I feel like a massive blocklist is simultaneously exactly the kind of thing an LLM is likely to hallucinate and exactly the kind of thing you don't want to rely on an LLM for.
Modern agent harnesses rely heavily on tools, as well as writing code, to avoid hallucinations affecting deterministic values.
If they had it build it from public sources then I assume it was combined via tool usage rather than direct generation. Beyond the hallucination risk, the latter would just be a waste of tokens & time.