OpenClaw AI hub faces wave of poisoned plugins, SlowMist warns
SlowMist flagged 472 AI skills containing malicious code, as plugins and extensions increasingly become a target for hackers seeking access to the devices of cryptocurrency investors.
A plugin hub associated with the open-source artificial intelligence agent project OpenClaw has become a target for supply chain poisoning attacks, according to a new report from cybersecurity firm SlowMist.
In a report released on Monday, SlowMist said attackers have been uploading malicious “skills” to OpenClaw’s plugin hub, known as ClawHub, exploiting what it described as weak or nonexistent review mechanisms. The activity allows harmful code to spread to users who install the plugins, potentially without realizing the risk.
SlowMist said its Web3-focused threat intelligence solution, MistEye, issued high-severity alerts related to 472 malicious skills on the platform.
