Thèmes / runtime security design

Point de vue reformulé

Infrastructure-level policy enforcement

NVIDIA OpenShell Runtime enforces every action at the infrastructure level—not within the agent’s own code—so even if an agent’s internal logic changes or behaves unexpectedly, the runtime blocks actions violating defined security policies.

Derrière ce point de vue

Les traductions sont destinées à la lecture ; les extraits originaux restent la source evidence.

Orchestrating Self-Evolving Agents with CrewAI and NVIDIA NemoClaw | CrewAI

Extrait original

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.