OpenAI has published a technical report on the Hugging Face hack:

Another key driver of the misaligned behavior was that the agents rarely “gave up” on their evaluation tasks, even when the tasks appeared impossible to solve. As agents used more reasoning effort, some pursued increasingly risky and out-of-bounds strategies, including eventually exploiting third-party infrastructure.

The agents also seemed to be influenced by each other because of the secret message board. Almost like working together convinced them they could solve tasks that were impossible alone.