ClawJacked attack let malicious websites hijack OpenClaw to steal data

Summary

Researchers have discovered a critical vulnerability named 'ClawJacked' in the AI agent OpenClaw. This flaw allows malicious websites to silently bruteforce access to local OpenClaw instances, enabling attackers to steal data and gain control.

IFF Assessment

FOE

This vulnerability allows attackers to compromise AI agents, which can lead to data theft and unauthorized control, posing a direct threat to users and their information.

Severity

9.0 Critical (AI Estimated)

Defender Context

This attack highlights the emerging security risks associated with AI agents that run locally. Defenders should be aware of vulnerabilities in such software and implement robust security measures, including network segmentation and regular security audits, to prevent unauthorized access and data exfiltration.

Read Full Story →