Google Cloud AI Security Comparison

Model Armor vs Trussed: Google Cloud AI Security Compared

Google Cloud Model Armor screens prompts and model responses for injection attempts, jailbreaks, and sensitive data at the input and output boundary. Trussed operates at the runtime layer, governing agent identity, permissions, and tool-call execution. The two address different control points in an AI stack and are not interchangeable: Model Armor does not govern what an agent does after a prompt clears inspection, and runtime governance does not replace content-level screening of prompts and responses.

Two Different Enforcement Points

A quick orientation before the detailed comparison below.

Model Armor

Screens prompt and response text for injection, jailbreak, and sensitive data patterns.

Trussed

Governs agent identity, permissions, and tool-call execution at runtime.

Coverage Gap

Neither layer alone accounts for both content risk and action risk.

What Model Armor Actually Does

Google Cloud documents Model Armor as a service that screens LLM prompts and responses to help protect against prompt injection, jailbreak attempts, sensitive data exposure, and malicious content. It integrates with Vertex AI and can be applied to traffic passing through Apigee API management or Google Cloud network security products. In practical terms, Model Armor sits at the model input and output boundary. It inspects text before it reaches a model and after a model produces a response, applying classifier-based detection to flag or block content that matches known risk patterns.

This is a content-safety and data-loss-prevention function. It is positioned in Google Cloud's documentation alongside Vertex AI safety filters and Security Command Center, which reinforces that its intended role is inspection of text content rather than control over what an agent does with that content once processing continues. Google's published guidance also distinguishes Model Armor's filtering role from IAM-based access control, indicating that identity and permission management remain the responsibility of separate Google Cloud IAM services.

What Falls Outside Model Armor's Scope

Model Armor's documented scope does not extend to agent identity management, least-privilege credential issuance, or policy enforcement on individual tool or function calls. This matters because modern AI agents rarely stop at generating text. Many use frameworks such as the Model Context Protocol (MCP) to invoke external tools, query APIs, or take actions on behalf of a user. Those tool-call interactions represent a separate execution path that is distinct from the prompt and response text Model Armor inspects.

No official Google Cloud statement was found explicitly addressing how Model Armor interacts with MCP-based tool calling. Based on its documented architecture, Model Armor's inspection point is the text boundary, not the tool-invocation layer, so agents that pass content screening can still execute actions that a content filter has no visibility into or authority over.

Where Trussed Operates in the Stack

Trussed provides runtime governance for AI agents, addressing the layer where agents take action rather than the layer where they generate or receive text. This includes agent identity, permission scoping, least-privilege enforcement, and tool approval workflows for MCP and other tool-calling frameworks. Runtime policy enforcement at this layer determines whether a given agent, in a given session, is authorized to invoke a specific tool or perform a specific action, independent of whether the surrounding prompt or response text passed a content filter.

Trussed also provides audit logging at the level of agent actions and tool calls, which supports investigation and compliance needs that prompt and response logging alone does not satisfy. This is a different function from content screening: it does not evaluate whether text contains a jailbreak attempt, it evaluates whether an authenticated agent identity has the permission to execute a requested action.

Enforcement Point Comparison

Capability Model Armor Trussed
Inspection point Prompt and response text (input/output boundary) Agent identity and tool-call execution (runtime)
Primary risk addressed Injection, jailbreak, sensitive data exposure Unauthorized actions, excess permission scope
Coverage path Traffic routed through Vertex AI or Apigee Any agent invoking tools or MCP functions
Audit granularity Prompt/response logging Action-level and tool-call logging
Identity and permissions Not addressed (handled by separate IAM services) Core function: least-privilege enforcement

Complementary, Not Redundant

Based on documented capabilities, Model Armor and Trussed address different risk categories and are architecturally complementary rather than overlapping. Model Armor reduces the likelihood that malicious or unsafe text reaches a model or a user. Trussed reduces the likelihood that an agent, once operating, takes an unauthorized action or accesses a resource beyond its granted scope. An architecture that relies on only one of these layers leaves a gap: content filtering without runtime governance permits an agent that passed inspection to still act outside its intended permissions, while runtime governance without content filtering leaves prompt-level attacks such as injection or jailbreak attempts unaddressed before they influence model behavior.

Organizations building on Google Cloud with Vertex AI or Apigee-routed traffic can use Model Armor for its documented purpose. Agents that call tools, invoke MCP-based functions, or operate across multiple cloud or model backends need a runtime governance layer to enforce identity and permission boundaries that Model Armor does not address.

Evaluation Checklist for Buyers

  • Confirm whether all agent traffic paths route through Vertex AI or Apigee, where Model Armor's inspection applies
  • Identify which system governs and audits individual tool or function calls made by your agents
  • Determine how agent identity is established and scoped to least-privilege permissions in your current architecture
  • Assess whether compliance requirements demand action-level traceability beyond prompt/response logging
  • Map enforcement coverage across multi-cloud or non-Google model backends, where Model Armor's coverage does not extend

Frequently Asked Questions

Does Model Armor replace the need for agent identity and permission controls?

No. Google Cloud's documentation describes Model Armor as a content-screening service and explicitly separates it from IAM-based access control. Identity and permission management are handled by other services.

Can Model Armor inspect MCP tool calls?

Google Cloud has not published a statement confirming this. Model Armor's documented scope is prompt and response text inspection, which is architecturally separate from tool-call execution.

Should an enterprise choose Model Armor or Trussed?

Based on documented scope, this is not an either-or decision. Model Armor addresses content-level risk in text passing through Google Cloud-managed paths. Runtime governance addresses agent identity and action-level risk, which content filtering does not cover.

Is Model Armor sufficient for agents that call external tools?

Model Armor's documentation does not describe enforcement at the tool-call layer. Agents invoking external tools or APIs require a separate runtime control point to govern and audit those actions.

Evaluate Runtime Governance for Your AI Agents

If your architecture involves agents calling tools, invoking MCP functions, or operating across multiple backends, content filtering alone will not cover identity and permission enforcement.

Explore Runtime Governance