[X]score: 0.34
In collaboration with @nvidia, we’re open-sourcing a dataset of security scans for 67,453 ClawHub skills on @huggingface: - NVIDIA SkillSpector fla…
June 1, 2026
A dataset of security scans across 67,453 agentic AI skills is now public on Hugging Face, produced using NVIDIA SkillSpector. SkillSpector flagged roughly 50% of skills for agentic risk, but only 0.31% were confirmed malicious, and scanner agreement on risk classification topped out at 8.5%, highlighting low consensus across tools.