TowerGuardian Consulting

Austin TX United States of America morganLR@proton.me

WIMSE Working Group Autonomous software agents increasingly act on behalf of human principals by invoking tools, services, and other agents, frequently across organizational boundaries. Existing workload and token-based authorization mechanisms were designed for a single trust domain and a small number of delegation hops. They do not adequately express, constrain, or verify authority that is delegated recursively among agents and that crosses the boundary between independently administered organizations. This document describes the problem of cross-organizational agent delegation, identifies the gaps in current mechanisms, and enumerates requirements that any solution within the scope of the Workload Identity in Multi-System Environments (WIMSE) working group should satisfy. It does not specify a solution. Note to the RFC Editor and Working Group Informative references to agent-to-agent and tool-invocation protocols, to workload identity credential formats, and to status-list-based revocation will be added in a subsequent revision; they are omitted here to keep the problem statement mechanism-neutral.

Introduction Software agents that incorporate large language models or other autonomous decision logic are increasingly deployed to perform tasks on behalf of human principals. A common pattern is for an orchestrating agent to decompose a task and delegate sub-tasks to specialized sub-agents, each of which may invoke tools or further sub-agents. These tool and agent invocations are frequently mediated by protocols such as the Model Context Protocol and agent-to-agent messaging, and they increasingly cross the boundary between independently administered organizations: an agent operated by one organization invokes a tool or agent operated by another. The Workload Identity in Multi-System Environments (WIMSE) working group is chartered to address identity for workloads that operate across multiple systems and trust domains. Autonomous agents are a workload class whose delegation behavior stresses existing identity and authorization mechanisms in ways that this document seeks to make explicit. The authorization question raised at each agent action is not a single question but a composition of several: which workload is acting; what authority it holds; from whom that authority was delegated and through how many intermediaries; on behalf of which human principal it ultimately acts; and whether a relying party in a different organization can answer all of the foregoing without contacting the originating organization at the moment of the call. Existing mechanisms answer some of these questions within a single trust domain. This document argues that none answers all of them across organizational boundaries, and that the gap is significant enough to warrant work within the WIMSE working group. This document is a problem statement and requirements document. It deliberately does not propose or endorse any specific mechanism, credential format, or token construction.

Terminology The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here. This document uses the following terms.

Agent:

A software workload that performs tasks autonomously, potentially invoking tools, services, or other agents. An agent is a workload in the sense of the WIMSE architecture.

Tool:

A function, API, or service that an agent may invoke to take an action or retrieve information.

Principal:

The human (or other ultimately-accountable entity) on whose behalf an agent acts.

Delegation:

The act of conferring a subset of one entity's authority upon another entity.

Delegation chain:

An ordered sequence of delegations originating at a principal or an originating agent and proceeding through zero or more intermediary agents to the agent that performs an action.

Attenuation:

The narrowing of authority at a delegation step, such that the authority conferred is no greater than the authority held.

Originating organization:

The organization whose trust anchor issued the identity or authority at the root of a delegation chain.

Relying party:

The entity that receives an agent's request and must decide whether to honor it; in cross-organizational cases the relying party belongs to a different organization than the originating organization.

Problem Statement This section describes seven facets of the cross-organizational agent delegation problem. They are interrelated; a solution that addresses only a subset leaves exploitable or operationally untenable gaps.

Recursive Delegation Among Agents An orchestrating agent commonly delegates a narrowed slice of its authority to a sub-agent, which may delegate a further narrowed slice to another sub-agent, and so on. Each step SHOULD only be able to narrow authority, never to widen it. Existing bearer-token mechanisms typically express a fixed set of scopes granted at issue time and provide no native, verifiable model in which authority is recursively attenuated across multiple hops while remaining verifiable end-to-end. Where multi-hop delegation is expressed at all, the constraint that a later hop cannot exceed an earlier hop is frequently enforced only by the issuing party's policy rather than being verifiable by an arbitrary relying party from the conveyed authority alone.

Crossing the Organizational Boundary When an agent in organization A invokes a tool or agent in organization B, organization B's relying party must evaluate authority that was issued under organization A's trust anchor. In the general case there is no pre-existing bilateral agreement between A and B specific to this interaction. Mechanisms that assume a shared identity provider, a shared policy store, or a pre-provisioned federation relationship do not generalize to the open, many-to-many case in which agents from numerous organizations interact without having been federated in advance.

Verification Without a Runtime Callback Agent tool invocations can occur at high frequency and with stringent latency budgets. Requiring the relying party to call back to the originating organization's infrastructure at the moment of each invocation -- to introspect a token, resolve a session, or confirm authority -- introduces latency, a runtime availability dependency on a third party, and a privacy exposure (the originating organization learns each time and where its agent's authority is exercised). A relying party SHOULD be able to reach a correct authorization decision from the conveyed authority, locally cached trust material, and locally cached revocation state, without a synchronous call to the originating organization on the critical path.

Binding the On-Behalf-Of Principal An agent typically acts on behalf of a human principal. Two distinct authorization questions arise at each action and are independent of one another: whether the agent is permitted to perform the class of action at all, and whether the human principal on whose behalf it acts is entitled to the specific resource the action targets. An authorization model that captures only the first question permits a "confused deputy", in which an agent authorized for a class of action is induced to apply it to a resource belonging to some principal other than the one it acts for. A model that resolves the second question by having the agent inherit the principal's full set of permissions produces an over-privileged deputy, in which compromise of the agent escalates to the full authority of the human. Across a multi-hop, cross-organizational delegation chain, the identity of the on-behalf-of principal must be conveyed and constrained in a manner that a remote relying party can evaluate, and that intermediary agents cannot silently alter.

Revocation and Freshness Across Domains Authority conferred on an agent must be revocable, and revocation must reach relying parties in other organizations. Because the verification path SHOULD avoid a synchronous callback (), revocation state must be conveyable to relying parties out of band and checkable locally, while remaining authentic (a revoked authority cannot be made to appear valid) and bounded in staleness (a relying party can reason about, and fail safe on, the age of its revocation information). Reconciling offline verification with timely cross-domain revocation is a central tension.

Composable Cross-Domain Audit After the fact -- for incident response, compliance, or dispute resolution -- it must be possible to reconstruct who authorized a given action, through which intermediaries, and on behalf of which principal, even though the relevant events were recorded by different organizations. No single organization observes the entire delegation chain in a cross-organizational interaction. The records held by each participant must be composable into a coherent end-to-end account, and each participant's record must be resistant to undetectable alteration.

Execution-Time Human Authorization Some classes of action are consequential enough that an organization's policy requires a human decision at the moment of execution, regardless of what standing authority the acting agent otherwise holds: releasing a payment above a threshold, deleting or exporting a data set, modifying a safety boundary, or triggering a physical action in the world. Within a single trust domain this is commonly implemented as step-up authentication or an approval workflow anchored at a shared authorization server. Across a multi-hop, cross-organizational delegation chain, three properties become difficult to obtain at once: that the requirement itself survives delegation, so that no intermediary can shed it; that the human's decision is bound to the specific action being taken, rather than to a session or to a class of actions; and that the relying party which enforces the requirement, possibly offline and in another organization, can verify the decision's evidence at the moment of enforcement. Public discussion has converged on this pattern from several directions, including grant-time consent records and challenge-based transaction-authorization proposals in the OAuth community, "user-mediated escalation" in agent-authorization use-case work, and "physical-world action authorization" requirements for embodied agents. These proposals differ in mechanism; they share the underlying need this facet states.

Gaps in Existing Mechanisms The following observations motivate work in this area. They are stated at the level of mechanism classes rather than specific documents, to avoid mischaracterizing any individual specification. Session-oriented authorization frameworks excel at granting a client scoped access within a trust domain but generally assume a small, fixed delegation depth and a relying party that can reach the authorization server. Their extension to recursive agent delegation across organizations is not native. Token exchange mechanisms can express that one party acts on behalf of or is impersonating another, but they do not provide a verifiable model of recursive attenuation across an arbitrary number of hops, nor a guarantee, checkable by an arbitrary relying party, that the on-behalf-of principal is invariant along the chain. Workload identity mechanisms establish strong identity for workloads and increasingly span multiple systems, which is precisely the WIMSE remit; the open question this document raises is how delegated, attenuated, principal-bound authority is conveyed and verified when the workloads in question are agents that delegate to one another across organizational boundaries. Mechanisms that rely on a shared policy decision point evaluate rich policy at runtime but reintroduce a runtime dependency and a single administrative domain, which is the dependency seeks to avoid in the cross-organizational case. The cumulative gap is that no widely deployed mechanism today lets a relying party in one organization verify, locally and without a callback, a recursively attenuated, principal-bound delegation chain that originated in another organization, while supporting cross-domain revocation and composable audit.

Requirements Any solution within scope SHOULD satisfy the following requirements. They are derived directly from the problem facets in and are stated independently of any particular credential format or cryptographic construction.

R1 (Recursive attenuation):

The mechanism MUST allow authority to be delegated through multiple hops such that each hop conveys a subset of the authority of the preceding hop, and MUST allow a relying party to verify, from the conveyed authority alone, that no hop exceeds its predecessor.

R2 (Cross-organizational verification):

A relying party in one organization MUST be able to verify authority that originated under another organization's trust anchor without a pre-existing bilateral agreement specific to the interaction.

R3 (No runtime callback):

The mechanism MUST permit a relying party to reach an authorization decision without a synchronous call to the originating organization on the critical path, using conveyed authority and locally cached trust and revocation material.

R4 (Proof of possession):

The mechanism MUST allow a relying party to confirm that the presenting party controls the key to which the conveyed authority is bound, so that a captured or relayed credential is not usable by another party.

R5 (Principal binding and invariance):

The mechanism MUST be able to convey the on-behalf-of principal along the delegation chain and MUST allow a relying party to verify that intermediary agents have not altered the identity of that principal.

R6 (Dual-axis authorization):

The mechanism MUST support authorization decisions that depend both on the agent's conveyed authority and on the entitlements of the bound principal, such that an action is permitted only when both admit it.

R7 (Authentic, bounded-staleness revocation):

The mechanism MUST support revocation whose authenticity is verifiable offline and whose staleness is bounded, so that a relying party can fail safe when its revocation information is older than a configured bound.

R8 (Tamper-evident, composable audit):

The mechanism SHOULD enable each participant to record its portion of a delegation in a manner resistant to undetectable alteration, and SHOULD enable those records to be composed into an end-to-end account of an action's provenance.

R9 (Format and transport agnosticism):

The requirements above SHOULD be expressible over the identity and messaging mechanisms already in use for agents and workloads, rather than presupposing a single new transport.

R10 (Execution-time human authorization):

It MUST be possible to designate classes of actions as requiring, at execution time, evidence of an authorization decision made by an accountable human approver distinct from the executing agent. The designation MUST be carried within the delegated authority itself, and derivation MUST be able to tighten but never remove it. The evidence MUST be bound to the specific action, including its arguments, its target resource, and the on-behalf-of principal; MUST be verifiable by the relying party at the moment of enforcement from conveyed or locally cached material, without a synchronous dependency on the originating organization or on an approval-orchestration service; and MUST be relied upon at most once. A relying party that does not recognize a designation MUST treat the designated action as unauthorized. This requirement deliberately does not select among challenge-based, evidence-carrying, or other approaches to satisfying it.

Non-Goals This document does not address the correctness of an agent's internal reasoning. Mechanisms that constrain delegated authority bound what an agent is permitted to do; they do not prevent an agent from misusing authority it legitimately holds, for example as a result of prompt injection. Defense against such misuse is complementary and out of scope here. This document does not address confidentiality of agent payloads beyond what is implied by ordinary transport security, nor does it address denial-of-service resistance except where a design choice in a future solution would create an asymmetric amplification. This document does not select among credential formats, signature schemes, or policy languages, and does not endorse any specific product or implementation.

Security Considerations This document is a problem statement; its security considerations are the security properties that a future solution must provide, which are stated as requirements in (notably R1, R4, R5, R7, and R10) and as problem facets in . Several tensions deserve explicit attention by any solution. The avoidance of a runtime callback (R3) is in tension with timely revocation (R7); a solution must make the staleness of offline revocation state explicit and must fail safe. The reliance on a relying party's local trust material for cross-organizational verification (R2) makes the integrity of that trust material, and of the means by which it is resolved and cached, a high-value target; a solution must ensure that the trust root used to verify a remote organization's authority cannot be silently substituted. The binding of an on-behalf-of principal (R5) is only meaningful if the binding is integrity-protected end to end, including against modification by the intermediary agents that form the delegation chain. Requirement R10 introduces considerations of its own. An execution-time approval is only as meaningful as the fidelity of what the approver was shown: a solution must ensure that the action presented for approval and the action bound into the evidence are the same action, and that no party, including the executing agent itself, can alter one relative to the other. The at-most-once reliance property becomes a distributed-consumption problem when a relying party is replicated, and its failure mode must be refusal rather than double reliance. Fail-closed treatment of unrecognized designations is what preserves the requirement across verifiers of differing capability; a fail-open interpretation would convert the newest designation into the weakest link. Finally, R3 and R10 compose deliberately: the human's decision may be obtained through any interactive means, but verification of its evidence at the point of enforcement inherits R3's offline discipline. Where authority is long-lived, or where audit records must remain verifiable over a multi-year retention period, the long-term resistance of the chosen cryptographic mechanisms, including under a future quantum-capable adversary, is a consideration for any solution; data and signatures recorded today may need to remain unforgeable for the lifetime of the audit obligation.

IANA Considerations This document has no IANA actions.

References Normative References Informative References Work in Progress

Changes Since -00

• Added , describing the execution-time human-authorization facet of the problem.
• Added requirement R10 (execution-time human authorization) to , stated mechanism-independently.
• Added security considerations for R10 to , and included R10 in the list of security-relevant requirements.
• Completed the informative reference (authors, exact title, draft name, version, and URL).
• Updated the facet count in and the Table of Contents; corrected an expiry-date inconsistency in the -00 boilerplate; editorial fixes.