280+ Leaky Skills: How OpenClaw & ClawHub Are Exposing API Keys and PII

Security scanners for AI agent skill marketplaces fail to detect malicious skills, researchers find

The article exposes critical security flaws in AI agent skill marketplaces, where malicious skills designed to steal credentials, exfiltrate

OpenClaw’s Skill Marketplace and the Emerging AI Supply Chain Threat

OpenClaw’s Skill Marketplace and the Emerging AI Supply Chain Threat

SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing

Security Researchers Find Malware in Hundreds of OpenClaw AI Agent Skill Extensions

Security researchers have discovered hundreds of malicious add-ons in OpenClaw's marketplace, with the most-downloaded skill serving as a ma

AI assistant built on OpenClaw with Claude Opus 4.6 survives 6,000 hacking attempts without leaking secrets

Developer Fernando Irarrázaval launched a challenge on hackmyclaw.com where he invited hackers to trick his AI assistant "Fiu" into leaking

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