We Scanned 25 OpenClaw Skills for Security Vulnerabilities — Here's What We Found
Dev.to AI
•
Generative AI
AI agents are running third-party code on your machine. Last week, Anthropic announced extra charges for OpenClaw in Claude Code, drawing fresh attention to the ecosystem. We wanted to answer a straightforward question: how safe are the most popular OpenClaw skills? We used AgentGraph's open-source security scanner to analyze 25 popular OpenClaw skill repositories from GitHub.