AI Security Is an Engineering Problem — How to Solve It at Every Layer of the Agent Stack
AI Security Is an Engineering Problem — How to Solve It at Every Layer of the Agent Stack
NVIDIA argues AI security should be treated as an engineering problem, with explicit requirements, executable controls, named owners and evidence of effective protection. Its open-source NVIDIA OpenShell enforces policies outside agent reasoning and provides sandboxed execution. Cisco DefenseClaw adds governance, while JFrog integrates OpenShell to scan and validate agent skills.
Selection record
Not admittedSum of both 84 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：讨论AI Agent安全工程与防护栈
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: NVIDIA Blog · blogs.nvidia.com