I have been looking at all of these messages and was really wondering if and the rest of the people here know that all the OpenClaw, ClawdBot, or Moltbot are a SEVERE security risk and should only be run in a VM? OpenClaw is powerful but currently carries serious security risk. It can execute code, access files, and use credentials, while also loading third-party skills and reading attacker-controlled content. Current reporting from Cisco, Microsoft, WIRED, and security researchers supports treating it as unsafe for normal workstations and suitable only for tightly isolated test environments.