Softlander Book a call
Agent security and cybersecurity

Agent supply-chain security

Review the chain of components that supplies an agent deployment

New tools, plugins, prompts or packages enter the release process. The decision is how to review the chain of components that supplies an agent deployment. 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 software supply-chain owners and agent platform 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 agent security relationship

  1. Starting evidenceDependency inventories

    Establish the basis for source provenance.

  2. Decision boundaryInstallation path

    Identify who can approve and alter dependencies.

  3. Decision artefactAgent supply-chain map

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. A bounded challenge cannot establish exhaustive protection.

Decision

Frame the decision around source provenance

Questions and the evidence they need

Criterion / evidenceSource provenance
Inspect dependency inventories for the relevant constraint or observation.
Criterion / evidenceInstallation path
Inspect provenance records for the relevant constraint or observation.
Criterion / evidenceRuntime privilege
Inspect update paths 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 review the chain of components that supplies an agent deployment. This is relevant to software supply-chain owners and agent platform leads when new tools, plugins, prompts or packages enter the release process. 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 trusted workflow inherits an unreviewed tool update with broader behaviour. 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

Dependencies carry authority into the running agent

Relationships within agent security

Source or conditionSource provenance
Trace selected packages and configuration inputs.
Crossing or choiceInstallation path
Identify who can approve and alter dependencies.
Consequence or decisionRuntime privilege
Inspect the authority the installed component receives.
Observe the control and resulting business effect. Each relationship needs evidence in the actual scope.

What this specialty examines

Agent supply-chain review includes components that influence behaviour and authority, not only executable packages. Prompts, tool descriptions, plugins, configuration and remote services may change what the agent attempts. Record provenance and update responsibility for each relevant dependency.

The review should trace selected dependencies from source and build through installation, configuration and runtime authority. 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, rapid ecosystem integration adds functionality while updates must remain attributable and reviewable. 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 source provenance

Illustrative working format

BasisDependency inventories
Identify provenance and the specific decision this material can inform.
ContextProvenance records
Connect the deployed artefact to its inputs, approval, and verifiable revision.
ObservationUpdate paths
Name the custodian and the conditions requiring a refreshed version.
DependencyApproval policies
Connect the accepted action parameters to grant, amendment, expiry, and withdrawal.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with dependency inventories, provenance records, update paths and approval policies. 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 security decision owner, agreed expectations for a representative threat scenario, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which a trusted workflow inherits an unreviewed tool update with broader behaviour 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 source provenance through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsDependency inventories

    Define the hypothetical attacker’s starting influence.

  2. Examine the relationshipInstallation path

    Apply the scoped check to runtime privilege.

  3. Retain the findingAgent supply-chain map

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

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

Define the controlled threat scenario

Review dependency inventories, provenance records, update paths and approval policies with software supply-chain owners and agent platform leads. State what the hypothetical attacker controls, the protected action and the systems included in the authorised exercise. Prepare synthetic records and harmless markers where appropriate, with stopping conditions for unexpected effects. The preparation output is a scenario brief that distinguishes an influence attempt from a prohibited action actually reaching a business resource.

Challenge the path and review effects

Trace a selected update through review, deployment and runtime discovery. Determine whether new actions or permissions trigger validation. An inventory supports the process but does not establish that updates are reviewed or constrained.

Select a control response and retest

Build an agent supply-chain map with change-control and provenance gaps from the reviewed observations. Separate agent behaviour, application enforcement and the resulting resource state so the recommended change reaches the responsible layer. Choose a bounded retest that reproduces the original condition and checks legitimate behaviour after remediation. If the required investigation exceeds the agreed technique or expertise, retain the unresolved path and identify the qualified review needed.

Indicative artefact

Make the agent supply-chain map usable by its owner

Agent supply-chain map

Illustrative working format

Annotated fieldAgent supply-chain map
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldChange-control
Link supporting and contrary observations to inspectable evidence.
Annotated fieldProvenance gaps
Name the missing evidence, responsible owner, and condition for revisiting the decision.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is an agent supply-chain map with change-control and provenance gaps. 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 runtime privilege through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationSource provenance

    A newly installed extension receives the same tool access as the core agent.

  2. Question to examineInstallation path

    Trace the extension from reviewed source into runtime permissions.

  3. Conditional next actionRuntime privilege

    Narrow or justify inherited authority before relying on the dependency.

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

Consider a fictional situation: a connector update adds a new write operation that the agent discovers automatically after deployment. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the connector’s added write operation, inspect whether automatic discovery exposes it immediately. The owner may choose explicit tool eligibility or a release review before new capabilities become available. The useful control concerns behaviour entering the deployment.

Scope and next action

Keep the conclusion within the agreed threat scenario

Confirm fit before the next commitment

Included boundarySource provenance
This review is limited to the agreed threat scenario.
PrerequisiteDependency inventories
The relevant owner must confirm access and the intended operating conditions.
Claim limitAgent supply-chain map
A bounded challenge cannot establish exhaustive protection.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Authorised scenario testing is not a claim of exhaustive penetration testing or guaranteed protection. Intrusive security work requires qualified specialists and a separately agreed scope. 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 new tools, plugins, prompts or packages enter the release process; 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 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

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.

Agent security6 MIN READ

Running an AI-agent incident tabletop exercise

A useful tabletop follows one plausible agent failure through detection, containment, evidence, business recovery and accountable return to service.

A little more clarity

Questions to consider.

Start with the questions that shape a better decision.

Should prompts and tool descriptions be included in the supply chain?

Yes, when they influence behaviour or authority. Track provenance, review and updates for prompts, descriptions and configuration as well as executable dependencies. A newly discovered tool can change effective capability without an application-code change.

Which dependencies influence agent behaviour and authority?

Start with dependency inventories, provenance records, update paths and approval policies. 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 new tool capabilities enter release review?

Trace selected dependencies from source and build through installation, configuration and runtime authority. State the hypothetical attacker's control and inspect attempted actions, tool enforcement and actual effects separately. A refusal, a blocked call and a successful prohibited action are different results. Preserve unsuccessful challenges as well as adverse findings.

What belongs in an agent supply-chain map?

The proposed output is an agent supply-chain map with change-control and provenance gaps. 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 should automatic discovery require approval?

Require review when newly discovered tools add authority, data access or behaviour beyond the evaluated scope. Automatic discovery should not silently promote a new function into production eligibility.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from software supply-chain owners and agent platform 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 dependency inventories, provenance records, update paths and approval policies 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

Model and dependency security

Assess security-relevant changes in model and software dependencies. The review connects version manifests, dependency advisories, integration tests and provider configuration to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.

MCP server security review

Inspect the authority exposed by a particular MCP server integration. The review connects server version, exposed tool definitions, authentication settings and resource permissions to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.

Adversarial agent testing

Challenge a defined agent workflow using authorised adversarial scenarios. The review connects rules of engagement, threat hypotheses, synthetic data and stop conditions to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.