Open-sourcing ClawHub skill security scan dataset with NVIDIA
Original title:In collaboration with @nvidia, we’re open-sourcing a dataset of security scans for 67,453 ClawHub sk...
AI summary
Working with @nvidia, we open-sourced a dataset of 67,453 ClawHub skill security scans on @huggingface: - NVIDIA SkillSpector flagged 1 in 2 agent risks - only 0.31% were malicious - no two scanners agreed on more than 8.5% of risks https://openclaw.ai/blog/openclaw-nvidia-skill-security
Key Takeaways
- Working with @nvidia,we open-sourced a dataset of 67,453 ClawHub skill security scans on…
- 31% were malicious - no two scanners agreed on more than 8.
- 5% of risks
Quick Facts
- Published
- Updated
- Source
- X:OpenClaw (@openclaw)
- Category
- Papers & Research
- AI score
- 72
OpenClaw 和 NVIDIA 开源了 6.7 万个 agent skill 的扫描结果,一半被标风险但真正恶意的不到千分之三,不同扫描器几乎没共识。做 agent 安全的应该看看。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Open-sourcing ClawHub skill security scan dataset with NVIDIA. June 1, 2026. https://new.nat6.net/en/news/cmpusv86800mjsl0zl7u3l9ia/