| Internet-Draft | Agent Principal Binding | July 2026 |
| Bu | Expires 5 January 2027 | [Page] |
Agent communication protocols often carry claims about user authority, agent instance identity, tool or external-resource identity, delegation state, session continuity, and action evidence. These claims have different verifiers, freshness requirements, failure modes, and security consequences. If they are collapsed into a single token, identity label, session identifier, or audit record, protocol text can accidentally imply more authority or accountability than the receiver can actually verify.¶
This document defines a verifier-facing model for separating those claims. It provides a reusable matrix format that protocol authors can use to state, for each security-relevant claim, which field carries it, which party verifies it, what binding or freshness rule applies, and what failure behavior is required when the claim is absent, stale, inconsistent, or not verifiable. The document is protocol-neutral. It is intended to help compare candidate agent communication drafts and to provide security-considerations and requirements text for agent session and delegation binding.¶
This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.¶
Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at https://datatracker.ietf.org/drafts/current/.¶
Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."¶
This Internet-Draft will expire on 5 January 2027.¶
Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved.¶
This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must include Revised BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Revised BSD License.¶
Agent protocols are being proposed for long-lived communication among agents, tools, gateways, services, and human or organizational principals. These protocols need to express several different kinds of security meaning:¶
These are not the same claim. A valid organizational identifier does not by itself prove a live agent instance. A session identifier does not by itself prove delegated authority. A transparency receipt does not by itself prove that the action was authorized. A tool invocation record does not by itself prove that the tool was within delegated scope.¶
The purpose of this document is to make these boundaries reviewable. It does not define a new agent protocol, token format, audit log, transparency service, or authorization system. Instead, it defines a claim-to-verifier discipline that other drafts can map to.¶
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 [RFC2119] [RFC8174] when, and only when, they appear in all capitals, as shown here.¶
This document is currently intended as Informational guidance. Requirement language is used to make security expectations reviewable by protocol authors; it does not by itself define a wire protocol.¶
An automated software component that initiates, receives, mediates, or performs actions on behalf of a human, organization, account, workload, or policy authority.¶
An entity whose authority, identity, state, or responsibility is relevant to a security decision.¶
A security-relevant statement that a protocol participant, credential, token, receipt, attestation, record, or external system asserts or carries.¶
The protocol field, credential, record, header, receipt, attestation, envelope, or external reference that carries a claim.¶
The party that evaluates a claim for a particular security decision.¶
The relationship between a claim and the specific state to which it applies, such as a session transcript, task digest, delegation chain, subject identifier, tool invocation, or evidence record.¶
The replay, expiration, revocation, sequence, rotation, challenge, nonce, or recency rule used to determine whether a claim can still be relied upon.¶
The required behavior when a claim is missing, stale, inconsistent, not verifiable, or out of scope for the decision being made.¶
A descriptive label for where a verifier decision is made or where a claim is carried. The label can use ordinary protocol-layer terminology, such as application, transport, or network, or an agent-native architectural taxonomy, but the vocabulary needs to be defined by the draft that uses it.¶
A stable reference to a public test vector, example, test case, implementation note, interop record, issue, pull request, or other reviewable artifact that supports a mapping row.¶
Agent communication drafts can become difficult to review when a single architectural label is used to imply several security properties. Common examples include:¶
These ambiguities are not merely editorial. They affect interoperability and security review. Two implementations can agree on a field name while making different decisions about who verifies the field, what state the field is bound to, and what happens when the field cannot be validated.¶
This document addresses that problem by requiring each security-relevant claim to be mapped to a carrier, verifier, verification rule, binding, freshness rule, layer, and failure behavior.¶
This document does not:¶
The following principals commonly appear in agent communication designs.¶
The person, organization, role, legal entity, account, or policy authority on whose behalf the agent acts.¶
The concrete live agent, runtime, workload, or execution environment that participates in the protocol exchange.¶
The party that supplies, hosts, or controls an agent implementation or runtime environment.¶
A tool, API, service, file, database, payment endpoint, browser, physical device, or other resource invoked by an agent.¶
An intermediary that translates, routes, composes, gates, or mediates agent interactions.¶
The party that grants authority to another party or agent.¶
The party or agent that receives attenuated authority.¶
The party that decides whether a claim is sufficient for a specific protocol action.¶
A party that later reviews, audits, composes, or relies on evidence of an action.¶
A protocol can use one credential, key, session, or record to carry more than one claim, but the draft needs to identify each claim separately. Reusing a carrier does not make the claims equivalent.¶
Workload identity documents, such as the WIMSE architecture [I-D.ietf-wimse-arch] and workload identity practices [I-D.ietf-wimse-workload-identity-practices], are useful examples of why an instance, workload, or execution environment claim should be separated from human or organizational authority and from delegated task scope.¶
A draft SHOULD identify which of the following claim classes it carries or depends on. The identifiers below are provisional and are intended to make early review concrete.¶
| ID | Claim Class | Review Question |
|---|---|---|
| C-001 | Instance identity | Which live agent, runtime, workload, endpoint, or process is acting now? |
| C-002 | Human or organizational authority | Who authorized the task, policy, role, or delegation? |
| C-003 | Delegated scope | What authority has been delegated, by whom, to whom, under what scope and attenuation? |
| C-004 | Session continuity | What state is bound to the current channel, connection, long-lived session, or task? |
| C-005 | Action evidence | What action was requested, attempted, completed, blocked, or failed? |
| C-006 | Tool or resource identity | Which external resource is being invoked or affected? |
| C-007 | Evidence provenance | What evidence, signature, receipt, attestation, log entry, or record supports an action or decision? |
| C-008 | Freshness or revocation | Is the authority, delegation, instance state, tool binding, or session state still current? |
| C-009 | Failure handling | What happens when the verifier cannot validate the claim for the requested action? |
| C-010 | Composition boundary | Which claims are preserved, transformed, or lost when agents, gateways, receipts, or tools are composed? |
The registry is intentionally claim-oriented rather than protocol-oriented. More than one candidate protocol can map to the same claim, and a protocol can map to only a subset of the registry.¶
For each security-relevant claim, a protocol draft SHOULD provide a row with the following fields.¶
The registry identifier for the claim being mapped.¶
The precise security statement being made.¶
The protocol field, token, credential, record, header, receipt, attestation, or out-of-band reference that carries the claim.¶
The party that validates the claim.¶
The check performed by the verifier.¶
The protocol layer or architectural review dimension associated with the row. This field is descriptive. It does not impose a fixed layer taxonomy on every protocol, and it does not require a protocol to spread claims across different layers.¶
The other state to which the claim is bound, such as a session identifier, TLS exporter, action digest, delegation chain, subject identifier, or tool invocation.¶
The replay, expiration, revocation, rotation, sequence, or recency rule.¶
The required behavior when the claim is missing, stale, inconsistent, or not verifiable.¶
Whether the row is implemented, not implemented, partially implemented, or externally implemented.¶
Whether the row is specified in the current draft, planned for a later revision, inherited from another document, or an architectural assumption.¶
The external draft, standard, service, governance process, transparency log, authorization system, attestation system, registry, or operational practice on which the row depends.¶
An optional reference to a public test vector, example, test case, implementation artifact, interop note, issue, pull request, or other stable evidence that makes the row checkable.¶
The matrix is intended to make review strict enough that a draft cannot obtain a security property merely by naming an adjacent mechanism. The following rules apply to a verifier matrix.¶
The Layer field needs to be explicit because candidate agent communication drafts do not all use the same architectural model. A draft MAY use conventional protocol-layer language, such as application, transport, and network, when that is the clearest description of where the relevant carrier or verifier behavior sits.¶
A draft MAY instead use an agent-native architectural taxonomy, such as substrate, composition, application, governance, or audit. If it does so, the draft needs to define that taxonomy and explain how the labels are used. For example, a "governance" label might be useful for review when a claim depends on a policy, registry, reputation process, slashing process, or administrative authority; however, that label is not a protocol layer unless the draft defines it as one.¶
The Layer field is open-ended per row. A protocol can place all of its relevant carriers or verifier behavior at the transport layer if that is how the protocol is designed. Conversely, a protocol can use an architectural label when the verifier decision depends on composition, audit, or governance behavior outside the transport exchange. The matrix does not require either vocabulary; it requires the chosen vocabulary to be explicit.¶
The matrix can be maintained as two linked tables.¶
The first table is a claim registry for AGENTPROTO review. It assigns stable identifiers to security claims or requirements, without selecting one protocol as the general solution for every row. Each row can name one or more candidate protocols that map to that claim.¶
| ID | Claim or Requirement | Candidate Protocol Mapping |
|---|---|---|
| C-001 | Agent or workload instance identity | AGTP, IACP, WIMSE profile, or another candidate |
| C-002 | Human or organizational authority | vLEI, OAuth, GNAP, authorization receipt, or another candidate |
| C-003 | Delegated scope | Delegation chain, delegation receipt, or capability profile |
| C-004 | Session continuity | Protocol session state, transport binding, or migration profile |
| C-005 | Action evidence | Audit receipt, capsule, transparency statement, or evidence graph |
The second table is a protocol mapping table. Each candidate draft provides one table for the claims it carries or depends on. This prevents a protocol from being treated as a complete architecture merely because it covers one claim well, and it lets the working group compare drafts row by row.¶
A protocol mapping row records the claim ID, claim text, carrier, verifier, verification rule, binding, freshness rule, layer label, failure behavior, implementation status, specification status, and any external dependency. For example, an instance-identity row might state that the carrier is a protocol field, the verifier is the peer, the binding is the handshake transcript, freshness is supplied by a nonce or epoch, and the failure behavior is connection rejection.¶
The claim registry is not a conformance target by itself. The protocol mapping table is the review surface: it states what the draft actually specifies, what is implemented, what is inherited from another component, what remains an architectural assumption, and what evidence or test vector can be used to check the row.¶
The implementation and specification status fields are security relevant. They prevent an author, implementer, or reviewer from treating an intended mechanism as a current protocol guarantee.¶
The current draft contains enough protocol text for an independent implementer to identify the carrier, verifier, binding, freshness rule, and failure behavior.¶
At least one implementation performs the verification behavior described by the row. The row SHOULD identify whether that evidence is source-level, unit-level, local-harness, interop, or deployment evidence. If a public test vector or reproducible artifact exists, the row SHOULD include an evidence reference.¶
The draft or implementation covers part of the row, but at least one of the carrier, verifier, binding, freshness rule, or failure behavior is incomplete.¶
The row depends on another specification or system. The dependency needs to be identified, and the draft needs to state what happens if the dependency is absent or not trusted. An inherited row is not complete if it merely names another document; it also needs to identify the inherited verifier, binding, freshness rule, and failure behavior or state that they are outside the current draft's scope.¶
The row is intended for a later revision and MUST NOT be treated as a current security guarantee.¶
The row depends on architecture, deployment, governance, or operational behavior that the draft does not specify.¶
Candidate protocol drafts can use the following compact template in a Security Considerations section, appendix, or companion document.¶
| Field | Description |
|---|---|
| ID | The claim identifier from the registry. |
| Claim | The precise statement being asserted or depended upon. |
| Carrier | The protocol field, credential, token, receipt, attestation, envelope, or external reference that carries the claim. |
| Verifier and verification rule | The party that performs the check and the rule it applies. |
| Binding and freshness | The state to which the claim is bound and the replay, revocation, expiration, sequence, nonce, or recency rule. |
| Layer | The protocol layer or architectural review dimension used by the draft for this row. |
| Failure behavior | The behavior when the claim is absent, stale, inconsistent, or not verifiable. |
| Implementation status | One of implemented, partial, none, or externally implemented. |
| Specification status | One of specified, planned, inherited, or assumption. |
| Dependency | The external document, system, service, registry, or operational process on which the row depends, if any. |
| Evidence reference | A stable public pointer to the test vector, example, test case, implementation artifact, interop record, issue, or pull request that supports the row, if available. |
When a draft does not carry a claim, the corresponding row MAY be omitted. If the draft relies on the claim for a security decision, the row SHOULD NOT be omitted; it should instead state the dependency or assumption explicitly.¶
A verifier matrix becomes more useful when its rows are checkable rather than only asserted. A row therefore MAY include an evidence reference. The reference can point to a public test vector, example, conformance test, implementation test, interop note, issue, pull request, or other stable artifact.¶
An evidence reference does not need to prove that a protocol is complete. It needs to support the specific row. For example, a test vector for session replay resistance supports a freshness or binding row; it does not by itself prove delegated authority. A receipt verification example supports an evidence-carrier row; it does not by itself prove that the recorded action was authorized.¶
When evidence is implementation-related, the row SHOULD distinguish the evidence type. Useful categories include source-level evidence, unit-level evidence, local-harness evidence, cross-implementation interop evidence, and deployment evidence. This distinction prevents a draft from treating a local unit test, public interop vector, and deployment signal as equivalent.¶
A useful evidence reference is row-specific. It identifies the input object, the canonicalization or serialization rule when bytes are compared, the verifier decision being tested, the expected positive result, and at least one negative case that fails for the same row. If the evidence depends on a private deployment or non-public implementation, the row should say so instead of treating the evidence as publicly reproducible.¶
Some mechanisms used by agent communication protocols are not communication protocols themselves. For example, an authorization receipt, transparency statement, action-evidence graph, revocation statement, or attestation result can be an artifact-layer mechanism that is carried by, referenced by, or bound to a communication exchange.¶
Such a mechanism can be a valid inheritance target for a protocol mapping row. If a draft marks a row as inherited, the row SHOULD identify the inherited mechanism and the decision state it supplies. The row should state the inherited verifier, carrier, binding, freshness rule, failure behavior, and evidence reference when available.¶
Marking a row as inherited is preferable to silently implying a guarantee. It allows a communication protocol to stay focused on its transport or session design while still making authority, action evidence, revocation, or audit dependencies visible to reviewers.¶
The following example is deliberately protocol-neutral. It is not a complete mapping for AGTP [I-D.hood-independent-agtp], IACP [I-D.gebauer-iacp], WIMSE [I-D.ietf-wimse-arch], or any other candidate draft.¶
Possible carriers include a role credential, account policy, vLEI, OAuth token, GNAP grant [RFC9635], or equivalent. The verifier is the receiving agent or policy verifier. The claim is bound to the task, scope, subject, and resource. Freshness comes from token lifetime, revocation, or policy version. Failure behavior is rejection or fresh authorization.¶
Possible carriers include channel authentication, an agent credential, attestation, or a protected key. The verifier is a peer, gateway, or relying party. The claim is bound to a session or channel transcript. Freshness comes from handshake freshness or attestation recency. Failure behavior is session rejection or capability downgrade.¶
Possible carriers include a delegation token or chain. The verifier is the recipient or gateway. The claim is bound to the delegator, delegatee, action class, and resource. Freshness comes from expiry, revocation, or attenuation version. Failure behavior is rejection of the delegated action.¶
Possible carriers include a tool call envelope or capability reference. The verifier is the tool gateway or policy engine. The claim is bound to delegated scope and tool identity. Freshness comes from a per-call nonce, session binding, or sequence. Failure behavior is denial of the invocation and failure recording if audit is claimed.¶
Possible carriers include an action digest, receipt, capsule, or audit record. The verifier is the profile verifier or composition verifier. The claim is bound to the canonical action input and native record. Freshness comes from digest context version and receipt policy. Failure behavior is refusal to compose the records as evidence of the same action.¶
Protocol authors SHOULD consider negative tests for each row in the verifier matrix. The following cases are intended as examples.¶
A delegation token or chain is structurally valid but expired, revoked, or superseded. The verifier rejects the delegated action or requests fresh authorization.¶
A tool call envelope is valid, but the envelope is not bound to the delegation scope, resource identifier, or session state used for the decision. The tool invocation is denied.¶
A claim or receipt from one session is replayed in another session. The verifier detects that the claim is not bound to the current session transcript, nonce, exporter, or equivalent channel state.¶
A receipt, log entry, capsule, or evidence record refers to a different action digest, input, resource, or policy version than the action being reviewed. The records are not composed as evidence of the same action.¶
A draft states that another component supplies authorization, attestation, or evidence, but does not identify the dependency or the failure behavior when the dependency is unavailable. The row is marked as inherited or assumption, not as a current protocol guarantee.¶
A candidate agent communication draft can use this document in three ways.¶
A draft that takes the third path remains reviewable if it identifies the dependency and failure behavior. The main review problem is not that a protocol omits a claim; the problem is when a protocol relies on a claim while leaving the verifier, binding, freshness rule, or failure behavior implicit.¶
When a draft supplies a verifier matrix, it SHOULD distinguish:¶
This distinction is important for review. A row that depends on a future reputation system, slashing process, governance committee, or external log can still be useful, but it should not be presented as a current protocol guarantee.¶
An agent communication protocol MUST NOT rely on a single identifier, token, session handle, log entry, or credential to imply multiple security properties unless the draft explicitly specifies the verification rule for each property.¶
In particular:¶
If a claim is required for a security decision and the verifier cannot validate that claim, the protocol MUST specify whether the action is rejected, downgraded, quarantined, delayed for additional authorization, or allowed with a recorded warning. Silent acceptance is not an acceptable default for a security-relevant claim.¶
Protocol authors should also consider cross-protocol composition. A claim that is valid in one protocol context might lose its security meaning when it is copied into a receipt, gateway envelope, audit record, or delegated session without preserving the binding and freshness state needed by the verifier.¶
Where attestation evidence is used, this document follows the RATS distinction among claims, evidence, appraisal, and relying-party decisions described in [RFC9334]. Where transparency services or signed-statement receipts are used, this document treats those receipts as evidence carriers and not as automatic proof of authorization or correct execution; see the SCITT architecture in [RFC9943].¶
Verifier-facing matrices can expose privacy-relevant design choices. A draft that binds actions to human authority, organizational identifiers, tool invocations, or long-lived sessions should state whether the binding creates linkability across actions, sessions, deployments, or administrative domains.¶
Drafts should avoid requiring globally linkable identifiers unless the security property being claimed requires them. Where possible, a matrix row should state whether the verifier needs a stable identifier, a pairwise identifier, a role or capability assertion, a freshness proof, or only evidence that a locally authorized policy decision was made.¶
This document makes no IANA requests.¶
If later versions define a reusable registry of claim identifiers, verifier matrix fields, or protocol mapping status values, that registry will need a separate IANA considerations section.¶
The AGTP [I-D.hood-independent-agtp] and IACP [I-D.gebauer-iacp] discussion threads provide useful early examples.¶
AGTP appears to expose candidate carriers for authority, agent identity, delegation, session state, composition-layer tool identity, and audit evidence. The next useful step is to turn those carriers into a matrix that states who verifies each claim and what failure behavior applies.¶
IACP has already been sketched by its author as a verifier-facing matrix. For reviewability, the useful next step is to separate rows that are currently in draft-gebauer-iacp-01 from rows that are future work or depend on governance systems not yet specified in the current I-D.¶
Both mappings can help converge a shared requirements note without requiring either protocol to adopt the other's wire format.¶
The author thanks Leonard Gebauer for proposing a two-level claim-registry and per-protocol mapping-table structure and for providing IACP-oriented mapping examples; Chris Hood for clarifying open-ended layer vocabulary and AGTP transport-layer mapping considerations; and Iman Schrock for proposing evidence-backed mapping rows and inheritance-target framing for artifact-layer mechanisms. The author also thanks participants on the AGENTPROTO mailing list for discussion of security-principal separation, verifier-facing review matrices, protocol comparison, and claim-level coordination among candidate drafts. Acknowledgment does not imply endorsement of this document or of any particular protocol mapping.¶