The methods could be better described in the paper, but my understanding is that they did 10 runs for each question for each prompt and took an average of those, so the compared values are not binary. You could do a sign test, but you'd lose power and answer a bit different question.

I don't know much about stats, but does "the null is that the success rate is the same" imply that it's a sketchy methodology because they can come up with some findings ("ruder prompts are better/worse!") more often?