Fetching from the wire…
Agents2026-05-10 · source-backed
NVIDIA's OpenShell enforces security policy at the execution layer without modifying agent code. Each agent runs in its own container with policy-enforced egress routing. Policies are declarative YAML controlling filesystem access, network, process execution, and inference calls. ServiceNow adopted it immediately. This pairs with NVIDIA's Red Team guidance declaring that LLM-generated code must be treated as untrusted output and all config file writes must be blocked.
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entities / Same source / Shared topic / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover Kernel, Level Isolation, NVIDIA; cite the same source (NVIDIA's Red Team guidance).
NVIDIA released OpenShell / Shared entities / Same source / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (NVIDIA released OpenShell); both cover Kernel, NVIDIA; cite the same source (NVIDIA's Red Team guidance).
LLM uses OpenAI / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover Each, LLM; reported by the same outlet (developer.nvidia.com, github.com).
Cursor partners with NVIDIA / Shared entities / Same source domain / Shared topic / What happened next / Tension
Linked by a graph relationship (Cursor partners with NVIDIA); both cover Apache, LLM; reported by the same outlet (github.com).
NVIDIA released OpenShell / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (NVIDIA released OpenShell); both cover Apache, NVIDIA; reported by the same outlet (github.com).
NVIDIA partners with Google / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (NVIDIA partners with Google); both cover Each, ServiceNow; reported by the same outlet (github.com).
NVIDIA uses Claude Code / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (NVIDIA uses Claude Code); both cover Each, LLM; overlapping topics (access, agent, code).
NVIDIA uses Codex / Shared entities / Same source domain / What happened next / Tension
Linked by a graph relationship (NVIDIA uses Codex); both cover Apache, Each; reported by the same outlet (github.com).