Softlander Book a call
Agent identity, authorisation, and delegation

Cross-tenant identity isolation

Verify that agent identity cannot cross tenant boundaries

One agent platform serves several customer organisations. The decision is how to verify that agent identity cannot cross tenant boundaries. 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 multi-tenant platform owners and security engineers. 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 identity and delegated authority relationship

  1. Starting evidenceTenant-principal mappings

    Establish the basis for tenant principal.

  2. Decision boundaryCached credential

    Prevent authority reuse across tenant contexts.

  3. Decision artefactTenant identity isolation matrix

    Retain the scoped finding and its unresolved dependencies.

Conceptual model. Technical findings do not settle a disputed mandate.

Decision

Frame the decision around tenant principal

Questions and the evidence they need

Criterion / evidenceTenant principal
Inspect tenant-principal mappings for the relevant constraint or observation.
Criterion / evidenceCached credential
Inspect token claims for the relevant constraint or observation.
Criterion / evidenceResource lookup
Inspect resource partitions 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 that agent identity cannot cross tenant boundaries. This is relevant to multi-tenant platform owners and security engineers when one agent platform serves several customer organisations. 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 cached credential or missing tenant condition allows one customer’s agent to access another’s records. 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

Tenant isolation must hold through caches and lookups

Relationships within identity and delegated authority

Source or conditionTenant principal
Bind the request to its authorised partition.
Crossing or choiceCached credential
Prevent authority reuse across tenant contexts.
Consequence or decisionResource lookup
Check the final tenant and object together.
Follow the check to the accepting resource. Each relationship needs evidence in the actual scope.

What this specialty examines

Tenant identity isolation needs consistent tenant binding through issuance, caching and resource access. Agent names may repeat across customers, so identifiers and cache keys should preserve the tenant boundary. Include administrative and artifact-access paths as well as ordinary tool calls.

The review should run paired tenant cases across issuance, caching, authorisation and resource lookup paths. 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, shared infrastructure improves operational efficiency while isolation requires tenant context at every decision. 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 tenant principal

Illustrative working format

BasisTenant-principal mappings
Match this description to the deployed or proposed boundary being examined.
ContextToken claims
Use nonsecret metadata to trace issuance, acceptance, and withdrawal responsibility.
ObservationResource partitions
Establish permitted access, provenance, and which task conditions it represents.
DependencySynthetic tenant fixtures
Keep expected behaviour and the limits of the constructed example explicit.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with tenant-principal mappings, token claims, resource partitions and synthetic tenant fixtures. 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 identity control owner, agreed expectations for a representative subject-action-resource case, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which a cached credential or missing tenant condition allows one customer’s agent to access another’s records 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 tenant principal through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsTenant-principal mappings

    Locate the source of the claimed authority.

  2. Examine the relationshipCached credential

    Apply the scoped check to resource lookup.

  3. Retain the findingTenant identity isolation matrix

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

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

Map principals, resources and authority

Reconcile tenant-principal mappings, token claims, resource partitions and synthetic tenant fixtures with the workflow described by multi-tenant platform owners and security engineers. Identify the initiating actor, executing workload, target resource and component that grants access. Prepare paired cases that differ in one material authority condition, such as assignment, tenant, expiry or approval. The preparation output is an action map showing which permission is expected at each boundary and which records can verify it.

Exercise and review the authority path

Test paired tenants with deliberately similar synthetic identifiers. Inspect whether credentials, sessions or permissions are reused incorrectly. An authorisation denial at one endpoint does not cover another endpoint that resolves the same resource without tenant context.

Select the identity control change

Consolidate the checked paths into a tenant identity isolation matrix with boundary-specific findings. Distinguish an identity-verification problem from an excessive permission, lost delegation context or delayed withdrawal. Assign the proposed change to the component that controls the affected action. Before recommending wider use, identify the allowed case and denied counterpart that would demonstrate the revised boundary without breaking legitimate work.

Indicative artefact

Make the tenant identity isolation matrix usable by its owner

Tenant identity isolation matrix

Illustrative working format

Annotated fieldTenant identity isolation matrix
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldBoundary-specific findings
Link observations and counterevidence to the case, configuration, and conclusion limit.
Annotated fieldCached credential 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 a tenant identity isolation matrix with boundary-specific findings. 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 resource lookup through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationTenant principal

    Two synthetic tenants issue similar requests through one shared worker.

  2. Question to examineCached credential

    Reuse the worker across paired tenant fixtures.

  3. Conditional next actionResource lookup

    Treat cross-tenant cache or lookup authority as an unresolved isolation finding.

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

Consider a fictional situation: two synthetic customers use similarly named agents and a credential cache keys only on agent name. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the name-keyed cache, alternate requests from two test tenants and compare the accepted principal and resource scope. The failure may sit in credential reuse rather than the model. The remediation should target that shared-state boundary.

Scope and next action

Keep the conclusion within named authority paths

Confirm fit before the next commitment

Included boundaryTenant principal
This review is limited to named authority paths.
PrerequisiteTenant-principal mappings
The relevant owner must confirm access and the intended operating conditions.
Claim limitTenant identity isolation matrix
Technical findings do not settle a disputed mandate.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Identity design and technical testing do not establish a legal mandate or resolve a disputed business authorisation. Qualified IAM review is needed for material control conclusions. 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 one agent platform serves several customer organisations; confirm which missing observation would change the owner’s next action.

Ways to engage

Related engagement scopes

Agent Release Readiness Review

The Agent Release Readiness Review is a fixed-scope, three-week independent test of one AI agent workflow that shows a release board what the agent does, what it is allowed to do and what happens when it is wrong, and ends in a signed recommendation.

3 weeksRead about this offer

AI Agent Authorisation Review

Make delegated authority inspectable. Trace who an agent acts for, what it can access and how that access can be withdrawn.

Read about this offer

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

Continue exploring

Related insights and resources

Whitepaper15 MIN READ

Designing agent authority boundaries

Turn agent permissions into an enforceable action contract. Separate a model's suggestion from a resource owner's authorisation, test the boundary, and make delegation and revocation reviewable.

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.

Is a tenant identifier in the prompt sufficient isolation?

No. Tenant context must be bound to identity, authorisation and resource lookup where actions occur. A prompt instruction does not establish isolation in credential caches, tool services or artefact stores.

Which mappings bind identities to tenants?

Start with tenant-principal mappings, token claims, resource partitions and synthetic tenant fixtures. 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 credential caches be tested across tenants?

Run paired tenant cases across issuance, caching, authorisation and resource lookup paths. Observe the authenticated principal, mandate and resource decision separately. Include a permitted action and a denied counterpart so the review can establish whether authority is narrow enough without making legitimate work impossible.

What should a tenant identity matrix show?

The proposed output is a tenant identity isolation matrix with boundary-specific findings. 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 must tenant context be checked again?

Check tenant context whenever credentials, requests or resources cross a boundary that can change or lose it, including caches and gateways. Earlier validation does not automatically cover a later lookup.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from multi-tenant platform owners and security engineers 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 tenant-principal mappings, token claims, resource partitions and synthetic tenant fixtures 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

Agent attribution and non-repudiation

Make consequential agent actions attributable to an accountable chain. The review connects event schemas, timestamps, identity evidence, delegation records and integrity controls to a bounded review of identity and authority, giving the identity control owner a clearer basis for the next action.

Authorisation policy testing

Verify authorisation policy decisions against intended rules. The review connects policy versions, subject-resource fixtures, action catalogues and expected decision tables to a bounded review of identity and authority, giving the identity control owner a clearer basis for the next action.

Consent and mandate management

Manage mandates as records that can change and expire. The review connects mandate versions, consent interactions, withdrawal events and execution queues to a bounded review of identity and authority, giving the identity control owner a clearer basis for the next action.