logoalt Hacker News

cyanydeezyesterday at 10:27 PM2 repliesview on HN

The backing to OpenClaw/MoltBot whatever they're calling themselves. Why is it insecure, well, Pi tells you >No permission popups.

Anyway, even if you give your agent permission, there's no secure way to know whether what they're asking to is what they'll actually do, etc.


Replies

chriswarbotoday at 12:57 AM

> Why is it insecure, well, Pi tells you >No permission popups.

Pi supports permission popups, but doesn't use them by default. Their example extensions show how to do it (add an event listener for `tool_call` events; to block the call put `block: true` in its result).

> there's no secure way to know whether what they're asking to is what they'll actually do

What do you mean? `tool_call` event listeners are given the parameters of the tool call; so e.g. a call to the `bash` tool will show the exact command that will execute (unless we block it, of course).

himata4113yesterday at 10:46 PM

you want to put agents in a sandbox instead such as bwrap anyways.