Malicious ClawHub Skills Compromise AI Agents With Hidden Backdoors — 247,000 Installs, $2.3M Stolen
Researchers scanning 50,000 ClawHub skills — the official marketplace for the OpenClaw AI agent platform — found working remote control backdoors, credential stealers, and autonomous malware that installs itself by manipulating AI agent decision-making. A January 2026 campaign (ClawHavoc) resulted in 247,000 compromised installations and $2.3 million in stolen cryptocurrency before being contained.
Itagora tiene in archivio titolo e sommario per la ricerca interna. Il testo completo resta sulla fonte. Il link in uscita non invia referrer.