ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
A new dataset called ClawHub Security Signals has been released, containing 67,453 OpenClaw skill versions to analyze the security of AI agents. The dataset reveals significant disagreement among three security scanners: VirusTotal, static analysis, and NVIDIA SkillSpector. Each scanner flags different types of risks, with SkillSpector focusing on agentic risks and VirusTotal on traditional malware, highlighting the need for layered security approaches for AI agent skills. AI
IMPACT Highlights the need for multi-layered security approaches for AI agents, moving beyond single-scanner solutions.