Softlander Book a call
Agent sandbox assurance

Auditability assessment

Make sandbox activity reconstructable for operational review

A failed or disputed execution lacks enough evidence to explain events. The decision is how to make sandbox activity reconstructable for operational review. 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 security operations and platform observability leads. 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 evidenceEvent schemas

    Establish the basis for session identity.

  2. Decision boundaryEvent sequence

    Retain useful timestamps and action boundaries.

  3. Decision artefactAuditability assessment

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. Untested surfaces remain outside the conclusion.

Decision

Frame the decision around session identity

Questions and the evidence they need

Criterion / evidenceSession identity
Inspect event schemas for the relevant constraint or observation.
Criterion / evidenceEvent sequence
Inspect timestamp sources for the relevant constraint or observation.
Criterion / evidenceMissing observation
Inspect retention rules 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 make sandbox activity reconstructable for operational review. This is relevant to security operations and platform observability leads when a failed or disputed execution lacks enough evidence to explain events. 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 tool events are recorded but subprocess or artefact actions cannot be linked to the same session. 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

Audit evidence should reconstruct a session without guesswork

Relationships within runtime isolation

Source or conditionSession identity
Correlate work across runtime and exported artefacts.
Crossing or choiceEvent sequence
Retain useful timestamps and action boundaries.
Consequence or decisionMissing observation
Expose gaps that prevent a conclusion.
Compare effective controls with harmless test observations. Each relationship needs evidence in the actual scope.

What this specialty examines

Auditability should support a concrete reconstruction question. Identify the session, initiating authority, runtime version, important actions and artefacts needed to explain what happened. Excessive payload collection can make records harder to use while increasing handling obligations.

The review should reconstruct selected sessions from permitted evidence and identify missing or conflicting event chains. 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, detailed telemetry supports investigation while collection must avoid unnecessary sensitive payloads. 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 session identity

Illustrative working format

BasisEvent schemas
Retain the observed conditions and distinguish gaps from contrary evidence.
ContextTimestamp sources
Establish permitted access, provenance, and which task conditions it represents.
ObservationRetention rules
Confirm the applicable revision and who resolves disputed interpretation.
DependencyCorrelation identifiers
Identify provenance and the specific decision this material can inform.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with event schemas, timestamp sources, retention rules and correlation identifiers. 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 tool events are recorded but subprocess or artefact actions cannot be linked to the same session 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 session identity through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsEvent schemas

    Declare the permitted environment and resources.

  2. Examine the relationshipEvent sequence

    Apply the scoped check to missing observation.

  3. Retain the findingAuditability assessment

    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 event schemas, timestamp sources, retention rules and correlation identifiers to identify the exact runtime and boundary claimed by security operations and platform observability leads. 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

Reconstruct selected sessions using independently retained events. Inspect missing correlations, inconsistent clocks and records whose integrity or retention is unclear. The result should show which conclusions can be supported and which remain speculative because an event was never captured.

Choose containment or configuration changes

Translate the observations into an auditability assessment and proposed minimum event model. 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 auditability assessment usable by its owner

Auditability assessment

Illustrative working format

Annotated fieldAuditability assessment
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldMinimum event model
Link supporting and contrary observations to inspectable evidence.
Annotated fieldEvent sequence evidence
Link observations and counterevidence to the case, configuration, and conclusion limit.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is an auditability assessment and proposed minimum event model. 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 missing observation through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationSession identity

    A cancelled worker has logs but no event connecting them to its task.

  2. Question to examineEvent sequence

    Attempt to reconstruct task identity and cancellation from retained events.

  3. Conditional next actionMissing observation

    Name missing correlation evidence instead of guessing the session history.

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

Consider a fictional situation: an operator sees that a file appeared in an output bucket but cannot connect it to a worker or initiating task. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the unexplained output file, follow artefact creation back to the worker and task. If no correlation exists, propose the smallest event addition that closes that gap. Recording more conversation text may not answer the missing provenance question.

Scope and next action

Keep the conclusion within the authorised runtime boundary

Confirm fit before the next commitment

Included boundarySession identity
This review is limited to the authorised runtime boundary.
PrerequisiteEvent schemas
The relevant owner must confirm access and the intended operating conditions.
Claim limitAuditability assessment
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 failed or disputed execution lacks enough evidence to explain events; 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.

What must be logged to reconstruct a sandbox session?

Capture the identifiers, authority, runtime revision, significant actions and artefact links needed for the reconstruction question. Avoid indiscriminate payload collection. Missing correlation often matters more than the amount of text retained.

Which events allow a session to be reconstructed?

Start with event schemas, timestamp sources, retention rules and correlation identifiers. 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 missing correlation evidence be investigated?

Reconstruct selected sessions from permitted evidence and identify missing or conflicting event chains. 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 a minimum audit event model contain?

The proposed output is an auditability assessment and proposed minimum event model. 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 does additional logging add little value?

Additional logging adds little value when it repeats payloads without closing the missing identity, action or correlation gap. Define the reconstruction question and collect the events needed to answer it.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from security operations and platform observability leads 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 event schemas, timestamp sources, retention rules and correlation identifiers 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

Comparative sandbox benchmarking

Compare sandbox options against the same workload and control requirements. The review connects candidate configurations, common workload fixtures, isolation criteria and cost inputs to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.

Secure computer-use environment design

Define a controlled environment for agents that operate a computer interface. The review connects application inventory, account permissions, clipboard rules and download paths to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.

Browser sandbox evaluation

Verify the browser state and access boundaries used by an agent. The review connects browser profile settings, cookie stores, extension inventory and navigation policies to a bounded review of execution boundaries, giving the runtime owner a clearer basis for the next action.