Re: [CG Report v1.6.2 draft] Vouch Protocol: Continuous State Verifiability for Autonomous AI Agents

On Tue, 2 Jun 2026 at 14:36, Ramprasad G <ram@vouch-protocol.com> wrote:

> Hey Amir, you've read it correctly, and the honest answer is: yes, these
> primitives are general-purpose, and no, there's no technical property that
> restricts them to AI agents.
>
> Delegation, heartbeat renewal, and state verifiability would all work for
> human actors, service accounts, and non-AI workloads. Nothing in the
> cryptography or the mechanisms lock them to AI. The scope is AI agents by
> choice and not by technical necessity, for two reasons:
>
>    1. The defaults are tuned to how AI agents fail. Heartbeat lifetimes
>    are short because the AI threats are fast like the prompt injection, a
>    swapped model or a behavioral drift mid-session. For a steady service
>    account that renewal cadence will be overhead. Same mechanism, different
>    setting.
>    2. A few mechanisms are AI-specific in motivation: keeping keys out of
>    the model's context window, binding identity to model weights to catch a
>    swap, canary checks to tell a dead or hijacked agent from an idle one -
>    these are AI-relevant, but they sit alongside the general primitives
>    instead of restricting them.
>
>
>    - On your middle question, should the scope reflect this: yes, and
>    right now it doesn't say so clearly. I'll add a short paragraph to the
>    scope section stating that the AI-agent scope is a deliberate threat-model
>    choice rather than a technical boundary, and that the underlying primitives
>    generalize.
>
> >Hi Ramprasad, Thanks for the detailed clarification — this makes things
much clearer.

>
>    - Applying them to humans or service accounts would require a separate
>    profile with re-tuned defaults, which is a reasonable future work rather
>    than something we should consider adding to the v1.0 scope, IMHO. If a
>    non-AI profile is something you or your team would find useful, I'm happy
>    to figure out the right home for it, whether that's a separate spec here in
>    the CCG or somewhere else.
>
> > That distinction answers my question. It clarifies that the same
primitives can apply across humans, service accounts, and non-AI workloads,
but would simply require different operational profiles and defaults.
> Thanks again for taking the time to explain

>Amir Hameed

>
> On Mon, 1 Jun 2026 at 10:38, Amir Hameed <amsaalegal@gmail.com> wrote:
>
>> Hi Ramprasad,
>>
>> The delegation, heartbeat, and state verifiability primitives in this
>> specification are general-purpose authorization and session-management
>> mechanisms. Do you anticipate these being applicable to human actors,
>> service accounts, and non-AI workloads? If so, should the specification's
>> scope reflect that? If not, what technical property restricts these
>> mechanisms to AI agents specifically.
>>
>> Regards
>> Amir Hameed Mir
>>
>>
>> On Sun, 31 May 2026 at 16:24, Alan Karp <alanhkarp@gmail.com> wrote:
>>
>>> Unfortunately, this specification makes the common error of limiting the
>>> delegation depth.  The result is a system that is harder to use and less
>>> secure.  One way to think of the issue is to recognize that blocking
>>> delegation makes attenuation difficult.
>>>
>>> Say that agent A is at the limit of the delegation chain, has query and
>>> update permissions on some object, and wants to use another agent B that
>>> only needs query permission.  Since agent A can't delegate, it can
>>> effectively share its credentials by blindly proxying whatever requests it
>>> receives from agent B.
>>>
>>> --------------
>>> Alan Karp
>>>
>>>
>>> On Sun, May 31, 2026 at 2:43 PM Ramprasad G <ram@vouch-protocol.com>
>>> wrote:
>>>
>>>> Hello Credentials Community Group,
>>>>
>>>> I would like to draw the group's attention to a Community Group Report
>>>> draft for Vouch Protocol, a continuous-state-verifiability layer for
>>>> autonomous AI agents built entirely on existing W3C primitives. The work
>>>> item has been filed at:
>>>>
>>>> https://github.com/w3c-ccg/community/issues/259
>>>>
>>>> The draft is at v1.6.2. It incorporates one round of pre-list review
>>>> feedback (folded into v1.6.1) along with subsequent editor polish. It is
>>>> co-authored & co-sponsored by Manu Sporny (Digital Bazaar).
>>>>
>>>> *Reading surfaces:*
>>>>
>>>> Repository: https://github.com/vouch-protocol/vouch
>>>> Report draft (Markdown):
>>>> https://github.com/vouch-protocol/vouch/blob/main/docs/specs/w3c-cg-report.md
>>>> Tagged release v1.6.2:
>>>> https://github.com/vouch-protocol/vouch/releases/tag/v1.6.2
>>>> 1-page executive summary:
>>>> https://github.com/vouch-protocol/vouch/blob/main/docs/specs/cg-report-executive-summary.md
>>>> Google Doc (comments open):
>>>> https://docs.google.com/document/d/1KYmLoY9XIuVFIW2HvhtLCW551CIE_SxZ/edit?usp=sharing
>>>>
>>>> *WHAT IT SPECIFIES*
>>>>
>>>>    - A W3C VC Data Model 2.0 credential profile for autonomous agent
>>>>    intent attestation, signed with W3C Data Integrity (eddsa-jcs-2022).
>>>>    - DID-based agent identity (did:web and did:key as primary methods).
>>>>    - The Identity Sidecar pattern, which physically isolates private
>>>>    keys from the LLM context window.
>>>>    - Resource-bound delegation chains (Section 9), with explicit
>>>>    resource URI binding per link to prevent confused-deputy attacks.
>>>>    - The Heartbeat Protocol (Section 11), inverting the trust model
>>>>    from "Trusted until Revoked" to "Untrusted until Renewed."
>>>>    - An optional dual-proof post-quantum profile in which a credential
>>>>    carries two independent W3C Data Integrity proofs (eddsa-jcs-2022 and
>>>>    mldsa44-jcs-2026) on the same RFC 8785 JCS-canonicalized payload bytes.
>>>>    This aligns with the Digital Bazaar mldsa44-rdfc-2024-cryptosuite family.
>>>>    - An optional Algorithm Quorum Verification mode (Section 13.6)
>>>>    generalizing the dual-proof pattern to M-of-N cryptosuite diversity.
>>>>
>>>> *WHAT IT DOES NOT DO*
>>>>
>>>>    - It does not introduce new cryptographic primitives where existing
>>>>    W3C standards suffice.
>>>>    - It does not replace identity or authorization specifications. It
>>>>    composes with them. Appendix A details the relationship to W3C VC, W3C DI,
>>>>    W3C DIDs, ZCAP-LD, OAuth 2.1, BitstringStatusList, and C2PA.
>>>>    - It does not address developer-time tooling for AI coding
>>>>    assistants. A companion series of disclosures (PAD-048 through PAD-055)
>>>>    covers that adjacent space and is referenced informatively in Appendix A.1.
>>>>
>>>> *REFERENCE IMPLEMENTATIONS*
>>>>
>>>> Three implementations, all in the same repository, produce
>>>> byte-identical credentials given the same input:
>>>>
>>>>    - Python (vouch/)
>>>>    - TypeScript (packages/sdk-ts/)
>>>>    - Go (go-sidecar/)
>>>>
>>>> Cross-implementation interop test vectors are in tests/interop/.
>>>>
>>>> *PRIOR ART*
>>>>
>>>> A 60-PAD defensive disclosure portfolio (CC0) is published in
>>>> docs/disclosures/. Most are informative; selected disclosures are cited at
>>>> architectural decision points in the Report:
>>>>
>>>>    - PAD-039: cross-implementation determinism
>>>>    - PAD-040: same-canonical-bytes property under the dual-proof
>>>>    carrier
>>>>    - PAD-041: Multikey algorithm-agnostic verification
>>>>    - PAD-043: cryptographic weight binding
>>>>    - PAD-045: RAG-anchored reasoning
>>>>    - PAD-046: algorithm quorum
>>>>    - PAD-047: verifiable-delay-function rate-limiting
>>>>    - PAD-059: Vouch-Amnesia attestation bridge
>>>>    - PAD-060: single-use audited override of egress block
>>>>
>>>> *WHAT I AM ASKING FROM THE GROUP*
>>>>
>>>>    1. Review. Comments on architecture, terminology, conformance
>>>>    language, security and privacy considerations are very welcome. The Google
>>>>    Doc above is open in commenter mode if you prefer inline comments; the
>>>>    GitHub repo accepts issues and pull requests.
>>>>    2. Implementer interest. If your organization is working on agent
>>>>    identity, agent authorization, or behavioral attestation, I would value an
>>>>    indication of interest (privately or on-list).
>>>>    3. CCG agenda time. I would like to present the architecture at an
>>>>    upcoming CCG call.  A 20-25 minute walkthrough plus discussion fits the
>>>>    standard agenda slot.
>>>>
>>>> *STATUS*
>>>>
>>>> Apache 2.0 licensed. Open to incorporation into the CCG's incubation
>>>> pipeline, including transition discussion when the group judges traction
>>>> supports it.
>>>>
>>>> Thanks for the consideration. Replies to-list or off-list are welcome.
>>>>
>>>> Best regards,
>>>> Ramprasad Gaddam
>>>> Editor, Vouch Protocol
>>>> ram@vouch-protocol.com
>>>> https://vouch-protocol.com
>>>> https://github.com/vouch-protocol/vouch
>>>>
>>>

Received on Tuesday, 9 June 2026 14:10:28 UTC