High-Assurance Agent Control Envelope
draft-watts-high-assurance-agent-control-envelope-00

Internet Engineering Task Force                              D. O. Watts
Internet-Draft                                      GoodShyt Group Inc.
Intended status: Informational                           14 October 2026
Expires: 14 April 2027

                 High-Assurance Agent Control Envelope
          draft-watts-high-assurance-agent-control-envelope-00

Abstract

   Agentic systems can authenticate successfully, hold a valid
   authorization object, and still be unsafe to execute because required
   evidence is missing, the software has not reached a required assurance
   stage, the authority epoch is stale, a prior revocation is unresolved,
   or a human-approval requirement is unsatisfied.  This document defines
   the High-Assurance Agent Control Envelope (HAACE), a protocol-neutral
   profile that binds an exact agent action to identity status,
   authorization state, policy, assurance stage, evidence state, authority
   epoch, revocation state, oversight requirements, and an action-time
   decision.  HAACE requires fail-closed treatment of missing or
   indeterminate prerequisites, separates authorization from execution,
   and produces non-bearer decision and execution receipts.

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), its areas, and its working groups.  Note that other groups
   may also distribute working documents as Internet-Drafts.

   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."

   The list of current Internet-Drafts can be accessed at
   https://www.ietf.org/1id-abstracts.html

   The list of Internet-Draft Shadow Directories can be accessed at
   https://www.ietf.org/shadow.html

   This Internet-Draft will expire on 14 April 2027.

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
   Simplified BSD License text as described in Section 4.e of the Trust
   Legal Provisions and are provided without warranty as described in the
   Simplified BSD License.

1. Introduction

   High-consequence agent deployments combine workload identity,
   delegated authorization, evidence or attestation, policy evaluation,
   revocation, software-assurance evidence, human oversight, and execution
   logging.  A recurring systems failure occurs when one valid artifact is
   silently treated as sufficient for a stronger conclusion.

   HAACE defines a narrow execution-gate profile.  A relying party declares
   an Assurance Requirement Profile (ARP).  An agent or intermediary
   presents an Action Request Record (ARR).  An independent Action Control
   Point (ACP) evaluates it and emits a non-bearer Action Decision Receipt
   (ADR).  Execution is recorded separately in an Action Execution Receipt
   (AER).

2. Core Requirements

   Identity is not authorization.  Evidence is not authority.
   Authorization is not execution.  Unknown is not allow.  Revocation
   request is not closure.  Software assurance does not self-promote.
   Agent self-approval is invalid when independent approval is required.

3. Action-Time Decision

   A conforming ACP validates ARR syntax and action binding, identity,
   independent authorization, current authority epoch, required revocation
   closure state, software-assurance stage, required evidence, policy
   digest, independent human approval when required, and the exact action
   presented at the effect boundary.

   ALLOW is returned only when every required predicate is satisfied.
   Known failure returns DENY.  A required predicate that cannot be
   established returns INDETERMINATE.  INDETERMINATE MUST NOT be treated as
   ALLOW.

4. Conformance

   A conforming implementation MUST reproduce the companion vector suite.
   It is non-conformant if valid identity alone yields ALLOW, if UNKNOWN
   evidence yields ALLOW, if a stale authority epoch is accepted, if local
   conformance satisfies an independent-reproduction requirement, or if an
   agent satisfies an independent approval requirement with its own
   approval.

5. Security Considerations

   Threats include action substitution, stale-epoch replay, self-issued
   authorization, evidence substitution, policy downgrade, confused-deputy
   behavior, delegation laundering, forged or replayed approval, queued
   effects after revocation, and fail-open handling of ACP outages.

   The ACP and effect boundary SHOULD be controlled independently of the
   agent.  Receipts preserve what was evaluated; they do not prove that
   external evidence was true, that a model was safe, or that a deployment
   is secure.

6. IANA Considerations

   This document has no IANA actions.

Author's Address

   Deonte O'dell Watts
   GoodShyt Group Inc.
   San Francisco, CA
   United States of America
   Email: deonte@goodshyt.fun
   ORCID: https://orcid.org/0009-0005-8586-3650