OpenClaw project hits over 148,000 GitHub stars amid security concerns
OpenClaw, once called Clawdbot, is an open-source AI project by Peter Steinberger that's quickly become a GitHub favorite, racking up over 148,000 stars.
It uses models like Claude and ChatGPT to help with daily tasks, but its fast rise has also exposed some big security issues.
OpenClaw team issues 34 security commits
With concerns like scam risks and system hacks popping up, the team has already rolled out 34 security-related commits to patch things like a one-click remote code execution (RCE) vulnerability and command injection flaws.
Steinberger points out this isn't just OpenClaw's problem: "Remember that prompt injection is still an industry-wide unsolved problem, so it's important to use strong models and to study our security best practices."
He's continuing to work on additional security improvements as AI keeps evolving.