1.0
Security belongs in the product
Operators need to see whether sender domains, signed routes, secrets, and policy gates are ready before support traffic scales.
- Signature verification
- Domain status
- Outbound limits
Home
Product
Security Center
A visible control plane for MFA, signed inbound routes, domain readiness, prompt-injection flags, and executor gates.
Posture
Visible
Security health is part of daily operations.
Scope
Tenant
Workspace access and project data stay separated.
Gates
Always
Executors check policy before side effects.
2.0
Prompt injection is operational risk
Suspicious instructions in email bodies and attachments are flagged as support risk, not treated as trusted system context.
- Injection flags
- Attachment policy
- Model context boundaries
Operations
What this means in production.
These pages describe the product contract behind the UI, not a decorative brochure. Each surface should connect back to the same governed support loop.
Control boundary
Provider tokens are never exposed client-side.
Operator workflow
Support moves through secure ingest, AI preparation, human approval, outbound execution, and audit evidence.
Configuration impact
Provider setup, project policies, knowledge trust, retention, and billing limits decide how this behaves for a real workspace.
Proof points
Designed for governed support, not hidden autonomy.
Provider tokens are never exposed client-side.
Protected routes re-check authorization.
Risk events remain filterable.
References
Official stack and legal references.
These external links point to provider documentation, privacy notices, data-processing terms, or platform terms that shape production operation.
Next