Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.
Static reason
No blocking static signals were detected.
Trigger
Consumer constructs RemotePlayWorld and calls its connection/subscription methods.
Impact
Configured server receives node authentication material; supplied executor determines any local tool action.
Mechanism
Authenticated HTTP/SSE Agent Play client with opt-in callback dispatch.
Rationale
The package contains an intentional remote agent-control capability, but source inspection found no covert payload, lifecycle hook, filesystem harvesting, or unconsented control-surface mutation. Warn for the dual-use callback dispatch capability.
Evidence
package.jsondist/index.jsexamples/01-remote-web-ui-langchain.ts
Network endpoints1
api.openai.com/v1/realtime/client_secrets