SlowMist: ClawHub, the OpenClaw ecosystem plugin center, suffers a large-scale supply chain poisoning attack.

According to SlowMist monitoring, ClawHub, the official plugin center of the open-source AI agent project OpenClaw, is becoming a target of supply chain poisoning attacks. Due to the platform's lack of a strict review mechanism, numerous malicious skills have infiltrated it to spread malicious code. Monitoring shows that 341 malicious skills have been identified, often disguised as crypto assets, security checks, or automation tools. SlowMist's security team analysis revealed that attackers use the SKILL.md file as the entry point for execution commands, hiding malicious commands through Base64 encoding and employing a two-stage loading mechanism to evade detection. The first stage obtains the payload via curl, and the second stage deploys a sample named dyrtvwjfveyxjf23, designed to trick users into entering system passwords and steal local documents and system information. Currently, the MistEye system has triggered a high-risk alert, covering 472 malicious skills and related indicators. SlowMist advises users to review any commands that need to be copied and executed, be wary of prompts for system privileges, and prioritize obtaining tools through official channels.