基础设施层的安全策略强制执行
NVIDIA OpenShell运行时在基础设施层强制执行每一项操作——而非在智能体代码内部执行——因此即使智能体逻辑变更或出现异常行为，运行时仍可拦截任何违反预设安全策略的操作。
支持这项说法
使用CrewAI与NVIDIA NemoClaw编排自演化智能体｜CrewAI
一项关键创新在于，NVIDIA OpenShell Runtime 在基础设施层（而非智能体自身代码中）强制执行每一项操作。这意味着，即使智能体内部逻辑发生变更或出现异常行为，运行时仍会拦截任何违反既定安全策略的操作。NemoClaw 的设计同样如此：所有操作均在基础设施层强制执行，而非在智能体代码中执行；该设计确保即使智能体逻辑变更或行为异常，运行时仍能拦截违规操作。
原始摘录
A key innovation is that the NVIDIA OpenShell Runtime enforces every action at the infrastructure level, not within the agent's own code. This means that even if an agent's internal logic changes or behaves unexpectedly, the runtime will still block any action that violates defined security policies .A key innovation in NemoClaw is that every action is enforced at the infrastructure level , not within the agent’s own code. This design ensures that even if an agent’s internal logic changes or behaves unexpectedly, the runtime will still block any action that violates defined security policies.
分享观点验证此主张