Peter Steinberger 馃#495
In collaboration with @nvidia, we鈥檙e open-sourcing a dataset of security scans for 67,453 ClawHub skills on @huggingface:
- NVIDIA SkillSpector flagged 1/2 for agentic risk - Only 0.31% were malicious - No two scanners agreed on more than 8.5% of risks https://openclaw.ai/blog/openclaw-nvidia-skill-security
Super proud to be collaborating with @nvidia to analyze and release the largest SKILL security dataset based on @openclaw data. Full paper and dataset in the 馃У
In collaboration with @nvidia, we鈥檙e open-sourcing a dataset of security scans for 67,453 ClawHub skills on @huggingface:
- NVIDIA SkillSpector flagged 1/2 for agentic risk - Only 0.31% were malicious - No two scanners agreed on more than 8.5% of risks https://openclaw.ai/blog/openclaw-nvidia-skill-security
On ClawHub, we take a multi-layered approach to skill scanning:
1. VirusTotal for malware risk in bundled code 2. Static analysis for code/text findings 3. NVIDIA SkillSpector for agentic risk in instructions
And combine these into a single ClawScan score.
In collaboration with @nvidia, we鈥檙e open-sourcing a dataset of security scans for 67,453 ClawHub skills on @huggingface:
- NVIDIA SkillSpector flagged 1/2 for agentic risk - Only 0.31% were malicious - No two scanners agreed on more than 8.5% of risks https://openclaw.ai/blog/openclaw-nvidia-skill-security
Peter Steinberger 馃#495In collaboration with @nvidia, we鈥檙e open-sourcing a dataset of security scans for 67,453 ClawHub skills on @huggingface:
- NVIDIA SkillSpector flagged 1/2 for agentic risk - Only 0.31% were malicious - No two scanners agreed on more than 8.5% of risks https://openclaw.ai/blog/openclaw-nvidia-skill-security
Many users praised OpenClaw and NVIDIA for open-sourcing their large AI skill security dataset because it promotes transparency and helps the community build safer tools.