



Network Working Group                                           Y. Jiang
Internet-Draft                                                     L. Li
Intended status: Informational                                   Y. Song
Expires: 5 December 2026                                          F. Liu
                                                                  Huawei
                                                             3 June 2026


  Security Considerations for Intent-Based Requests in Agentic Systems
                     draft-jiang-intent-security-02

Abstract

   Intent-based requests enable users, applications, and agents to
   express goals and constraints without specifying step-by-step
   procedures.  Such intents are commonly translated into executable
   directives and propagated across multiple entities (clients, agents,
   authorization components, orchestration functions, and execution
   endpoints).  This multi-hop processing expands the attack surface for
   tampering, privilege escalation, constraint bypass, and intent drift.
   In addition, at the point where an intent enters the system, a forged
   or unauthorized origin may cause actions to be taken without valid
   consent.

   This document provides a solution-agnostic security analysis for
   intent-based requests across agentic systems.  It introduces a
   reference model and scenarios to guide protocol and system design,
   and also presents threats and requirements.  The document emphasizes
   origin authentication and admission control, constraint validation,
   invocation validation, multi-hop chain-of-custody, and policy-driven
   responses to drift, while remaining independent of any specific
   deployment domain.

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."




Jiang, et al.            Expires 5 December 2026                [Page 1]

Internet-Draft               Intent Security                   June 2026


   This Internet-Draft will expire on 5 December 2026.

Copyright Notice

   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.

Table of Contents

   1.  Introduction  . . . . . . . . . . . . . . . . . . . . . . . .   3
     1.1.  Scope . . . . . . . . . . . . . . . . . . . . . . . . . .   3
   2.  Terminology and Conventions . . . . . . . . . . . . . . . . .   3
     2.1.  Conventions . . . . . . . . . . . . . . . . . . . . . . .   3
     2.2.  Definitions . . . . . . . . . . . . . . . . . . . . . . .   3
     2.3.  Acronyms  . . . . . . . . . . . . . . . . . . . . . . . .   5
   3.  Problem Statement and Threat Model  . . . . . . . . . . . . .   5
     3.1.  Example of multi-hop intent architecture  . . . . . . . .   5
     3.2.  Threats . . . . . . . . . . . . . . . . . . . . . . . . .   7
     3.3.  Requirements  . . . . . . . . . . . . . . . . . . . . . .   8
   4.  Reference Model . . . . . . . . . . . . . . . . . . . . . . .   9
     4.1.  Reference Model Entities  . . . . . . . . . . . . . . . .  10
     4.2.  Operational Overview  . . . . . . . . . . . . . . . . . .  11
   5.  Security Scenarios  . . . . . . . . . . . . . . . . . . . . .  11
     5.1.  Scenario 1: Directive Tampering and Authorization Boundary
           Expansion . . . . . . . . . . . . . . . . . . . . . . . .  12
     5.2.  Scenario 2: Spoofed Origin and Non-Consensual Intent
           Origination . . . . . . . . . . . . . . . . . . . . . . .  12
   6.  Security Considerations . . . . . . . . . . . . . . . . . . .  13
     6.1.  Scenario-to-Requirement Mapping . . . . . . . . . . . . .  13
     6.2.  Considerations for Scenario 1 (Directive Tampering) . . .  14
       6.2.1.  Overview  . . . . . . . . . . . . . . . . . . . . . .  14
       6.2.2.  Illustrative Procedure  . . . . . . . . . . . . . . .  14
     6.3.  Considerations for Scenario 2 (Spoofed/Non-Consensual
           Origin) . . . . . . . . . . . . . . . . . . . . . . . . .  15
       6.3.1.  Overview  . . . . . . . . . . . . . . . . . . . . . .  15
       6.3.2.  Illustrative Procedure  . . . . . . . . . . . . . . .  16
     6.4.  General Security Considerations . . . . . . . . . . . . .  17
   7.  IANA Considerations . . . . . . . . . . . . . . . . . . . . .  17
   8.  Normative References  . . . . . . . . . . . . . . . . . . . .  17



Jiang, et al.            Expires 5 December 2026                [Page 2]

Internet-Draft               Intent Security                   June 2026


   9.  Informative References  . . . . . . . . . . . . . . . . . . .  18
   Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . .  19
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .  19

1.  Introduction

   Intent-based interaction is increasingly adopted in automation,
   orchestration, and agentic systems, where a request expresses desired
   outcomes and constraints rather than explicit procedures.  A
   receiving system (or a chain of systems) translates the intent into
   executable directives and invokes tools or services to achieve the
   intended outcome.

   Multi-hop processing (client-to-agent, agent-to-agent, agent-to-tool/
   service) introduces security risks beyond traditional single-hop
   APIs, including: (1) integrity and substitution attacks against
   derived directives, (2) privilege escalation during tool/service
   invocation, (3) constraint bypass, (4) multi-hop intent drift where
   constraints degrade or diverge over transformations, and (5)
   admission-time risks where an intent of spoofed or unauthorized
   origin is accepted and acted upon without valid consent.

   This document does not define a new protocol.  Instead, it provides a
   security-oriented reference model, threat analysis, requirements, and
   scenarios to support future standardization and interoperable
   designs.

1.1.  Scope

   This document focuses on security considerations for intent-based
   requests in multi-hop agentic systems.  While examples may reference
   telecom or networking contexts, the analysis applies broadly to any
   domain where intent processing spans multiple trust boundaries.

2.  Terminology and Conventions

2.1.  Conventions

   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.

2.2.  Definitions

   This document uses the following terms:




Jiang, et al.            Expires 5 December 2026                [Page 3]

Internet-Draft               Intent Security                   June 2026


   Intent:  A declarative expression of desired operational goals and
      outcomes, without specifying how to achieve or implement them.
      This definition is aligned with intent-based networking (IBN)
      guidance [RFC9315] [RFC9316].

   Intent Translation:  The process of transforming an intent into more
      concrete representations, such as constraints, objectives,
      candidate procedures, or executable directives.

   Constraint:  A condition that limits acceptable outcomes or actions.
      Constraints may include invariants, policy rules, safety
      boundaries, and compliance requirements.

   Constraint Validation:  Verifying whether an intent and/or its
      derived artifacts comply with applicable constraints, invariants,
      policy rules, and safety boundary requirements.

   Invocation:  A request to a tool or service intended to fulfill an
      intent (e.g., API call, workflow step, actuation command).

   Invocation Validation:  Determining whether an invoker holds the
      required privileges to invoke a tool or service and whether
      invocation parameters satisfy the requirements and constraints
      specified by the intent.

   Observation:  Telemetry, events, measurements, or other signals used
      for monitoring and assurance.

   Drift:  A divergence between the intent (including its constraints)
      and the realized plan or actions over time or across multi-hop
      transformations.

   Derived Directive:  An executable or enforceable artifact generated
      from an intent through translation, such as an allowed rule set,
      capability token, or authorization grant.

   Intent Originator:  The entity that produces an intent (e.g., a user,
      an application, or an agent).  The originator is the asserted
      source of the intent and is distinct from the entity that merely
      transports or forwards it.

   Admission Control:  The decision, taken before an intent is forwarded
      into or accepted by the processing chain, of whether to admit the
      intent, based on the verified origin, the originator's
      authorization to request the targeted service, and applicable
      consent.





Jiang, et al.            Expires 5 December 2026                [Page 4]

Internet-Draft               Intent Security                   June 2026


2.3.  Acronyms

   IBN:  Intent-Based Networking

   IBS:  Intent-Based System

3.  Problem Statement and Threat Model

   In many agentic systems, an intent is translated into executable
   directives (e.g., an allowed rule set) that must be propagated across
   multiple entities and enforced at execution endpoints.  However,
   existing designs often lack end-to-end mechanisms that jointly
   ensure: (1) the intent originates from an authenticated and
   authorized originator and has obtained any required consent before
   admission, (2) directives remain within authorized boundaries across
   transformations and propagation, (3) constraints are validated before
   execution, (4) invocations are privilege-checked and constraint-
   checked at each call boundary, and (5) drift is detected and handled
   under policy.

3.1.  Example of multi-hop intent architecture

   In modern agentic systems, complex user intents often exceed the
   capabilities of single-agent architectures.  Multi-agent systems
   provide a robust framework for intent processing through specialized
   role assignments, parallel execution, and structured intent
   propagation.  In this section, observing the numerous agent
   architectures, a typical architecture is present that demonstrate
   effective intent processing patterns across domains, including:
   sequential orchestration for intent-based processing, parallel
   systems for information gathering, etc.  The core principle is that
   intent decomposition and propagation are fundamental to multi-agent
   collaboration.  Each architecture implements this principle
   differently based on domain requirements, but all maintain the
   critical property that intent must be preserved, verifiable, and
   contextually appropriate as it flows through the system.















Jiang, et al.            Expires 5 December 2026                [Page 5]

Internet-Draft               Intent Security                   June 2026


                                             |intent input
                                             v
                                     +--------------------+
                                     |      Agent1        |
                                     | (e.g., Summarizer) |
                                     +--------------------+
                                             v
                                     +--------------------+
                                     |     Agent2         |
                                     | (e.g., Translator) |
                                     +--------------------+
                                             v
                                     +--------------------+
                                     |     Agent3         |
                                     |   (e.g., QA)       |
                                     +--------------------+
                                             |    Result
                                             v

          Figure 1: Example of the typical multi-agent processing

   Specifically, the architecture for multi-hop intent processing is
   shown in Figure 1, following the sequential orchestration pattern of
   the Microsoft Agent Framework [MS-AF-SEQ].  In the figure, agents
   process intents in a pipeline fashion.  By default, each agent
   receives the conversation from the previous agent, ensuring context
   preservation while allowing specialized processing at each stage.

   The architecture consists of:

   1.  Agent Pipeline: Agents are arranged in a predefined sequence
       where output from one agent becomes input for the next.

   2.  Shared Context: By default, each agent consumes the previous
       agent's full conversation, so context is preserved across the
       pipeline.  The framework also allows agents to be configured to
       consume only the previous agent's response messages, which
       truncates earlier context.

   3.  Human-in-the-Loop: Optional approval points for sensitive
       operations (e.g., tools marked as approval-required).

   4.  Mixed Executors: Ability to combine LLM-based agents with custom
       code executors.

   Usually, the original intent can be preserved through the shared
   conversation history, with each agent adding specialized processing
   while maintaining contextual continuity.  The system demonstrates



Jiang, et al.            Expires 5 December 2026                [Page 6]

Internet-Draft               Intent Security                   June 2026


   that even simple sequential architectures can effectively process
   complex intents when agents have clearly defined roles and shared
   context.  However, under certain specific threats, the intent may
   change, potentially introducing security risks.  The next section
   will focus on this in detail under the architecture.

3.2.  Threats

   Based on the typical multi-agent processing in Section 3.1
   (Figure 1), the following representative threats are considered.
   T1-T5 arise during multi-hop intent processing, while T6-T7 arise at
   the intent origination/admission boundary, i.e., where an intent
   enters the system:

   T1 (Directive Tampering/Substitution):  A malicious intermediary
      agent modifies conversation history or derived directives between
      pipeline stages, altering budget constraints or action parameters
      while maintaining superficial coherence.

   T2 (Unauthorized Invocation / Privilege Escalation):  An agent abuses
      mixed-executor capabilities by smuggling unauthorized commands
      through parameter injection, bypassing the intended privilege
      boundary because custom code executors run arbitrary code without
      an enforced access-control layer.

   T3 (Constraint Bypass):  Security constraints degrade across pipeline
      stages due to context truncation or improper inheritance,
      violating the shared-context integrity assumption.

   T4 (Multi-Hop Semantic Drift):  Gradual semantic deviation occurs as
      agents reinterpret ambiguous instructions across hops, causing
      final actions to diverge from original intent boundaries despite
      syntactically intact messages.

   T5 (Monitoring Evasion / False Observations):  Attackers evade
      detection by suppressing, forging, or selectively presenting
      observations used for assurance and drift detection.

   T6 (Origin Spoofing / Forged Provenance):  A co-resident or upstream
      malicious application or agent fabricates an intent artifact that
      appears to originate from the user or a legitimate originator, so
      that downstream entities accept and act on an intent that the
      claimed originator never authorized.

   T7 (Unauthorized or Non-Consensual Origination):  An originator that






Jiang, et al.            Expires 5 December 2026                [Page 7]

Internet-Draft               Intent Security                   June 2026


      is not entitled to request the targeted service, or that is
      operating in a disallowed state (e.g., running unattended in the
      background), issues a high-impact intent without valid user
      consent; the system admits it because it does not gate on the
      originator's eligibility, runtime state, or explicit consent.

   NOTE1: By default, the example framework does not provide
   cryptographic binding between pipeline stages, so agents cannot be
   assumed to be mutually trustworthy.  The degree of such binding may
   vary across implementations.

   NOTE2: Human approval may be agent-triggered rather than enforced by
   the receiver, creating bypass opportunities.

3.3.  Requirements

   Based on the threats above, this document identifies the following
   security requirements:

   R1 (Provenance and Authorization Boundary Binding):  The system
      provides a verifiable binding between the intent, derived
      directives, and the applicable authorization boundary, such that
      unauthorized expansion can be detected or prevented.

   R2 (Chain-of-Custody for Derived Directives):  The system protects
      derived directives against tampering and substitution across
      multi-hop propagation.

   R3 (Constraint Validation):  The system validates the intent and/or
      derived artifacts against applicable constraints, invariants,
      policy rules, and safety boundaries before accepting or executing
      actions.

   R4 (Invocation Validation):  The system validates that an invoker
      holds the required privileges to invoke a tool/service and that
      invocation parameters satisfy intent constraints prior to and/or
      at invocation time.

   R5 (Non-Bypass Enforcement):  The execution endpoint enforces
      constraints and authorization boundaries such that direct/side-
      path invocation cannot bypass required checks.

   R6 (Observability and Auditability):  The system provides sufficient
      observations and audit evidence to support compliance assessment,
      drift detection, and incident investigation.

   R7 (Policy-Driven Drift Response):  Upon drift detection or




Jiang, et al.            Expires 5 December 2026                [Page 8]

Internet-Draft               Intent Security                   June 2026


      constraint violation, the system supports policy-driven responses
      (e.g., deny, degrade, re-confirm, re-negotiate, fallback).

   R8 (Origin Authentication):  The system provides a verifiable binding
      between an intent artifact and the identity of its actual
      originator, such that a forged or spoofed origin can be detected
      before the intent is admitted or forwarded.

   R9 (Originator Authorization and Consent-Gated Admission):  Before
      admitting or forwarding an intent, the system determines whether
      the originator is permitted to request the targeted service, based
      on originator attributes (e.g., identity, type, runtime state,
      history) and applicable permission policy.  For high-impact or
      irreversible actions, the system additionally obtains and verifies
      explicit user consent.  Intents from unauthorized originators,
      from originators in a disallowed state, or lacking required
      consent are rejected or escalated.

4.  Reference Model

   This section introduces a technology-neutral reference model for
   intent-based requests.  The model is aligned with intent-based system
   decomposition commonly used in IBN guidance [RFC9315], while
   remaining applicable to non-networking domains.

   +--------------+           +---------------------------+
   |  User Space  |           |       IBS Space           |
   |              |  Intent   |                           |
   |   Intent     |---------->|  Intent Processing Func   |
   |  Originator  | Artifact  |                           |
   |              |---------->|  +---------+  +---------+ |
   |   Intent     |           |  | Intent  |  |Constrain| |
   |   Client     |           |  |Transform|  |Validate |-+-> Policy/
   +--------------+           |  +---------+  +---------+ |   Constrain
                              |                           |   Authority
                              |  +---------+              |
                              |  |Invocate |              |
                              |  | Gate    |--------------+-> Tool/
                              |  +---------+              |   Service
                              +---------------------------+   Provider
                                       ^          |
                                       |   Observe|
                                       |          v
                              +---------------------------+
                              |  Observer (Monitoring)    |
                              +---------------------------+

         Figure 2: Reference Model for Multi-Hop Intent Processing



Jiang, et al.            Expires 5 December 2026                [Page 9]

Internet-Draft               Intent Security                   June 2026


   The figure separates User Space from IBS Space for clarity.
   Deployments may collapse functions into fewer components or
   distribute them across multiple agents and services.

4.1.  Reference Model Entities

   The following entities are defined in the reference model:

   Intent Originator:  The party whose goals and constraints are to be
      satisfied (e.g., human user, application owner, operator, or
      delegated principal).

   Intent Client:  The component that submits intents to an IBS and may
      carry contextual signals.  The Intent Client (or an equivalent
      admission point) may also enforce origin authentication and
      originator-level admission control before an intent is forwarded
      (see R8 and R9).

   Intent Processing Function:  A logical function that performs
      translation, validation, and orchestration for intent fulfillment.
      This function encompasses the Intent Transformer, Constraint
      Validator, and Invocation Gate.

   Intent Transformer:  A function that transforms intent
      representations (e.g., natural language to structured intent,
      structured intent to constraints/objectives, objectives to derived
      directives).

   Constraint Validator:  A function that enforces R3 by validating
      intents and derived artifacts against constraints, invariants,
      policy rules, and safety boundaries.

   Invocation Gate:  A function that enforces R4 and R5 by privilege-
      checking and constraint-checking each tool/service invocation and
      preventing bypass of required checks.

   Policy/Constraint Authority:  A logical source of constraints and
      policy boundaries (e.g., organizational policy, compliance rules,
      safety invariants, subscription/contract limits).  It also
      supplies the permission policy that determines which originators
      may request which services (R9).

   Tool/Service Provider:  A system that executes actions (APIs,
      workflows, actuators, management functions, data services).

   Observer (Monitoring Function):  A function that collects
      observations (telemetry, events, measurements) used for assurance,
      compliance assessment, and drift detection (R6 and R7).



Jiang, et al.            Expires 5 December 2026               [Page 10]

Internet-Draft               Intent Security                   June 2026


4.2.  Operational Overview

   This section provides an informative lifecycle overview to
   contextualize admission control, constraint validation, invocation
   validation, observation, and drift handling.

   1.   The Intent Originator expresses an intent via the Intent Client.

   2.   The Intent Client (or an equivalent admission point)
        authenticates the origin and applies admission control (R8, R9):
        it verifies the originator, evaluates the originator's
        eligibility to request the targeted service, and obtains consent
        for high-impact actions before forwarding.

   3.   The Intent Client submits an admitted intent artifact to the
        IBS.

   4.   The IBS performs intent translation (Intent Transformer) to
        derive constraints, objectives, and candidate directives.

   5.   The IBS performs constraint validation (R3) in consultation with
        the Policy/Constraint Authority.

   6.   The IBS determines one or more tool/service invocations needed
        for fulfillment.

   7.   Prior to each invocation, the IBS performs invocation validation
        (R4), including privilege checks and parameter/constraint
        checks.

   8.   The Tool/Service Provider executes the invocation and returns
        results; side effects may be irreversible.

   9.   The Observer produces observations used by the IBS for assurance
        and drift detection (R6).

   10.  If drift or violations are detected, the IBS applies a policy-
        driven response (R7), such as deny, degrade, re-confirm, re-
        negotiate, or fallback.

5.  Security Scenarios

   This section describes representative security scenarios using a
   consistent template: Setting, Actors, Assets, Attack Sketch, Impact,
   and Relevant Requirements.  These scenarios are not exhaustive but
   illustrate key threat patterns in multi-hop intent processing.





Jiang, et al.            Expires 5 December 2026               [Page 11]

Internet-Draft               Intent Security                   June 2026


5.1.  Scenario 1: Directive Tampering and Authorization Boundary
      Expansion

   Setting:
      An IBS translates an intent into derived directives (e.g., allowed
      rules) that traverse multiple intermediaries before reaching an
      execution endpoint.

   Actors:
      Intent Originator, Intent Client, IBS, one or more intermediaries
      (agents/clients), Tool/Service Provider.

   Assets:
      Authorization boundary, constraints/invariants, protected
      resources, audit evidence.

   Attack Sketch:
      1.  An intermediary modifies derived directives to add operations
          or widen resource scope.

      2.  The modified directives are forwarded to the execution
          endpoint without effective detection.

      3.  The endpoint performs out-of-bound operations (e.g., modifying
          account state, accessing other parties' data, disabling safety
          rules).

   Impact:
      Privilege escalation, policy bypass, unauthorized side effects,
      compliance violations.

   Relevant Requirements:
      R1 (Provenance and Authorization Boundary Binding), R2 (Chain-of-
      Custody for Derived Directives), R3 (Constraint Validation), R5
      (Non-Bypass Enforcement), R6 (Observability and Auditability).

5.2.  Scenario 2: Spoofed Origin and Non-Consensual Intent Origination

   Setting:
      A user-facing device (e.g., a terminal) hosts multiple
      applications and agents.  Any of them can express intents that are
      submitted to a local Intent Client and forwarded to a remote IBS
      that accepts intent artifacts and may trigger high-impact services
      or actions.  The remote receiver acts on whichever intents it
      admits.






Jiang, et al.            Expires 5 December 2026               [Page 12]

Internet-Draft               Intent Security                   June 2026


   Actors:
      Intent Originator (the user or a legitimate originator), a
      legitimate local agent, a malicious co-resident application/agent,
      the Intent Client, and the remote IBS / Tool/Service Provider.

   Assets:
      Originator identity and account/identity bindings, user consent,
      the permission policy that determines which originators may
      request which services, billing/spending limits, and safety
      constraints.

   Attack Sketch:
      1.  The malicious application fabricates an intent artifact that
          appears to originate from the user or a legitimate agent
          (spoofed provenance); or an originator that is not entitled to
          the targeted service, or is running unattended in the
          background, issues a high-impact intent.

      2.  The Intent Client / IBS forwards the intent, and the remote
          receiver executes high-impact actions (purchases, data
          disclosure, account or state changes) without verifying the
          actual originator, the originator's eligibility for the
          requested service, the originator's runtime state, or valid
          user consent.

   Impact:
      Unauthorized actions, fraud, privacy leakage, billing abuse, and
      irreversible side effects.

   Relevant Requirements:
      R8 (Origin Authentication), R9 (Originator Authorization and
      Consent-Gated Admission), R3 (Constraint Validation), R6
      (Observability and Auditability).

6.  Security Considerations

   This section provides solution-agnostic security considerations
   mapped to the scenarios and requirements.  Implementations may
   realize these considerations using different security mechanisms
   (tokens, signatures, attestation, policy engines, or protocol-level
   bindings).

6.1.  Scenario-to-Requirement Mapping

   Table 1 summarizes the primary mappings between the elaborated
   scenarios and security requirements.  Note that these mappings are
   non-exhaustive; additional requirements may apply depending on
   deployment context.



Jiang, et al.            Expires 5 December 2026               [Page 13]

Internet-Draft               Intent Security                   June 2026


    +=========================+=================+====================+
    | Scenario                | Primary Threats | Key Requirements   |
    +=========================+=================+====================+
    | 1 (Directive Tampering) | T1, T3          | R1, R2, R3, R5, R6 |
    +-------------------------+-----------------+--------------------+
    | 2 (Spoofed/Non-         | T6, T7          | R8, R9, R3, R6     |
    | Consensual Origin)      |                 |                    |
    +-------------------------+-----------------+--------------------+

                 Table 1: Scenario to Requirement Mapping

6.2.  Considerations for Scenario 1 (Directive Tampering)

   Scenario 1 highlights that derived directives are often more
   operationally powerful than the original intent text.  Therefore,
   systems should treat derived directives as security-relevant
   artifacts whose integrity and authorization boundary binding should
   be protected across hops.

6.2.1.  Overview

   The core challenge is ensuring that derived directives cannot be
   tampered with or substituted in transit, and that execution endpoints
   can verify the authenticity and authorization boundary of received
   directives.

   Binding and Custody (R1, R2):  Derived directives should be bound to
      the intent context and authorization boundary such that
      unauthorized expansion or substitution is detectable or
      preventable across hops.

   Pre-Execution Constraint Validation (R3):  Even if directives appear
      intact, the receiver should validate that the intended actions
      remain within constraints and invariants before execution.

   Non-Bypass Enforcement (R5):  Execution endpoints should enforce
      checks such that direct calls cannot bypass required validation
      gates.

   Audit Evidence (R6):  Systems should produce evidence linking
      execution decisions to validated directives and constraints.

6.2.2.  Illustrative Procedure

   The following procedure is informative and solution-agnostic.
   Implementations may use various mechanisms (e.g., signed tokens,
   cryptographic binding, attestation) to achieve these objectives.




Jiang, et al.            Expires 5 December 2026               [Page 14]

Internet-Draft               Intent Security                   June 2026


   1.  Directive Derivation and Binding: The IBS derives directives from
       an intent and associates them with the applicable authorization
       boundary.  The IBS generates a cryptographically-protected
       artifact (e.g., signed token, sealed directive) that binds the
       directives to the intent context and authorization scope.

   2.  Integrity Protection for Multi-Hop Propagation: Before forwarding
       directives across trust boundaries, the system attaches integrity
       and binding evidence (e.g., digital signature, MAC, or
       attestation token) sufficient for downstream verification.  This
       evidence includes the authorization boundary, constraint set, and
       issuer identity.

   3.  Reception and Verification: Upon receipt, the execution-side gate
       verifies the integrity and binding evidence of the received
       directives.  This verification confirms: (a) the directives have
       not been tampered with or substituted, (b) the directives
       originate from an authorized IBS, and (c) the authorization
       boundary matches expected scope.

   4.  Constraint Re-Validation: The execution endpoint re-validates the
       directives against local constraints, invariants, and policy
       rules.  This step provides defense-in-depth even if upstream
       validation was bypassed or compromised.

   5.  Enforcement and Audit: If verification or validation fails, the
       system denies or degrades execution under policy and records
       audit evidence.  If successful, the system proceeds with
       execution and logs the binding evidence, execution decision, and
       outcomes for compliance assessment.

   This procedure addresses T1 (Directive Tampering/Substitution) and T3
   (Constraint Bypass) by establishing end-to-end integrity and
   validation across multi-hop processing.

6.3.  Considerations for Scenario 2 (Spoofed/Non-Consensual Origin)

   Scenario 2 highlights that an intent must be controlled at the point
   where it enters the system, not only while it is in transit.  The
   receiver (or the admission point on the originating device) should be
   able to distinguish authorized, consented originators from
   unauthorized or spoofed ones, and to gate high-impact actions on
   explicit consent.

6.3.1.  Overview

   Origin Authentication (R8):  The intent artifact should provide a




Jiang, et al.            Expires 5 December 2026               [Page 15]

Internet-Draft               Intent Security                   June 2026


      verifiable binding to its actual originator's identity, so that a
      fabricated or spoofed origin can be detected before admission.

   Originator-Level Authorization (R9):  Admission should evaluate
      originator attributes (e.g., identity, type, runtime state,
      history) against a permission policy that specifies which
      originators may request which services.  Intents from disallowed
      originators, or from originators in a disallowed state (e.g.,
      background/unattended), should be rejected or escalated.

   Consent for High-Impact Actions (R9):  For high-impact or
      irreversible actions, the system should obtain and verify explicit
      user consent (e.g., step-up confirmation).  Absence or refusal of
      consent should result in rejection.

   Audit Evidence (R6):  Systems should record the verified origin, the
      admission decision, and the consent outcome to support
      investigation of fraudulent or non-consensual origination.

6.3.2.  Illustrative Procedure

   The following procedure is informative and solution-agnostic.
   Implementations may use various mechanisms (e.g., signed origin
   assertions, platform attestation of the originating application,
   policy engines) to achieve these objectives.

   1.  Origin Binding: The intent artifact carries a verifiable binding
       to the actual originator's identity/credential (rather than a
       self-asserted, unverifiable label).

   2.  Origin Verification: The admission point verifies the origin
       binding and rejects intents whose provenance is forged or cannot
       be verified.

   3.  Originator Authorization: The admission point evaluates the
       originator's attributes (identity, type, runtime state, history)
       against the applicable permission policy to determine whether the
       originator is eligible to request the targeted service.

   4.  Consent Gate: For high-impact or irreversible actions, the system
       obtains and verifies explicit user consent and denies the request
       on absence or refusal.

   5.  Enforcement and Audit: If origin verification, authorization, or
       consent fails, the system rejects or escalates the intent under
       policy and records audit evidence.  If all checks pass, the
       intent is admitted and forwarded, and the decision is logged.




Jiang, et al.            Expires 5 December 2026               [Page 16]

Internet-Draft               Intent Security                   June 2026


   This procedure addresses T6 (Origin Spoofing/Forged Provenance) and
   T7 (Unauthorized or Non-Consensual Origination) by establishing
   authenticated, policy-gated, and consent-gated admission before an
   intent enters the processing chain.

6.4.  General Security Considerations

   Beyond the scenario-specific considerations, the following general
   principles apply to intent-based systems:

   *  Trust Boundary Awareness: systems explicitly identify trust
      boundaries and apply appropriate security controls at each
      boundary crossing.

   *  Defense in Depth: validation occur at multiple layers (admission,
      translation, propagation, invocation, execution) to provide
      resilience against bypass or compromise of individual layers.

   *  Least Privilege: derived directives and invocations are scoped to
      the minimum privileges necessary for intent fulfillment.

   *  Fail-Safe Defaults: when validation fails or drift is detected,
      systems default to denying actions rather than permitting
      potentially unsafe operations.

   *  Auditability: all security-relevant decisions and events are
      logged with sufficient context to support post-incident
      investigation and compliance assessment.

7.  IANA Considerations

   This document has no IANA actions.

8.  Normative References

   [RFC2119]  Bradner, S., "Key words for use in RFCs to Indicate
              Requirement Levels", BCP 14, RFC 2119,
              DOI 10.17487/RFC2119, March 1997,
              <https://www.rfc-editor.org/info/rfc2119>.

   [RFC7991]  Hoffman, P., "The "xml2rfc" Version 3 Vocabulary",
              RFC 7991, DOI 10.17487/RFC7991, December 2016,
              <https://www.rfc-editor.org/info/rfc7991>.

   [RFC8174]  Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
              2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
              May 2017, <https://www.rfc-editor.org/info/rfc8174>.




Jiang, et al.            Expires 5 December 2026               [Page 17]

Internet-Draft               Intent Security                   June 2026


9.  Informative References

   [I-D.goswami-agentic-jwt]
              Goswami, A., "Secure Intent Protocol: JWT Compatible
              Agentic Identity and Workflow Management", Work in
              Progress, Internet-Draft, draft-goswami-agentic-jwt-00, 1
              January 2026, <https://datatracker.ietf.org/doc/html/
              draft-goswami-agentic-jwt-00>.

   [I-D.ietf-oauth-transaction-tokens]
              Tulshibagwale, A., Fletcher, G., and P. Kasselman,
              "Transaction Tokens", Work in Progress, Internet-Draft,
              draft-ietf-oauth-transaction-tokens-08, 2 March 2026,
              <https://datatracker.ietf.org/doc/html/draft-ietf-oauth-
              transaction-tokens-08>.

   [I-D.irtf-nmrg-ibn-usecases]
              Yao, K., Chen, D., Jeong, J. P., Wu, Q., Yang, C.,
              Contreras, L. M., and G. Fioccola, "Use Cases and
              Practices for Intent-Based Networking", Work in Progress,
              Internet-Draft, draft-irtf-nmrg-ibn-usecases-03, 15 March
              2026, <https://datatracker.ietf.org/doc/html/draft-irtf-
              nmrg-ibn-usecases-03>.

   [I-D.liu-oauth-a2a-profile]
              Liu, P. C. and N. Yuan, "Agent-to-Agent (A2A) Profile for
              OAuth Transaction Tokens", Work in Progress, Internet-
              Draft, draft-liu-oauth-a2a-profile-00, 20 October 2025,
              <https://datatracker.ietf.org/doc/html/draft-liu-oauth-
              a2a-profile-00>.

   [I-D.ni-a2a-ai-agent-security-requirements]
              Yuan, N., Liu, P. C., Gao, Q., and Z. Li, "Security
              Requirements for AI Agents", Work in Progress, Internet-
              Draft, draft-ni-a2a-ai-agent-security-requirements-01, 28
              February 2026, <https://datatracker.ietf.org/doc/html/
              draft-ni-a2a-ai-agent-security-requirements-01>.

   [I-D.oauth-transaction-tokens-for-agents]
              Raut, A., "Transaction Tokens For Agents", Work in
              Progress, Internet-Draft, draft-oauth-transaction-tokens-
              for-agents-06, 11 April 2026,
              <https://datatracker.ietf.org/doc/html/draft-oauth-
              transaction-tokens-for-agents-06>.







Jiang, et al.            Expires 5 December 2026               [Page 18]

Internet-Draft               Intent Security                   June 2026


   [MS-AF-SEQ]
              Microsoft, "Microsoft Agent Framework Workflows
              Orchestrations - Sequential", 2026,
              <https://learn.microsoft.com/en-us/agent-
              framework/workflows/orchestrations/sequential>.

   [RFC9315]  Clemm, A., Ciavaglia, L., Granville, L. Z., and J.
              Tantsura, "Intent-Based Networking - Concepts and
              Definitions", RFC 9315, DOI 10.17487/RFC9315, October
              2022, <https://www.rfc-editor.org/info/rfc9315>.

   [RFC9316]  Li, C., Havel, O., Olariu, A., Martinez-Julia, P., Nobre,
              J., and D. Lopez, "Intent Classification", RFC 9316,
              DOI 10.17487/RFC9316, October 2022,
              <https://www.rfc-editor.org/info/rfc9316>.

Acknowledgments

   TODO

Authors' Addresses

   Yuning Jiang
   Huawei
   Email: jiangyuning2@h-partners.com


   Lun Li
   Huawei
   Email: lilun20@huawei.com


   Yurong Song
   Huawei
   Email: songyurong1@huawei.com


   Faye Liu
   Huawei
   Email: liufei19@huawei.com











Jiang, et al.            Expires 5 December 2026               [Page 19]
