>IMO the security pitchforking on OpenClaw is just so overdone.

Isn't the whole selling point of OpenClaw that you give it valuable (personal) data to work on, which would typically also be processed by 3rd party LLMs?

The security and privacy implications are massive. The only way to use it "safely" is by not giving it much of value.

There's the selling point of using it as a relatively untrustworthy agent that has access to all the resources on a particular computer and limited access to online tools to its name. Essentially like Claude Code or OpenCode but with its own computer, which means it doesn't constantly hit roadblocks when attempting to uselegacy interfaces meant for humans. Which is... most things to do with interfaces, of course.