Partially Verified65% confidenceFactExact time
OpenShell's credential handling mechanism ensures the agent never sees the real keys; only when a request is sent to a user-approved endpoint does OpenShell inject the key.
3
Sources
65%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
NVIDIA Open-Sources OpenShell: Putting a Safety Cage Around AI Agents
bilibili岩石与宇宙的家10/25/2026
Related Entities
Related Claims
UnverifiedOpenHands v1.28.0 supports requesting secrets during a conversation: the agent can pop up a request for a secret, and once the user enters it, it is stored in Secrets in settings, and the name must exactly match the environment variable injected into the execution layer.76% similarUnverifiedOpenShell includes a policy advisor feature; when enabled, requests wait for human review rather than allowing the agent to self-approve.75% similarUnverifiedOpenShell enables anonymous telemetry by default, but users can turn it off.75% similarUnverifiedA token key is a key issued to a token group, which applications use to access the OpenAI-compatible inference endpoint without holding an account-level API key; the token group simultaneously serves as a permission boundary and a policy container.74% similarUnverifiedNVIDIA open-sourcing OpenShell is a signal of extending from compute supplier to agent infrastructure, aiming to seize the entry point of agent security boundaries.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1103867API
curl https://kongchang.com/api/v1/knowledge/claims/1103867MCP
get_claim(id=1103867)