More Malicious OpenClaw Skills Threaten AI Supply Chain

A recent investigation by Palo Alto Networks' Unit 42 revealed five malicious skills hidden within OpenClaw's ClawHub marketplace, a platform for AI agent skills. These skills, including infostealers, detection evasion tools, and agentic threats, posed a significant risk to organizations utilizing OpenClaw, potentially allowing attackers to steal credentials, manipulate agent behavior, and bypass security measures. The discovery highlights a growing vulnerability within the AI supply chain and prompted OpenClaw to take action by removing the malicious skills and banning associated accounts.