[OAUTH-WG] Re: [agent2agent] Re: Re: Review of draft-rosenberg-oauth-aauth-00

[Aaron Parecki <[e-mail]>]

If we think of an agent as just a piece of software with a custom
non-browser UI, this problem sounds the same as how people want to provide
native login interfaces in mobile apps. If the account being accessed is
first-party to the agent (like the user calling a support center to access
the user's data that lives at that same company) then that's what we
created the "OAuth 2.0 for First Party Apps" draft for:

https://datatracker.ietf.org/doc/draft-ietf-oauth-first-party-apps/

But like Dick said, if this is third party access, you would never want the
user to give PII or credentials to the agent software, and is the entire
reason OAuth was created in the first place. In any case, I would recommend
rewriting this as a profile of the First Party Apps draft.

I also noticed at one point in the draft you say that the AS fetches scope
descriptions from the RS. We recently published an RFC, Protected Resource
Metadata RFC9728, which provides a way for an RS to publish metadata about
the resources. I would recommend using and referencing this mechanism
instead of creating the bespoke ".well-known/aauth.json" endpoint.

Aaron

On Fri, Jul 25, 2025 at 3:53 AM Dick Hardt <[e-mail]> wrote:

> In the doc,
> https://datatracker.ietf.org/doc/html/draft-rosenberg-oauth-aauth#name-basic-token-flow
>
>
> The sharing of the personal information is being used as a form of not
> only identifying the user, but verifying it is the user using KBA
> (Knowledge Based Authentication) mimicking what happens in a voice
> interaction with a human today. The premise being that only the user would
> have the correct answers to the questions of name, SSN, DOB etc. This is an
> authentication process.
>
> This is an anti-pattern, and is similar to why OAuth was created. Before
> OAuth, APIs could be called if the client had a valid username and
> password. Apps that wanted to get people's contacts programmatically would
> ask for their username and password, and then would make API calls on the
> user's behalf. The OAuth protocol enabled an app to request access to a
> resource by directing the user to an authorization server which would
> authenticate the user, present the request to the user, and if the user
> consents, provide access to the user's resources.
>
> The pattern of the agent getting the PII to authenticate the user is
> similar to the anti-pattern of asking for the username and password.
>
> /Dick
>
>
>
> On Fri, Jul 25, 2025 at 8:25 AM Leonard Rosenthol <[e-mail]>
> wrote:
>
>> You’ve have to forgive me, Dick (and others), but I am coming to this
>> discussion not as an OAuth person – so I had to look up all the acronyms
>> that are freely flowing.  But I think I am caught up – at least for now
>> 😉.
>>
>>
>>
>> > Having an agent obtain information about the user to authenticate to
>> the AS smells like a bad idea
>>
>> >
>>
>> I would actually state it more as the “user provides information to the
>> agent”.  For example, if the agent’s protocol declaration defines that it
>> requires some form of information from a user – be it auth token, VC, etc.
>> – how is that any different from how REST APIs work today, where API
>> declarations frequently (almost always!) include such info??   That
>> information passes across the protocol (e.g., HTTP today), is picked up by
>> some system on the other side, checked for authorization and/or
>> entitlement, and if valid “allowed to pass on” to the actual process.  I
>> see agents working the same way.
>>
>>
>>
>> Leonard
>>
>>
>>
>>
>>
>> *From: *Dick Hardt <[e-mail]>
>> *Date: *Thursday, July 24, 2025 at 10:10 AM
>> *To: *Leonard Rosenthol <[e-mail]>
>> *Cc: *Nick Watson <[e-mail]>, Lombardo, Jeff <
>> [e-mail]>, Patrick White <[e-mail]>,
>> [e-mail] <[e-mail]>, [e-mail] <
>> [e-mail]>
>> *Subject: *Re: [OAUTH-WG] Re: [agent2agent] Re: Re: Review of
>> draft-rosenberg-oauth-aauth-00
>>
>> *EXTERNAL: Use caution when clicking on links or opening attachments.*
>>
>>
>>
>> Having an agent obtain information about the user to authenticate to the
>> AS smells like a bad idea and a conflation of concerns, breaking the
>> security principle of separation of concerns.
>>
>> How an OAuth flow happens where the user is authenticating to the AS over
>> non web communication channels such as IVR does sounds like work for OAuth,
>> not unlike the the Device Authorization Grant (RFC 86280
>> https://datatracker.ietf.org/doc/html/rfc8628
>>
>>
>>
>> /Dick
>>
>>
>>
>> On Thu, Jul 24, 2025 at 10:55 AM Leonard Rosenthol <lrosenth=
>> [e-mail]> wrote:
>>
>> Agreed that PII is not a good thing to pass around – however, that
>> doesn’t necessarily preclude passing around “human and organizational
>> identity” in a format that can be used to determine authentication and/or
>> authorization. This is important in uses cases where the “endpoint” (tool,
>> agent, service, etc.) is basing that decision on the human/org and not on
>> the bot itself.
>>
>>
>>
>> Leonard
>>
>>
>>
>> *From: *Nick Watson <nwatson=[e-mail]>
>> *Date: *Thursday, July 24, 2025 at 1:49 PM
>> *To: *Lombardo, Jeff <jeffsec=[e-mail]>
>> *Cc: *Patrick White <[e-mail]>, [e-mail] <
>> [e-mail]>, [e-mail] <[e-mail]>
>> *Subject: *[agent2agent] Re: [OAUTH-WG] Re: Review of
>> draft-rosenberg-oauth-aauth-00
>>
>> *EXTERNAL: Use caution when clicking on links or opening attachments.*
>>
>>
>>
>> RFC 9728 already provides a lot of natural language descriptions of
>> resource APIs - what would scope descriptions add over that?
>>
>>
>>
>> I agree with Jeff that CIBA + RFC 9728 seems like it would address this,
>> and we should avoid agents' passing PII around as an authn mechanism.
>>
>>
>>
>> On Tue, Jul 22, 2025 at 7:52 PM Lombardo, Jeff <jeffsec=
>> [e-mail]> wrote:
>>
>> The scopes to be defined that still can be an AI agent role based on the
>> task at stake. There is no issue with that cause the scopes have to be
>> provided on the Authorization request to the AS.
>>
>> My problem is the authentication flow going through the Agent and being
>> based on PII. I would prefer an Out-of-Band Authentication if possible, and
>> if not at least a dynamic authentication.
>>
>> In this case, event a battlecard authentication would be better than a
>> PII “authentication”, like the AS asking through the Agent give A-9, D-16,
>> and E-4 for the user to retrieve the corresponding answer from its secret
>> sheet.
>>
>>
>>
>> The flow for OOB [which is exactly CIBA] would like in a picture:
>>
>>
>>
>>
>>
>> Here is a Mermaid link to the live Editor:
>> https://mermaid.live/edit#pako:eNqlVu9v2jAQ_VdO_rJOY1XapYVEVaeO7kO_TAj2Q5qQKpMcwapjZ45Txqr-7zs7YYUQYNP6qYnv3r17fnfkiSU6RRazEn9UqBK8FTwzPJ8qoL8RN1YkouDKwo0UCe55_aqEm8ouUNFrboVWcIuPneGTqii0obQ7uMkovo6Y6Z8eQBvxq86foHlEU5-2MYZSUCaMMROlNXX8R5UWWqzxdkhuYR-O_awfsB1DT7utjLHUlUlwi6uX4-rq7dvr64PKxHUkiBKM7wMNpkDHFAupD4G5Nv6RF4VssusibRHreodkievEFuWGZ6c4cTvYUS2MtphYYjpbHbiwTxQF2uW0mcY7bxxswgs-k5Qyhw0Vidqb3fyr0efJJ1BVPkMjVHZ9vKJInfpzQYe5yBYWZk5hIx6pjbnROeRoecotr5-c4gmXsgdSPCCsdOUfKao-501xuIMHpZfdN-K4-yZi-IYy0ZRsNZCcdMVSKFdBEcCCP_oKZoPk-6MS3AHPN8fxUPEFt02tVHtDuX6sTvnqb-osnc-JuEGFS8hXZAAsEyMKf-V0XUKVFfVz_BJuveBQJrrAshbSuI1T2uO5Q4OcTjmMRbJo2W68CdIpxB53N6Dbxw0lWAq7gMTP071Ie0BgSBNFhqkbIG_oTKj7BUHBiZfwdSNnZ7lufW8SZyCJaYa5m4QTTsn3xIFqNnBS6wK-kDMk8E6mbnq0Kikd05d91iXE9l6LYaTJ1NsvvUHmUi8JMy8kvmwcXC_A_f0dWXcTggClncebEy9ySrMnZAknXtjei-ivN-y5D3XD6COJvMTNMGz5-9g63sgk2d3Ir_6NQmPF9X3QcnKj4_vywv5p7d-IDWs4h-XW0HqC9gAe5LlnFL5yKdLdYTg6Wv_lqO247gEZo62MakIneIBK67eKuKCh0rQmR3cwdLp5t203-AG5oYXj4VmP5WhyLlL6FnpyhaaMZMxxymL6N8U5r6Sdsql6plCaRT1ZqYTF1lTYY0ZX2YLFcy5LeqoKp2bzIfXnLX0zfNc6X6dkxpVq0mk20Ax1pSyLw7NB4KNZ_MR-svjsXXgaBYP-xXkYnoXB5flFj61YPIhOg4soiPrnURC8i4LL5x775fGD00E_jKKoH52F4eDysh8-_wa4dWW_
>>
>>
>>
>> Here is the Mermaid for those who could not see the picture nor use the
>> link:
>>
>> sequenceDiagram
>>
>>     Participant Alice
>>
>>     Participant Alice's Authentication Device
>>
>>     Participant Support AI Agent
>>
>>     box Authorization Server
>>
>>         Participant Client Registration Endpoint
>>
>>         Participant Authorization Endpoint
>>
>>         Participant Token Endpoint
>>
>>     End
>>
>>     Participant Resource Server
>>
>>     Alice<<-->>Alice's Authentication Device: Alice is registered on the
>> device for the application
>>
>>     Support AI Agent<<-->>Client Registration Endpoint:
>>
>>     Resource Server<<-->>Authorization Endpoint: Resource Server is
>> protected by Authorization Server
>>
>>     Note over Support AI Agent: Support AI Agent is capable of
>>
>>     Alice->>+Support AI Agent: <PTSN numbering>
>>
>>     Note over Support AI Agent: identifier might be derived from metadata
>> from the call, like you call me from a number I know
>>
>>     Support AI Agent->>+Alice: Welcome to our online can I have your
>> identifier?
>>
>>     Alice->>+Support AI Agent: I am Alice
>>
>>     Support AI Agent->>+Alice: What can I do for you today?
>>
>>     Alice->>+Support AI Agent: I want to renew my prescription of insulin
>>
>>     Note over Support AI Agent: Derive scopes from request
>>
>>     Note over Support AI Agent: Create a Rich Authorization Request
>>
>>     Support AI Agent->>+Authorization Endpoint: Create Authorization
>> request with client_id, generated scopes, login_hint *(*Alice*)*
>>
>>     Authorization Endpoint->>+Support AI Agent: Acknowledgement *(*
>> auth_req_id*)*
>>
>>     loop Until authorization request is consented
>>
>>         Support AI Agent->>+Token Endpoint: Poll Token Endpoint for flow
>> completion
>>
>>     end
>>
>>     Authorization Endpoint->>+Alice's Authentication Device: Send
>> notification with details *(*scope*,* client_id*)*
>>
>>     Alice's Authentication Device->>+Alice: Please Authenticate
>>
>>     Alice->>+Alice's Authentication Device: Authenticate locally
>>
>>     Alice's Authentication Device->>+Alice: Request consenting to scope
>> for client_id
>>
>>     Alice->>+Alice's Authentication Device: Consent to all scopes for
>> client_id
>>
>>     Alice's Authentication Device->>+Authorization Endpoint: Validate
>> Authorization Request
>>
>>     Support AI Agent->>+Token Endpoint: Poll Token Endpoint for flow
>> completion
>>
>>     Token Endpoint->>+Support AI Agent: Return Token Set
>>
>>     Support AI Agent->>+Resource Server: Perform API Call with
>> Authorization Bearer Token
>>
>>
>>
>>
>>
>> *Jean-François “Jeff” Lombardo* | Amazon Web Services
>>
>>
>>
>> Architecte Principal de Solutions, Spécialiste de Sécurité
>> Principal Solution Architect, Security Specialist
>> Montréal, Canada
>>
>> ( [phone] <(514)%20778-5565>
>>
>> *Commentaires à propos de notre échange? **Exprimez-vous **ici*
>> <https://urldefense.com/v3/__https:/feedback.aws.amazon.com/?ea=jeffsec&fn=Jean*20Francois&ln=Lombardo__;JQ!!Pe07N362zA!0k9CkAV8Djpw_8EfIAKrbhP3TQrJr0oMnznlUgBJ3V3NoEk6hihx7dNHnQuejn6SSH2CP8Iow3G-tTzppHeg$>
>> *.*
>>
>>
>>
>> *Thoughts on our interaction? Provide feedback **here*
>> <https://urldefense.com/v3/__https:/feedback.aws.amazon.com/?ea=jeffsec&fn=Jean*20Francois&ln=Lombardo__;JQ!!Pe07N362zA!0k9CkAV8Djpw_8EfIAKrbhP3TQrJr0oMnznlUgBJ3V3NoEk6hihx7dNHnQuejn6SSH2CP8Iow3G-tTzppHeg$>
>> *.*
>>
>>
>>
>> *From:* Patrick White <[e-mail]>
>> *Sent:* July 22, 2025 7:09 PM
>> *To:* Lombardo, Jeff <jeffsec=[e-mail]>
>> *Cc:* [e-mail]; [e-mail]; Lombardo, Jeff <
>> [e-mail]>
>> *Subject:* RE: [EXT] [agent2agent] Review of
>> draft-rosenberg-oauth-aauth-00
>>
>>
>>
>> *CAUTION*: This email originated from outside of the organization. Do
>> not click links or open attachments unless you can confirm the sender and
>> know the content is safe.
>>
>>
>>
>> *AVERTISSEMENT*: Ce courrier électronique provient d’un expéditeur
>> externe. Ne cliquez sur aucun lien et n’ouvrez aucune pièce jointe si vous
>> ne pouvez pas confirmer l’identité de l’expéditeur et si vous n’êtes pas
>> certain que le contenu ne présente aucun risque.
>>
>>
>>
>> Hey Jeff, someone pointed out the OIDC HITL spec here, there's absolutely
>> some overlap, but one of the big things that missing is natural language
>> descriptions of scopes (well, and also that it's not an oauth flow, but I'm
>> not sure how much that matters). At a high level, a really important part
>> of the AAuth stuff I proposed is tooling to allow the LLMs to actually
>> discover what scopes they need. You could do it as part of a dance (I make
>> a request, get the scope demand, then flow that through), but I was trying
>> for a model where the models themselves would craft the scope request based
>> on the well known scope definition document. Maybe I missed something
>> around natural language scope definitions in the OIDC spec, though
>>
>>
>>
>> On Tue, Jul 22, 2025 at 7:01 PM Lombardo, Jeff <jeffsec=
>> [e-mail]> wrote:
>>
>> [+ OAuth WG as this touches their core specs]
>>
>> Thanks Jonathan and Pat for putting that forward.
>>
>>
>>
>> Here are some comments / questions / suggestions:
>>
>>
>>
>>    - The use cases are very clear and are very good thought experiments
>>    to rubberstamp / challenge the models of delegated authorization we have
>>    build so far
>>
>>
>>
>>    - Unfortunately, the proposition seems to point towards a glorified
>>    Knowledge Based Authentication (KBA) as it will use PII validation to
>>    authenticate  as a form of “password” in a glorified Resource Owner
>>    Password Grant type flow as the request is only dealing with the Token
>>    endpoint… the problems are:
>>
>>
>>    - Knowledge Based Authentication is highly insecure cause anyone that
>>       knowing this static information can impersonate someone else
>>       - It is based on PII which are Identifiers and not Authentication
>>       factors, therefore can only allow to identify someone. On top of that, PII
>>       leak constantly and are no longer considered secure
>>
>>
>>    - Also what would prevent the AI agent to fetch those information
>>          from the internet on behalf od the user as you noted into section *3.1.
>>          <https://datatracker.ietf.org/doc/html/draft-rosenberg-oauth-aauth#section-3.1>Basic
>>          Token Flow
>>          <https://datatracker.ietf.org/doc/html/draft-rosenberg-oauth-aauth#name-basic-token-flow>
>>          *
>>
>>
>>
>> *By altering the required set of PII elements, designers of AI Agents can
>> control the likelihood of hallucination (or malicious prompt injection
>> attacks) resulting in a token issuance for the wrong user. The selection of
>> the information becomes even more important for AI Agents. Usage of PII
>> elements which are known publically becomes a real risk. If these are
>> included in the training data for the LLM, it is indeed possible (and
>> likely) that the LLM would hallucinate it. For example, if the patient in
>> question is a famous actor, and their date of birth is public record in the
>> IMDB, it is likely that the LLM would hallucinate the date of birth.
>> Consequently, the Authorization Servers can be configured to require
>> sufficient number and complexity of PII in order to provide the desired
>> level of security.*
>>
>>
>>
>>    - This hardly advocates for the PII to not flow through the AI cause
>>          thinking the AS will be smarter than the AI* by configured to
>>          require sufficient number and complexity of PII in order to provide the
>>          desired level of security *is a false expectation
>>
>>
>>
>>    - Resource Owner Password Grant flow is obsolete and deprecated see
>>       https://www.rfc-editor.org/rfc/rfc9700.html#name-resource-owner-password-cre
>>
>>
>>
>>    - Without consideration about the above points we are exchanging an
>>    AI Agent risk by a very secure AI Agent that could on very misleading /
>>    spoofable / malicious crafted information. I don’t think this better.
>>
>>
>>
>>    - Have you evaluated Client Initiated Backchannel Authorization grant
>>    type flow [
>>    https://openid.net/specs/openid-client-initiated-backchannel-authentication-core-1_0.html
>>    ] before designing this new specification?
>>
>>
>>    - This would perfectly fit into the following specification statement
>>       in section *3.2.
>>       <https://datatracker.ietf.org/doc/html/draft-rosenberg-oauth-aauth#section-3.2>Human-In-The-Loop
>>       <https://datatracker.ietf.org/doc/html/draft-rosenberg-oauth-aauth#name-human-in-the-loop>
>>       *
>>
>>       *Initiate the consent review flow with the user. This spec does
>>       not specify how this occurs, it could be through an app, a chat client, or
>>       some other mechanism.*
>>
>>
>>
>> My 0.02 Canadian Dollars
>>
>>
>>
>> Jeff
>>
>>
>>
>> *Jean-François “Jeff” Lombardo* | Amazon Web Services
>>
>>
>>
>> Architecte Principal de Solutions, Spécialiste de Sécurité
>> Principal Solution Architect, Security Specialist
>> Montréal, Canada
>>
>> ( [phone]
>>
>> *Commentaires à propos de notre échange? Exprimez-vous **ici*
>> <https://urldefense.com/v3/__https:/feedback.aws.amazon.com/?ea=jeffsec&fn=Jean*20Francois&ln=Lombardo__;JQ!!Pe07N362zA!0k9CkAV8Djpw_8EfIAKrbhP3TQrJr0oMnznlUgBJ3V3NoEk6hihx7dNHnQuejn6SSH2CP8Iow3G-tTzppHeg$>
>> *.*
>>
>>
>>
>> *Thoughts on our interaction? Provide feedback **here*
>> <https://urldefense.com/v3/__https:/feedback.aws.amazon.com/?ea=jeffsec&fn=Jean*20Francois&ln=Lombardo__;JQ!!Pe07N362zA!0k9CkAV8Djpw_8EfIAKrbhP3TQrJr0oMnznlUgBJ3V3NoEk6hihx7dNHnQuejn6SSH2CP8Iow3G-tTzppHeg$>
>> *.*
>>
>>
>>
>> _______________________________________________
>> agent2agent mailing list -- [e-mail]
>> To unsubscribe send an email to [e-mail]
>>
>> _______________________________________________
>> OAuth mailing list -- [e-mail]
>> To unsubscribe send an email to [e-mail]
>>
>> _______________________________________________
>> OAuth mailing list -- [e-mail]
>> To unsubscribe send an email to [e-mail]
>>
>> _______________________________________________
> OAuth mailing list -- [e-mail]
> To unsubscribe send an email to [e-mail]
>