Axis B and the modifier

Is privilege escalation a defect, or is it the function?

Level says how much can be fixed at design time. Mandate says whether run-time detection is available at all. Reach says what it costs when both fail.

Mandate

Three mandates, one question

MandateThe agent is authorized toEscalation isBehavioral detection
ObservationalLearn and report. Any state change is out of mandate.A defect, and unambiguousStrongest — any write is an alarm
OperationalChange specified state within a defined functionA defectStrong — escalation-shaped activity is an alarm
AdversarialDefeat controls, in order to demonstrate that they can be defeatedThe functionUnavailable

↔ scroll table

The load-bearing distinction in the entire framework

Adversarial agents are expected to escalate. Privilege escalation, credential harvesting, lateral movement, control evasion, and persistence are the deliverable, not the failure. The agent escalates constantly and correctly, so anomaly detection cannot separate authorized escalation from a breakout. Containment must be structural: enforced by network position and identity scope regardless of what the agent does, because there is no behavioral signature to key on.

Structural containment is more expensive than detection. Adversarial mandate is therefore an expensive mandate, and should be granted deliberately and narrowly.

Not a scale

Operational and adversarial are incomparable

Observational is contained by operational. But a penetration testing agent is authorized to harvest credentials and move laterally, and typically not to make production business-state writes. An operational deployment agent is the reverse. Neither is a superset of the other.

Treat mandate as a partial order with observational at the bottom and two independent branches above it. A total ordering would license an adversarial parent to mint an operational child and silently drop it out of structural containment.

Independent of level

The pairings are free

An L2 scripted vulnerability scan is adversarial at L2. An L5 orchestrator producing market research is observational at L5.

Do not assume offensive means autonomous, or that autonomous means offensive.

A trap

Response agents

SOC containment, auto-remediation, and incident response automation carry an operational mandate: escalation is still a defect. But their authorized actions (isolate a host, disable an account, kill sessions, block at the perimeter) have adversarial-grade blast radius, and they hold credentials with adversarial-grade breadth in order to perform them.

Classify them operational. Expect their measured reach to come back R2 or R3. Do not assign R3 by fiat as a rigor dial; measure it, and it will usually be R3 anyway.

Modifier · Reach

What it costs when containment fails

Reach is a property of what the agent can touch, not what it intends to touch. It is measured by network and identity position, not by the prompt.

R0

Isolated

Synthetic or copied data, ephemeral resources, no route to production, systems of record, or third parties.

R1

Internal non-production

Real internal systems, no production data, no customer-visible effect.

R2

Production, internal

Production systems and data. Consequences confined to the organization.

R3

External

Third-party, customer-facing, regulated, shared-tenancy, safety-relevant, or partner-connected. Includes anything where a mistake creates a notification obligation.

The practical test

An agent on a developer workstation with an active VPN session has R2 or R3 reach regardless of its assignment, because reach is measured by the network and identity position, not the prompt. This is the test that most cleanly separates asserted containment from real containment.

Interactive

Build a profile

Every agent gets one: Level / Mandate / Reach. Control rigor is a function of all three. Pick a combination to see the posture CUSTODY assigns it.

L3 / Operational / R2

This is a reading aid, not the control matrix. The specification's annex carries the full matrix.

Governance

Cells to govern explicitly

ProfilePosture
L1–L2 / Observational or Operational / R0–R1Low ceremony. Do not over-govern this. It is most of the fleet and the controls should be cheap.
L3–L4 / Operational / R2The volume case. Most agents, most incidents, most of the exposure. Full pillar coverage at maturity 2 is the target.
Any / Adversarial / R3Per-target legal authorization, no exceptions. Structural containment only.
L5–L6 / Adversarial / anyFormal program with named executive owner, standing legal authorization, and continuous supervision.
L6 / Adversarial / R2 or R3Prohibited by default. Nothing is fixed at design time and no behavioral signal is available. Requires a documented exception at the risk-owner level, or do not run it.
L4 and above / any / R3Synchronous human approval for every irreversible action.

↔ scroll table

Authority ceiling

No agent's granted authority may exceed the authority of the human who authorized it. This is violated constantly and quietly: agents receive service accounts more powerful than any individual on the owning team, because the account was scoped to the tool rather than to the authorizer.

Contact & consulting

Questions, corrections, or help applying this?

The author offers consulting and training on threat modeling and risk assessing AI applications and agents, agentic containment architecture, and CUSTODY adoption. Feedback and disagreement are equally welcome, and cost nothing.

custody-framework@malwarejake.com