Internet-Draft Agent Continuity Evaluation November 2026
Selvaraj Expires 21 May 2027 [Page]
Workgroup:
AUDIT BOF
Internet-Draft:
draft-stafordtituss-agentic-mandate-evidence-00
Published:
Intended Status:
Informational
Expires:
Author:
S. T. Selvaraj
Independent

Continuity Evaluation of Agent Delegation Records

Abstract

The AUDIT architecture defines records that capture the user's intent, delegation, authorization state, and the actions that agents take across trust boundaries. Records alone don't answer the question an auditor, an operator, or a relying party asks next: did the executed effect stay within the authority the user delegated?

This document defines a deterministic, three-valued evaluation over such records. The outcomes are preserved, violated, and unresolved, and every non-preserved outcome names the invariant that was broken. The document also defines the claim model that the evaluation needs, the roles permitted to sign each record, a mapping onto the AUDIT record types, and a set of interoperable test vectors. It is derived from the Agentic Mandate Evidence Protocol (AMEP).

Status of This Memo

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 21 May 2027.

▲

Table of Contents

1. Introduction

AI agents act through chains of delegation: a user to an agent, an agent to sub-agents, and agents to tools, adapters, and services. Each hop can widen what is done relative to what was asked. Common examples:

[I-D.kuehlewind-audit-architecture] defines Interaction, Action, Delegation, and Authorization Transition records, and the propagation of audit context, so that these chains can be reconstructed.

This document is complementary. Given a set of such records, it specifies:

  1. a claim model that makes delegated authority machine-checkable (actions, resources, deny lists, data classes, an effect ceiling, validity, a delegation budget, and an optional risk budget);

  2. signer roles, so that a record counts as evidence only when it is signed by a party entitled to make it;

  3. invariants that a chain of records must satisfy (I1 to I11);

  4. a deterministic evaluation procedure that returns preserved, violated, or unresolved, together with the deciding invariant;

  5. test vectors, so that independent verifiers can demonstrate that they agree.

The evaluation can run before an effect, when an enforcement point decides on the predicted effect, or after the fact, when an auditor evaluates recorded effects. It never treats missing evidence as success, and it never treats a post-execution decision as a block.

1.1. Requirements Language

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.

1.2. Terminology

This document uses the roles of [I-D.kuehlewind-audit-architecture]: User, Agent, Tool/Service, Auditing Service, Audit Store, Transparency Log, and Auditor. It adds:

Mandate:

a signed claim set issued for a principal, stating what an agent may do on the principal's behalf.

Intent:

an optional claim set derived from a single request (for example, a prompt), narrower than the mandate.

Invocation:

a declared call to a tool or service, made under a mandate (possibly delegated).

Effect:

what was actually executed at the boundary where the action took effect.

Observer:

the party that produced the effect record.

Verifier:

an entity that runs the evaluation in Section 6.

2. Relationship to the AUDIT Architecture

Table 1
This document AUDIT record type What is evaluated
Mandate, Intent Interaction Record (prompt, signed grant) claim set C (Section 3)
Delegation Delegation Record attenuation, I1
Approval Interaction Record (approval, HITL escalation) binding to the exact effect, I8
Invocation and interpretation Action Record (declared) interpretation provenance (I3), influence (I4)
Effect Action Record (at the effect boundary) I2, I5, I9, I10, I11
Grant, revocation, status Authorization Transition Record liveness, I6
Continuity decision (none) the output of this document, with its phase

Mandates and delegations commonly originate in OAuth 2.0 Token Exchange chains [RFC8693]. Records MAY be carried as COSE_Sign1 objects [RFC9052], and MAY be registered with a transparency service [I-D.ietf-scitt-architecture], which makes selective omission of records detectable.

This document doesn't define new transport or storage. It requires only that records carry the fields listed in Section 7, and that records can be linked using the AUDIT audit context: trace, parent, actor, and on-behalf-of.

3. Claim Model

A claim set is C = (A, R, A⁻, R⁻, D, E, V, P, K, B), where:

C1 ⊑ C2 (C1 is equal to or narrower than C2) holds if and only if: every pattern in A1 and R1 is subsumed by some pattern in A2 or R2 respectively; every pattern in A2⁻ and R2⁻ is subsumed by some pattern in A1⁻ or R1⁻ respectively (denies only grow); D1 ⊆ D2; E1 ≤ E2; V1 ⊆ V2; P1 = P2 or P2 is unrestricted; the depth rule holds (if K2 is present, K2 > 0 and K1 < K2); and B1 ≤ B2 when B2 is present.

The meet C1 ⊓ C2 is taken component-wise, with denies unioned so that no hop and no intent can lift a deny.

Resource identifiers MUST be canonical. File-system paths MUST be absolute and normalized, with the home directory expanded and ".." collapsed. URLs MUST carry their resolved host class. SaaS objects MUST be identified as provider:type/id. A verifier MUST NOT rely on user-relative forms.

An effect is x = (a, r, d, e, t). x ⊨ C if and only if a matches A and not A⁻, r matches R and not R⁻, e ≤ E, every released (data class, recipient class) pair is in D, and t ∈ V.

4. Signer Roles

A valid signature shows only that a key signed a record. Each key in the verifier's key set carries roles, and a record counts as signed only when its key holds a role permitted for the record's kind:

Table 2
Record Permitted signer roles
Mandate, revocation, revocation status issuer
Delegation, intent issuer, host
Interpretation, invocation, decision host
Effect observer
Approval approver
Content finding host, observer

Without roles, a compromised host key could mint its own mandate or approve its own action.

5. Invariants

Table 3
ID Invariant When broken
I1 Attenuation: child ⊑ parent at every delegation edge violated
I2 Every effect matches the declared (or mediated) effect, satisfies the meet of the chain (and of the intent), and stays within risk budgets unless a bound approval covers it violated
I3 The invocation was interpreted by an approved, version-pinned mapping unresolved
I4 Content withheld by a quarantine did not reach a later step; a mutation influenced by content that is not signed and trusted was confirmed by the principal violated (executed) or unresolved
I5 Data classes released to a recipient are permitted violated
I6 No ancestor was revoked, per signed revocation or status evidence, at or before the invocation violated
I7 All required records are present, well-formed, signed by a permitted role, and fresh where required unresolved
I8 An approval matches the executed effect (without its time), is within its validity window, unconsumed, and used once violated
I9 No agent effect targets guardrail configuration, keys, instruction files, or the audit store violated
I10 An effect at or above write_shared names its actor and was observed by a party other than that actor unresolved
I11 Every recorded effect links to an authorized invocation, and none exists for an invocation a pre-execution decision denied violated

6. Evaluation Procedure

For each invocation, in recorded order, a verifier MUST apply the following checks in order and return the first outcome that applies. "Verified" means signed by a key holding a permitted role (Section 4).

ID   Outcome     Condition
I4   violated    quarantined content in the influence set,
                 not confirmed by the principal
I7   unresolved  no root mandate
I7   unresolved  cited intent missing, or a needed record
                 not verified
I7   unresolved  lineage names an invocation that is not earlier
I3   unresolved  no approved interpretation, or a pin mismatch
I1   violated    a delegation edge where not (child ⊑ parent)
I6   violated    verified revocation or status shows an
                 ancestor revoked
I7   unresolved  unverified revocation on the chain, or a
                 revocable record without a fresh verified status
I9   violated    guardrail target
I4   violated    untrusted influence on a mutation, unconfirmed
                 (unresolved instead if no effect exists)
I7   unresolved  no effect record
     For every effect record of the invocation:
I7   unresolved    record not verified
I10  unresolved    e >= write_shared and the actor is absent,
                   the effect is self-observed, or assurance L0
I2   violated      executed != declared (and != the mediated
                   effect)
I9   violated      executed resource is a guardrail
I2   violated      x does not satisfy the meet of the chain and
                   intent (I5 when the failure is a release)
I5   violated      data classes carried in through lineage reach
                   a recipient class the claims do not permit
I7   unresolved  approval missing or not verified
I8   violated    approval unbound, outside its window,
                 consumed, or reused
I7   violated    recorded budget spend != recomputed cost
I2   violated    risk budget exceeded without a bound approval
-    preserved   otherwise

After all invocations:

ID   Outcome     Condition
I11  violated    pre-execution deny/hold decision, and an effect
                 exists (enforcement contradicted)
-    preserved   pre-execution deny/hold decision, no effect,
                 enforcement fail-closed or applied = confirmed
I11  violated    effect with no invocation

Lineage: an effect may record the data classes it read (accessed) and the recipient class of what it sent; an invocation may name the earlier invocations its input came from (derived_from). The data classes an invocation carries are those its own effects read plus those carried by the invocations it derives from, transitively. This detects sensitive data leaving in a later step even when that step declares no release.

A verifier evaluating a stream of packets MAY carry approval use and risk-budget spending from one packet to the next, so that single use and budgets hold across the stream.

Decisions carry a phase: pre_execution, post_execution, or simulation. Only pre-execution decisions can confirm or contradict a block. A post-execution decision is detection and MUST NOT be presented as having prevented the action.

When B is present, the cost of x is base(e) × m(d) × rev(x). The base table is read 0, write_local 1, write_shared 3, external_send 5, destructive 10, financial 20. m(d) is the largest data-class multiplier among the released classes (1, 2, or 5). rev(x) is 1 if the effect is a read, or reversible and not an external send, and 3 otherwise. The cost is charged to every node in the chain. The tables are registries (Section 12).

7. Required Fields

The evaluation needs the following fields from each AUDIT record. Field names are placeholders until the AUDIT data model is defined.

Records are canonicalized with JCS [RFC8785] and signed with Ed25519 [RFC8032]. Times are numbers of seconds since the epoch or RFC 3339 [RFC3339] strings. A CDDL [RFC8610] definition and JSON Schemas are published in [AMEP].

8. Test Vectors

[AMEP] publishes 95 vectors: 25 positive and 70 must-reject. The must-reject vectors cover all eleven invariants, signer roles, revocation status, decision phase, deny lists, data lineage, state across packets, risk-budget accounting, and a deny that an executed effect contradicts. Each vector is a packet of signed records, with the expected outcome and invariant. Two independently written implementations (Python, and JavaScript run under Node.js and in a browser) agree on all 95.

A conforming verifier MUST return the expected outcome and invariant for every vector.

9. Implementation Status

Note to the RFC Editor: please remove this section before publication, per [RFC7942].

Implementation experience motivated several parts of this document: canonical resource identifiers (absolute-path forms bypassed relative-prefix rules); recording the enforcement context and phase (hosts differ in whether they support "ask" and whether hook failures block); and treating an effect that contradicts a deny as evidence of bypass.

10. Security Considerations

11. Privacy Considerations

Effect records can contain personal data. Verifiers need only canonical actions, resource identifiers, data-class labels, and digests. Payloads SHOULD be detached and hashed, following the AUDIT selective-disclosure work.

12. IANA Considerations

This document proposes registries for effect classes, data classes, recipient classes, signer roles, and the risk-cost tables, with the registration policy Specification Required. The registries are to be defined in a later revision.

13. References

13.1. Normative References

[RFC2119]
Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, , <https://www.rfc-editor.org/rfc/rfc2119>.
[RFC3339]
Klyne, G. and C. Newman, "Date and Time on the Internet: Timestamps", RFC 3339, DOI 10.17487/RFC3339, , <https://www.rfc-editor.org/rfc/rfc3339>.
[RFC8032]
Josefsson, S. and I. Liusvaara, "Edwards-Curve Digital Signature Algorithm (EdDSA)", RFC 8032, DOI 10.17487/RFC8032, , <https://www.rfc-editor.org/rfc/rfc8032>.
[RFC8174]
Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, , <https://www.rfc-editor.org/rfc/rfc8174>.
[RFC8785]
Rundgren, A., Jordan, B., and S. Erdtman, "JSON Canonicalization Scheme (JCS)", RFC 8785, DOI 10.17487/RFC8785, , <https://www.rfc-editor.org/rfc/rfc8785>.

13.2. Informative References

[AMEP]
Selvaraj, S. T., "Agentic Mandate Evidence Protocol (AMEP) v0.2", , <https://github.com/stafordtituss/amep>.
[I-D.ietf-scitt-architecture]
Birkholz, H., Delignat-Lavaud, A., Fournet, C., Deshpande, Y., and S. Lasker, "An Architecture for Trustworthy and Transparent Digital Supply Chains", Work in Progress, Internet-Draft, draft-ietf-scitt-architecture-22, , <https://datatracker.ietf.org/doc/html/draft-ietf-scitt-architecture-22>.
[I-D.kuehlewind-audit-architecture]
Kühlewind, M. and H. Birkholz, "An Architecture for Auditing Agent Delegation and Interactions", Work in Progress, Internet-Draft, draft-kuehlewind-audit-architecture-01, , <https://datatracker.ietf.org/doc/html/draft-kuehlewind-audit-architecture-01>.
[RFC7942]
Sheffer, Y. and A. Farrel, "Improving Awareness of Running Code: The Implementation Status Section", BCP 205, RFC 7942, DOI 10.17487/RFC7942, , <https://www.rfc-editor.org/rfc/rfc7942>.
[RFC8610]
Birkholz, H., Vigano, C., and C. Bormann, "Concise Data Definition Language (CDDL): A Notational Convention to Express Concise Binary Object Representation (CBOR) and JSON Data Structures", RFC 8610, DOI 10.17487/RFC8610, , <https://www.rfc-editor.org/rfc/rfc8610>.
[RFC8693]
Jones, M., Nadalin, A., Campbell, B., Ed., Bradley, J., and C. Mortimore, "OAuth 2.0 Token Exchange", RFC 8693, DOI 10.17487/RFC8693, , <https://www.rfc-editor.org/rfc/rfc8693>.
[RFC9052]
Schaad, J., "CBOR Object Signing and Encryption (COSE): Structures and Process", STD 96, RFC 9052, DOI 10.17487/RFC9052, , <https://www.rfc-editor.org/rfc/rfc9052>.

Acknowledgments

This document is derived from the Agentic Mandate Evidence Protocol (AMEP), designed and written by the author.

Author's Address

Staford Titus Selvaraj
Independent