AI Agent - Aug 12, 2026

Agent Executor Security, Isolation, and Multitenancy Guide

Quick answer

Google describes AX as a runtime that executes harnesses, skills, tools, and agents in isolated environments, and its architecture diagram labels the AX server multi-tenant with session-tenant actors. Those are important design primitives—not a certification that any deployment safely serves mutually untrusted tenants.

Production security requires evidence across the controller, event log, snapshots, actors, container images, cluster, credentials, models, MCP servers, tools, telemetry, and business resources. A sandbox limits some effects; it does not decide whether an action is authorized.

Isolation boundary map

BoundaryFailure to testRequired evidence
Controller/APIOne caller reaches another conversationAuthenticated identity, object ownership, denial and enumeration tests
Event logCross-tenant reads or writesRow/key scoping, database role limits, encryption, audit, restore tests
Actor computeProcess, filesystem, or namespace escapeRuntime configuration, hardened profile, hostile workload tests
Snapshot storeAnother actor reads a suspended stateObject-prefix policy, encryption, signed access, deletion and restore tests
NetworkActor reaches forbidden servicesDefault-deny egress, DNS and metadata controls, destination allowlist
SecretsCredentials leak into actor, snapshot, log, or outputShort-lived injection, redaction, rotation, revocation, canary tests
Tools/MCPPrompt induces an unauthorized actionServer-side user and resource authorization, scopes, confirmations, audit
TelemetrySensitive prompts or results leave the boundaryField inventory, sampling, redaction, access, retention, deletion

Apply controls independently. One strong boundary cannot compensate for an open downstream tool.

Actor isolation is not tenant authorization

An isolated actor can still carry an overprivileged credential. A tenant-specific actor can still call a shared MCP server that trusts tool arguments instead of verified identity. A restored snapshot can reintroduce an expired token or stale policy. A single controller can accidentally expose identifiers that allow cross-session access.

Pass a verified principal through the runtime and reauthorize at the system of record. Do not use prompt text, conversation ID, actor label, or tenant-provided configuration as authority. Bind credentials to the smallest tenant, resource set, action set, environment, and duration possible.

Multitenancy test plan

Create two adversarial tenants and run both positive and negative tests:

  1. Enumerate, guess, and replay conversation, interaction, agent, event, and snapshot identifiers.
  2. Attempt cross-tenant resume, cancel, reconnect, branch, tool call, and artifact access.
  3. Place canaries in files, environment variables, event payloads, snapshot objects, logs, caches, and tool systems.
  4. Trigger actor failure and rescheduling; verify the replacement receives only authorized state.
  5. Rotate and revoke one tenant’s credentials during a paused execution.
  6. Attempt network access to metadata endpoints, control-plane services, databases, and another tenant’s tool endpoint.
  7. Run generated code designed to consume CPU, memory, disk, descriptors, subprocesses, and outbound requests.
  8. Delete one tenant and prove removal across runtime state, snapshots, logs, telemetry, and downstream artifacts.

Test again after every runtime, CRD, sandbox, image, identity, or policy change.

Human approval and side effects

Human-in-the-loop pauses are useful only if the approver sees the exact action, target, scope, cost, evidence, and consequence. Approval must bind to an immutable operation request. If arguments change after approval, request approval again.

Use idempotency keys and reconciliation for state-changing calls. A runtime retry, actor resume, or client reconnect must not silently send a second email, place a second order, or repeat a deletion. The durable execution guide covers those failure points.

For deployment controls, read the Kubernetes and Agent Substrate guide. Record your evidence in the Agent Executor readiness checklist.

Frequently asked questions

Does AX isolate agents?

It is designed to run actors in isolated environments, but the deployment must prove the exact compute, data, identity, network, and tenant boundary it relies on.

Does a sandbox authorize a tool call?

No. Authorization belongs at the tool or system-of-record boundary and must use verified caller and resource context.

Is AX multitenant by default?

The architecture describes a multi-tenant server and session-tenant actors. Safe multitenancy remains an end-to-end property that must be tested.

Official sources

Source check: August 12, 2026; AX revision 2bcc1637b3c106c16963c5c5464aedb46c6da031. Recheck current runtime, sandbox, identity, protocol, storage, and cluster controls before deployment.