Softlander Book a call
Agent sandbox assurance

Isolation-boundary testing

Verify the resource boundaries an execution environment is meant to enforce

A new isolation configuration or shared-host deployment is proposed. The decision is how to verify the resource boundaries an execution environment is meant to enforce. The work begins with your actual workflow and looks for the evidence that separates intended behaviour from a consequential exception. It is particularly relevant to runtime engineers and security test owners. A useful outcome is an explicit account of what was examined, what remains uncertain, and which decision the evidence can support.

Book a 30 minute readiness callBrowse this capability group

The runtime isolation relationship

  1. Starting evidenceApproved boundary claims

    Establish the basis for allowed fixture.

  2. Decision boundaryDenied fixture

    Exercise an explicitly excluded resource.

  3. Decision artefactIsolation test matrix recording allowed, blocked

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. Untested surfaces remain outside the conclusion.

Decision

Frame the decision around allowed fixture

Questions and the evidence they need

Criterion / evidenceAllowed fixture
Inspect approved boundary claims for the relevant constraint or observation.
Criterion / evidenceDenied fixture
Inspect synthetic fixtures for the relevant constraint or observation.
Criterion / evidenceHost observation
Inspect runtime policies for the relevant constraint or observation.
Read each criterion against the available evidence before deciding that additional work is needed.

The decision is how to verify the resource boundaries an execution environment is meant to enforce. This is relevant to runtime engineers and security test owners when a new isolation configuration or shared-host deployment is proposed. Name the affected workflow, the consequence of a wrong decision, and the owner who can act on the result. The initial discussion should establish which evidence is already available and which uncertainty is material enough to investigate.

The specific failure hypothesis is that a restriction works for one access route but an alternate interface reaches the same resource. It remains a hypothesis until examined in the deployment. Existing internal tests or operating records may already resolve it; identify the uncovered question before commissioning additional work.

Mechanism

Isolation claims need observations on both sides

Relationships within runtime isolation

Source or conditionAllowed fixture
Demonstrate intended access using harmless markers.
Crossing or choiceDenied fixture
Exercise an explicitly excluded resource.
Consequence or decisionHost observation
Corroborate worker reports with boundary evidence.
Compare effective controls with harmless test observations. Each relationship needs evidence in the actual scope.

What this specialty examines

Isolation testing should enumerate resources on both sides of a claimed boundary. Use controlled markers and allowed operations so each result has a clear meaning. A test that never attempted the relevant access should not be reported as evidence that isolation held.

The review should exercise agreed cross-boundary cases using harmless markers and compare runtime and host evidence. Identify the normal route, relevant exceptions and the authoritative record of the outcome. Inspect the relevant business-system record, enforcement event or process evidence alongside any reported status. Keep incomplete cases visible, with an explanation of what their absence prevents the owner from concluding.

The tradeoff to make explicit

For this decision, deeper boundary coverage requires visibility into the host and control plane. Compare the available design or operating choices against the same intended outcome. If one option removes a required control or changes the task boundary, describe that difference before treating its apparent simplicity, speed or lower effort as an improvement. The decision should expose the tradeoff instead of burying it in an aggregate score.

Preparation

Connect the working inputs to the boundary being examined

Evidence packet for allowed fixture

Illustrative working format

BasisApproved boundary claims
Identify provenance and the specific decision this material can inform.
ContextSynthetic fixtures
Keep expected behaviour and the limits of the constructed example explicit.
ObservationRuntime policies
Confirm the applicable revision and who resolves disputed interpretation.
DependencyHost observations
Retain the observed conditions and distinguish gaps from contrary evidence.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with approved boundary claims, synthetic fixtures, runtime policies and host observations. Identify the owner, revision and operating context of each source. Sanitised examples may support initial design, but differences from actual conditions should remain explicit. Where direct access is unsuitable, a customer-controlled evidence or execution route may be considered, with agreed handling and retention.

The scope also needs the runtime owner, agreed expectations for a representative boundary test, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which a restriction works for one access route but an alternate interface reaches the same resource from acceptable behaviour. If stakeholders disagree about intended behaviour, resolve the interpretation before classifying the observed difference as a defect.

How the work proceeds

Carry allowed fixture through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsApproved boundary claims

    Declare the permitted environment and resources.

  2. Examine the relationshipDenied fixture

    Apply the scoped check to host observation.

  3. Retain the findingIsolation test matrix recording allowed, blocked

    Record the evidence, open dependencies, and the owner’s next decision.

Proposed sequence; resolve interpretation or access gaps before relying on the next step.

Prepare the runtime boundary and fixtures

Use approved boundary claims, synthetic fixtures, runtime policies and host observations to identify the exact runtime and boundary claimed by runtime engineers and security test owners. Mark permitted resources and protected resources in a controlled fixture, including shared services where they are relevant. Define observable success, denial and incomplete setup before execution. The preparation output is a boundary map and fixture manifest that lets reviewers distinguish effective isolation from a test that never reached its target.

Exercise and inspect the boundary

Examine alternate interfaces to the same resource. A direct filesystem restriction can coexist with a helper API that reads the protected path. Record the enforcement component and resulting host state so the finding does not depend only on the agent’s report.

Choose containment or configuration changes

Translate the observations into an isolation test matrix recording allowed, blocked and inconclusive access. Locate each issue in the worker, shared service, policy rollout or cleanup path rather than attributing every symptom to the sandbox as a whole. Decide which configuration change, narrower resource exposure or specialist investigation is warranted. Retest the affected boundary and inspect residual state before treating the changed environment as equivalent to the intended design.

Indicative artefact

Make the isolation test matrix recording allowed, blocked usable by its owner

Isolation test matrix recording allowed, blocked

Illustrative working format

Annotated fieldIsolation test matrix recording allowed, blocked
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldIsolation test matrix recording allowed
Link supporting and contrary observations to inspectable evidence.
Annotated fieldBlocked
Name the unresolved condition, next action, and accountable owner.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is an isolation test matrix recording allowed, blocked and inconclusive access. Supporting material may include selected cases, configuration or process records, evidence references, a disagreement log and prioritised actions. Retain the case selection rationale and material disagreements alongside the result; otherwise the result may be mistaken for complete coverage.

Illustrative scenario

Examine host observation through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationAllowed fixture

    A worker reports denied access while an external marker has changed.

  2. Question to examineDenied fixture

    Compare worker denial logs with the external synthetic marker.

  3. Conditional next actionHost observation

    Keep the case unresolved until the conflicting observations are explained.

Fictional example. No executed test, customer engagement, or measured outcome is implied.

Consider a fictional situation: a test worker cannot open a protected directory directly but an exposed helper service can read it. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the helper service, test whether it checks the caller’s scope before reading. The remedy may belong in the helper or its exposure rules. Repeating the direct-file test would not address the alternate route.

Scope and next action

Keep the conclusion within the authorised runtime boundary

Confirm fit before the next commitment

Included boundaryAllowed fixture
This review is limited to the authorised runtime boundary.
PrerequisiteApproved boundary claims
The relevant owner must confirm access and the intended operating conditions.
Claim limitIsolation test matrix recording allowed, blocked
Untested surfaces remain outside the conclusion.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Testing is confined to explicitly authorised environments and non-destructive cases. A bounded assessment cannot establish that escape or cross-boundary access is impossible. Any engagement depends on an agreed scope, qualified team, authorised access and confirmed availability. Bring the affected workflow, its current configuration or process, the triggering change and the evidence already available. The immediate scope question is prompted by the situation in which a new isolation configuration or shared-host deployment is proposed; confirm which missing observation would change the owner’s next action.

Ways to engage

Related engagement scopes

AI Agent Runtime Security Review

Make every delegation explicit. Examine who the agent acts for, where it can execute and which tools it can reach when instructions alone are not enough.

Read about this offer

AI Agent Red Team

Challenge the boundaries that matter to your workflow. Test agreed attack scenarios against agent instructions, tools and data access.

Read about this offer

AI Agent Sandbox Assurance

Examine the boundary between agent execution and the systems around it, including files, networks, secrets and cleanup.

Read about this offer

Continue exploring

Related insights and resources

Agent security6 MIN READ

The permission boundary behind every agent action

An agent can only be evaluated in the context of what its tools allow. Examine identity, delegated authority and action boundaries before you put a workflow in motion.

Whitepaper5 MIN READ

Before your agent can act, define its authority

A working paper for the moment an AI system moves from advice to action. Map identity, permissions, approvals and recovery into an authority model your team can review and test.

A little more clarity

Questions to consider.

Start with the questions that shape a better decision.

How do you distinguish a blocked attempt from an untested boundary?

A blocked attempt has an observed denial at the intended boundary and no prohibited side effect under the tested conditions. An untested boundary lacks that evidence. Setup failures and inaccessible resources should remain inconclusive.

Which fixtures make isolation boundaries observable?

Start with approved boundary claims, synthetic fixtures, runtime policies and host observations. Record their revision, owner and relationship to the intended workflow. Missing context should be identified before interpreting outcomes; a sanitised fixture is useful only when its relevant differences from the operating case are understood.

How should alternate access routes be tested?

Exercise agreed cross-boundary cases using harmless markers and compare runtime and host evidence. Retain effective runtime configuration and observations from the relevant boundary. Distinguish an enforced denial from failed setup or an operation that never reached the resource. Use controlled markers and preserve residual-state evidence.

What should an isolation matrix distinguish?

The proposed output is an isolation test matrix recording allowed, blocked and inconclusive access. Include the selected conditions, supporting observations, unresolved differences and next decision. A reviewer should be able to follow each important conclusion back to its evidence and understand the limits without depending on an undocumented explanation from the author.

When is a blocked attempt inconclusive?

An apparent block is inconclusive if setup failed, the target was absent or the request never reached the intended control. Retain evidence of the attempted route and actual resource state.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from runtime engineers and security test owners may already be sufficient. In that case, capture the decision, unresolved limitations and the change that would require another review. Additional assessment should address a real gap.

What would make the findings inconclusive?

Missing approved boundary claims, synthetic fixtures, runtime policies and host observations can prevent a reliable interpretation, depending on the case. Record the specific missing observation and its implication. The owner can supply evidence, narrow the claim or defer the dependent decision; an incomplete case should not silently be counted as a pass.

Start with the decision you need to make.

Tell us about the agent workflow you want reviewed, and where you need greater clarity. Scope and availability are confirmed together.

Book a 30 minute readiness call Get the agent release checklist

Connected disciplines

Escape-resistance assessment

Assess evidence for resisting escape from a defined execution environment. The review connects runtime versions, privilege configuration, host interfaces and an authorised threat model to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.

Filesystem-access testing

Verify what files an agent execution environment can read or change. The review connects mount maps, path permissions, symlink rules and synthetic sensitive-file markers to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.

Network-egress control review

Define and validate where a sandbox may send network traffic. The review connects destination policies, DNS behaviour, proxy routes and connection logs to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.