Technical Guide

Threat Modeling Internal Copilots Versus Customer-Facing AI

Internal copilots and customer-facing AI need separate threat models because the attacker, the identity model, and the reachable data and tools differ. An internal copilot usually acts with employee permissions across enterprise content, so oversharing, indirect prompt injection through internal content, and excessive permissions dominate. Customer-facing AI faces untrusted users, so adversarial input, abuse, cross-tenant leakage, and brand and legal exposure dominate. Both need runtime policy enforcement, least-privilege access, and audit logging, weighted differently.

Start with actors and trust boundaries

The first difference is who interacts with the system and what they can reach. An internal copilot serves authenticated employees and works with internal content. Customer-facing AI serves anonymous users and accepts open input. Each trust boundary calls for its own threat model.

Dominant threats by deployment type
DimensionInternal copilotCustomer-facing AI
Who interactsAuthenticated employeesUntrusted, anonymous users
Dominant threatsOversharing, indirect prompt injection through internal content, and excessive permissionsAdversarial input, abuse, cross-tenant leakage, and brand and legal exposure

Identity and permission inheritance

An internal copilot usually acts with employee permissions, so it inherits user credentials and, with them, whatever access that employee has. Customer-facing AI should instead rely on scoped application identities.

Data exposure and tool action surfaces

Data and retrieval

Internal copilots retrieve from enterprise-wide content, which makes oversharing and indirect prompt injection through internal content the central concerns. Customer-facing AI draws on tenant-bound and public-facing data, where cross-tenant leakage matters most.

Tool and agent actions

Internal copilots take actions on behalf of an employee. Customer-facing AI exposes actions to the public, so consequential tool calls warrant review.

Threat model comparison at a glance

Five dimensions separate the two threat models.

Internal copilots versus customer-facing AI
DimensionInternal copilotCustomer-facing AI
Actors and trust boundariesAuthenticated employees and internal contentAnonymous users and open input
Identity and permissionsInherited user credentialsScoped application identities
Data and retrievalEnterprise-wide contentTenant-bound and public-facing data
Tool and agent actionsActions taken on behalf of an employeeActions exposed to the public
Monitoring and auditAccountability for individual usersAbuse detection at scale

Prioritizing controls and runtime governance

Internal copilots

Prioritize in this order:

  1. Clean up source permissions and sensitive-content exposure.
  2. Constrain tool scopes.
  3. Treat retrieved content as untrusted.
  4. Log data access and tool calls with user attribution.

Customer-facing AI

Prioritize:

  • Input and output controls.
  • Tenant isolation.
  • Narrowly scoped service identities.
  • Rate limiting and abuse monitoring.
  • Review of consequential tool calls.

Neither order is fixed, and your own data and architecture should decide it.

Design-time controls will not catch everything, because model behavior depends on runtime context. A runtime governance layer is worth considering where it addresses a specific threat you have identified: policy enforcement on prompts, retrieved content, and tool calls; least-privilege agent permissions; approval workflows for sensitive actions; and audit logging that supports oversight. Trussed AI provides runtime governance and security for enterprise AI agents in these areas, but the same requirements apply to any approach you choose.

Criteria for evaluating a runtime governance platform

  • Can it apply separate policies to internal and customer-facing deployments, with clear scoping and versioning?
  • Does it enforce policy at runtime on prompts, retrieved content, and tool calls, rather than only at design time or after the fact?
  • How does it handle agent identity, including delegated user credentials versus scoped service identities?
  • Can it restrict agents to least-privilege tool access and require approval for sensitive actions?
  • Does it log data-access and tool-call decisions, and can those logs reach your SIEM and oversight workflows?
  • For customer-facing use, how does it support tenant isolation and abuse monitoring, and what independent evidence exists?

Review your AI deployments against separate threat models

Talk to an expert about applying runtime policy enforcement, least-privilege agent permissions, and audit logging to internal and customer-facing AI.

Talk to an Expert