A smart AI would realise that I can MITM its web access such that sees the .well-known token that isn't actually there. I assume that the model doesn't have CA certificates embedded into it, and relies on its harness for that.
MITM the cloud AI on the modern internet is non-trivial, and probably harder and less reliable than just talking your way around the guardrails anyhow.
Looking upthread, we seem to be talking about Claude. Claude is cloud-hosted inference but the harness is local if you're using Claude Code, and can be MITM'd there.