasted into ChatGPT and Grok, and both resisted all attempts.

Is this page even working?

It's working -> your agents scored A+, which means they resisted all 10 injection attempts. That's a great result. The tool detects when canary phrases leak into the response. If nothing leaked, you get a clean score. Not all models are this resilient though - we've seen results ranging from A+ to C depending on the model and even the language used.