never trust a screenshot of a command prompts output blindly either.
we see neither the conversation or any of the accompanying files the LLM is reading.
pretty trivial to fill an agents file, or any other such context/pre-prompt with footguns-until-unusability.
That's true. Claude Code should lawyer up. This is a clear case of libel.
You are welcome to review the full session here - https://gist.github.com/bretonium/d1672688feb5c5cbccf894c92d...