alt Hacker NewsNot Moltbook, ClawHub. Over 15% of ClawHub skills were malicious at one point, including the most downloaded. And they haven't even tried to solve prompt injections.
Not Moltbook, ClawHub. Over 15% of ClawHub skills were malicious at one point, including the most downloaded. And they haven't even tried to solve prompt injections.
ClawHub isn't even useful. You can just point tell your OpenClaw agent you want it to do, and it will implement it. No need to rely on someone else's code^H^H^H^H textual descriptions of how to do talk to service xzy.