OpenClaw AI agents targeted for the first time by infostealer malware

(Image credit: Shutterstock / NicoElNino)

Subscribe to our newsletter


  • Hudson Rock detects first infostealer attack stealing OpenClaw AI helper configuration files
  • Stolen secrets (API keys, tokens) could provide access to linked applications like Telegram or calendars
  • Researchers warn that information thieves may soon add dedicated modules to analyze data from AI agents, increasing risks to professional workflow.

Thanks to its immediate success and widespread adoption, OpenClaw has drawn a big target on its back and is now under attack by information thieves, after security researchers at Hudson Rock claimed to have seen a first-of-its-kind attack in the wild.

OpenClaw (formerly known as Clawdbot and Moltbot) is open source AI assistive software designed to actually perform tasks, rather than just answer questions or generate multimedia. Users can set it up on their personal computers or servers and connect it to apps like Telegram, calendars, etc., after which it can perform practical tasks like email management, scheduling meetings and tasks, and automating workflows.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top