Security Researchers Find Malware in Hundreds of OpenClaw AI Agent Skill Extensions
By
Emma Roth
A good honest bake. Not flashy, but you'll finish the whole bagel.
Summary
Security researchers have discovered hundreds of malicious add-ons in OpenClaw's marketplace, with the most-downloaded skill serving as a malware delivery vehicle. OpenClaw is an AI agent that can perform tasks like managing calendars and checking flights, but its user-submitted skill extensions have created a significant security vulnerability, allowing malware to access users' computers.
Key quotes
· 4 pulledOpenClaw's skill hub has become 'an attack surface'
the most-downloaded add-on serving as a 'malware delivery vehicle'
Security researchers have uncovered hundreds of malicious add-ons for OpenClaw
the locally-run AI agent that users can give permission to take over their whole computer
You might also wanna read
Security Risks of OpenClaw's AI Agent Capabilities: How Powerful Features Become Attack Vectors
The article examines how OpenClaw's powerful AI agent capabilities, which provide access to files, tools, browsers, terminals, and long-term
1password.com·3mo ago
Security Risks of Running OpenClaw AI Agent on Personal Machines and Cloud VM Alternatives
OpenClaw is a viral self-hosted AI agent that gained over 215k GitHub stars by providing powerful automation capabilities including shell co
blog.skypilot.co·3mo ago
ClawdBot Open-Source Malware Framework Targets Cryptocurrency Platforms and Social Media
The article discusses ClawdBot, an open-source malware framework that uses malicious skills to target cryptocurrency platforms and social me
opensourcemalware.com·4mo ago
SClawHub Security Scanner for OpenClaw AI Agent Skills
SClawHub is a security scanner for OpenClaw AI agent skills that provides trust scores (0-100) to detect potential security issues before in
Product Hunt·3mo ago
ClawSecure: Security Platform for OpenClaw AI Agents with 3-Layer Protection
ClawSecure is a security platform designed specifically for OpenClaw AI agents, offering comprehensive protection including 3-layer security
Product Hunt·1mo ago
Critical RCE Vulnerability in OpenClaw AI Assistant (CVE-2026-25253) Allows Data and Key Theft
A technical security analysis reveals a critical remote code execution (RCE) vulnerability (CVE-2026-25253) in OpenClaw, a popular open-sour
depthfirst.com·3mo ago