]> Helixar Limited

protocol@helixar.ai https://helixar.ai

Security agentic AI delegation provenance Ed25519 token chain of custody human authorization Agentic AI systems operate on behalf of human principals, often delegating tasks through multi-step chains of AI agents. There is currently no standard mechanism to record who authorized an agent to act, under what scope, and through what chain of delegation, in a way that can be verified offline, without a central registry, and without third-party trust anchors. This document specifies the Human Delegation Provenance Protocol (HDP) version 0.1, a lightweight token-based protocol that captures, structures, cryptographically signs, and verifies human delegation context in agentic AI systems. An HDP token binds a human authorization event to a session, records each agent's delegation action as a signed hop in an append-only chain, and enables any participant to verify the full provenance record using only the issuer's Ed25519 public key and the current session identifier. Verification is fully offline. No registry lookup, no network call, and no third-party trust anchor is required. HDP's distinguishing contribution is a signed, tamper-evident record of each agent's declared action at each hop, an execution audit trail that complements, rather than replaces, capability-based delegation formats such as UCAN and ZCAP-LD. The underlying append-only, offline-verifiable chain-of-custody mechanism is payload-agnostic; human-authorized agentic delegation is the reference profile specified in this document.

Introduction Autonomous AI agents are increasingly used to execute consequential actions: sending emails, modifying files, running code, calling APIs, and transacting on behalf of users. When a human authorizes an orchestrator agent, which in turn delegates to sub-agents, which further delegate to tool-execution agents, the originating human authorization becomes disconnected from the terminal action. There is no standard record of the authorization chain. This gap creates accountability, auditability, and safety problems:

• Downstream agents cannot verify that the action they are being asked to perform was actually authorized by a human.
• Post-hoc audits cannot reconstruct who approved what, and when.
• Prompt injection attacks (where malicious content in the environment instructs an agent to act) cannot be distinguished from legitimate human delegation.

HDP addresses this by defining a token that:

• Records the human principal, their declared scope, and the session binding at issuance.
• Accumulates a cryptographically signed hop record for each agent that handles the token.
• Allows any recipient to verify the entire chain (root signature plus all hop signatures) using only the issuer's Ed25519 public key and the session identifier.

Motivation The need for agentic delegation provenance is not hypothetical. Production deployments of AI orchestration systems (LangChain, AutoGPT, CrewAI, and similar frameworks) today pass natural language task descriptions between agents with no cryptographic binding to the original human authorization. The operational risk compounds as models become more capable and agents are granted access to higher- consequence tools. A provenance token that travels alongside the task (tamper-evident, offline-verifiable, and scoped to what the human actually approved) provides the foundation for auditable, accountable agentic systems.

Design Goals HDP is designed with the following goals in order of priority:

1. Offline verifiability. Verification MUST require only a public key and session ID. No network call, registry lookup, or third-party endpoint is required.
2. Self-sovereignty. Any organization MUST be able to issue and verify HDP tokens without registering with a central authority or anchoring to a third-party key.
3. Tamper evidence. Any modification to a token's recorded content (its header, principal, scope, or any recorded hop) MUST be detectable by the verification pipeline. Completeness of the chain (that no trailing hop has been omitted) is a separate property; see .
4. Minimal footprint. The protocol MUST be implementable in any language with Ed25519 and JSON support. No mandatory infrastructure beyond key management is required.
5. Privacy by design. Principal identity fields MUST be separable from the audit-relevant parts of the token, so tokens can be transmitted to agents without exposing PII.

Relationship to IPP (draft-haberkamp-ipp-01) The Intent Provenance Protocol addresses the same problem space. HDP and IPP share the use of Ed25519 signatures and append-only provenance chains but make different architectural trade-offs, which are detailed in . The two protocols are not interoperable. HDP is offered as a distinct design point, not a revision of IPP. The full HDP protocol specification is available at . A TypeScript reference implementation is available at .

Generality of the Chain-of-Custody Mechanism The core of HDP is an append-only, cryptographically chained record: each hop extends a signed entry that covers all prior state, gaps in the hop sequence are tamper-evident, and any party can verify the entire chain offline using only a public key. This chain-of-custody mechanism is independent of what the chain carries. This document profiles that mechanism for one application: human-authorized agentic delegation. In this profile the carried payload is the scope object () and each hop record describes an agent delegation action. The same mechanism could carry other payloads, for example data provenance, consent delegation, or physical-world command chains, each as a distinct profile. Such profiles are out of scope for this document; HDP v0.1 defines only the agentic-delegation profile. Where practical, the signing (, ) and verification () procedures are described in a payload-agnostic way so that future profiles can reuse them unchanged.

Conventions and Definitions 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 and when, and only when, they appear in all capitals, as shown here.

Issuer:

The system or person that creates and signs an HDP token on behalf of a human principal.

Principal:

The human who authorized the agentic task. Represented in the token's principal object.

Agent:

Any AI system, model, or automated process that receives and acts upon an HDP token.

Hop:

A single delegation event, recorded as a signed entry in the token's chain array.

Root signature:

The Ed25519 signature over the token's header, principal, and scope, computed by the issuer at token creation time.

Hop signature:

The Ed25519 signature over the cumulative chain state at the time of extension. In HDP v0.1 it is produced by the issuer using the same key as the root signature.

Session:

A logical unit of work identified by a session_id string, established between the issuer and the agent framework before the token is issued.

Token Structure An HDP token is a JSON object with six top-level fields. The token MUST conform to the following structure. All integer timestamps are Unix milliseconds (milliseconds since 1970-01-01T00:00:00Z).

HDP Token Top-Level Structure

Header The header object carries token lifecycle and session binding fields.

token_id:

REQUIRED. A version 4 UUID . Unique identifier for this token.

issued_at:

REQUIRED. Unix milliseconds. Time of issuance.

expires_at:

REQUIRED. Unix milliseconds. Token MUST NOT be accepted after this time. Default lifetime is 24 hours.

session_id:

REQUIRED. Opaque string. Established out-of-band between issuer and agent framework before token issuance. Provides replay defense: a token is only valid within the session for which it was issued.

version:

REQUIRED. MUST equal the value of the top-level hdp field.

parent_token_id:

OPTIONAL. If present, identifies the token this token supersedes in a re-authorization chain. See .

Principal The principal object identifies the authorizing human. It MUST contain id and id_type. All other fields are OPTIONAL. The id_type field MUST be one of the following defined values, or a custom string prefixed with x-:

• opaque: Application-defined identifier. No resolution semantics are implied.
• email: An email address as defined in .
• uuid: A UUID as defined in .
• did: W3C Decentralized Identifier . DID resolution is application- defined and not required by this protocol.
• poh: A Proof-of-Humanity credential identifier. Verification semantics are application-defined; see .

HDP does not mandate any specific identity model. The did id_type is available for deployments with existing DID infrastructure; it is not required.

Scope The scope object records what the human authorized. It is signed as part of the root signature and MUST NOT be modified after issuance. The values above are illustrative. In particular, the max_hops value shown is an issuer choice for this example, not a protocol limit.

intent:

REQUIRED. Natural language description of the authorized task. Free-form string. This is the human-readable authorization statement.

authorized_tools:

OPTIONAL. Array of tool identifiers the principal has explicitly authorized. Enforcement is application-defined.

authorized_resources:

OPTIONAL. Array of resource identifiers (URIs, paths, etc.) the principal has authorized access to.

data_classification:

REQUIRED. One of: public, internal, confidential, restricted. Expresses the sensitivity level of data the agent is authorized to access.

network_egress:

REQUIRED. Boolean. Whether the agent is authorized to make outbound network requests.

persistence:

REQUIRED. Boolean. Whether the agent is authorized to write persistent state.

max_hops:

OPTIONAL. Positive integer, chosen by the issuer, expressing the delegation budget the human authorized for this token. HDP defines no fixed or maximum value; an issuer MAY set any positive integer. Verification MUST reject tokens whose chain length exceeds this value. If max_hops is absent, HDP places no limit on chain length, and delegation depth is governed by application policy (see ).

HDP does not mandate a central taxonomy for intent, authorized_tools, or authorized_resources. These are self-described by the issuer. Semantic validation of agent actions against declared scope is an application-layer concern.

Chain The chain array is append-only. Each element records a single delegation event (hop). The array is empty at issuance and grows as the token passes through agents. Agents MUST NOT remove or modify existing entries. " } ]]>

seq:

REQUIRED. Positive integer. Sequential index, starting at 1. MUST be exactly one greater than the previous hop's seq. Gaps in sequence are a protocol violation.

agent_id:

REQUIRED. Identifier of the agent adding this hop.

agent_type:

REQUIRED. One of: orchestrator, sub-agent, tool-executor, custom.

agent_fingerprint:

OPTIONAL. Model or binary fingerprint for the acting agent.

timestamp:

REQUIRED. Unix milliseconds. Time of hop extension.

action_summary:

REQUIRED. Human-readable description of the action this agent intends to take.

parent_hop:

REQUIRED. Non-negative integer. Index of the hop that triggered this delegation, where 0 indicates the root (human) authorization.

hop_signature:

REQUIRED. Base64url-encoded (no padding) Ed25519 signature. See . Absence is a protocol violation per Rule 6 of .

Signature The signature object carries the root signature computed by the issuer. " } ]]> The alg field MUST be Ed25519 for HDP v0.1. The kid field SHOULD be used by verifiers to identify the correct public key when multiple keys are in circulation.

Cryptographic Signing

Root Signature The root signature is computed by the issuer at token creation time. It covers the token's header, principal, and scope, the fields that constitute the human authorization event. The signing procedure is:

1. Construct the unsigned token object containing the hdp, header, principal, scope, and chain (empty array at issuance) fields.
2. Serialize the object to canonical JSON using RFC 8785 (JSON Canonicalization Scheme). This ensures deterministic byte representation across implementations and platforms.
3. Compute the Ed25519 signature over the canonical JSON bytes using the issuer's private key.
4. Encode the signature bytes as base64url (no padding).
5. Attach the signature object (kid, alg, value) to the token.

The signature field itself MUST NOT be included in the canonical JSON payload before signing. Because the root signature is computed while chain is empty, the signed payload is deterministically recoverable from a populated token by removing the signature field, resetting chain to an empty array, and re-serializing with RFC 8785. The root signature therefore covers hdp, header, principal, and scope; the chain is protected by the hop signatures () rather than by the root signature.

Hop Signature Each hop MUST carry a hop_signature. This signature binds the new hop record to the entire accumulated delegation history and to the root signature, making retroactive chain modification detectable. The hop signing procedure is:

1. Construct the new hop record (all fields except hop_signature).
2. Build the signing payload as a JSON array: [hop_1, hop_2, ..., hop_(n-1), new_hop_unsigned] where hop_1 through hop_(n-1) are the previously signed hops (WITH their hop_signature fields) and new_hop_unsigned is the new hop record WITHOUT its hop_signature.
3. Prepend the root signature value (base64url string) to the array as its first element: [root_sig_value, hop_1, ..., new_hop_unsigned]. This chains the hop signature to the root.
4. Serialize the array to canonical JSON per RFC 8785.
5. Compute the Ed25519 signature over the canonical JSON bytes using the issuer's private key.
6. Encode as base64url and attach as the hop_signature field on the new hop record.
7. Append the signed hop to the token's chain array.

The asymmetry between previously-signed hops (WITH hop_signature) and the new hop (WITHOUT hop_signature) in step 2 is intentional and critical. The verifier MUST reconstruct this exact payload structure when verifying each hop. See . In HDP v0.1, all signatures (the root signature and every hop signature) are produced by the issuer using a single key. An extending agent that is not the issuer has its hop signed by the issuer, within the same trust domain. This keeps verification dependent on a single public key (). Per-agent hop signing, in which each agent signs its own hop with its own key, is a planned extension for a future version and is not part of v0.1.

Chain Integrity Rules The following rules govern chain construction and MUST be enforced by both extenders and verifiers:

1. Hop seq values MUST start at 1 and increment by exactly 1. No gaps are permitted.
2. Existing hop records MUST NOT be modified or removed.
3. A hop's parent_hop MUST reference a valid prior hop index (0 for the root human authorization, or the seq value of a prior hop).
4. If scope.max_hops is set, the chain length MUST NOT exceed it. A token with a full chain MUST NOT be extended.
5. Each hop's timestamp SHOULD be monotonically non-decreasing.
6. The hop_signature field MUST be present on every hop. A hop without a hop_signature is a protocol violation and MUST cause verification to fail.

Verification Pipeline A verifier MUST execute the following seven steps in order. A failure at any step MUST cause immediate rejection with an appropriate error. The verifier MUST NOT proceed to subsequent steps after a failure.

1. Version check. The hdp field MUST contain a recognized protocol version string. For this specification, the only recognized value is "0.1". The header.version field MUST equal the hdp field; a mismatch MUST cause rejection.
2. Expiry check. The token's header.expires_at MUST be strictly greater than the current time. Expired tokens MUST be rejected.
3. Root signature verification. Reconstruct the canonical JSON payload by removing the signature field and resetting chain to an empty array (its value when the root signature was computed), then serializing the remaining token object per RFC 8785. Verify that signature.alg is Ed25519, then verify the signature in signature.value against this payload using the issuer's public key. A failure indicates tampering with the header, principal, or scope.
4. Hop sequence and structure integrity. For each hop in chain, verify that hop.seq == (index + 1); any gap or duplication MUST cause rejection. Verify that each hop's parent_hop references either 0 (the root authorization) or the seq of a prior hop; an out-of-range parent_hop MUST cause rejection (Rule 3 of ).
5. Hop signature verification. For each hop at index i:
   1. Verify that hop_signature is present. Absence MUST cause rejection.
   2. Reconstruct the signing payload as described in , using the hops at indices 0...(i-1) with their signatures, plus the hop at index i without its hop_signature, prepended by the root signature value.
   3. Serialize the payload per RFC 8785 and verify the hop_signature against the issuer's public key (the same key used for the root signature in HDP v0.1).
6. max_hops check. If scope.max_hops is defined, the length of chain MUST NOT exceed it.
7. Session binding check. The token's header.session_id MUST exactly match the session_id provided by the verifying application. This prevents token replay across sessions. See .

An optional eighth step MAY be performed if the application has registered a Proof-of-Humanity verifier: if principal.poh_credential is present and a verifier callback is configured, the credential MUST be validated by that callback. See . Verification is fully offline. Steps 1 through 7 require only the issuer's Ed25519 public key, the current session identifier, and the current time (for the expiry check). No network call, registry lookup, or third-party contact is required at any step.

Re-Authorization Long-running or streaming sessions may exhaust the max_hops limit, require scope expansion, or encounter situations where a high-risk action warrants fresh human confirmation. In these cases, the issuer (acting on behalf of the human principal) issues a new token that supersedes the original. Re-authorization is indicated by setting header.parent_token_id to the token_id of the token being superseded. This field MUST be set before computing the root signature, so the parentage link is cryptographically covered by the new token's root signature. A re-authorized token:

• Has a new token_id, issued_at, and expires_at.
• Inherits session_id, principal, and scope from the original unless explicitly overridden.
• Starts with an empty chain (delegation count resets).
• Records parent_token_id pointing to the original, creating an auditable lineage of scope evolution.

Verifiers that require re-authorization chain traversal SHOULD retain all tokens in a session and verify the full parent_token_id linkage.

Multi-Principal Delegation HDP v0.1 supports one principal per token. Joint authorization by multiple humans is achieved by sequential chaining: Human A issues token T1; Human B issues token T2 with parent_token_id equal to T1's token_id. Each token is independently signed with its issuer's key. To verify a multi-principal chain, the verifier MUST:

1. Verify each token individually against its issuer's public key using the standard 7-step pipeline.
2. Verify that T[i].header.parent_token_id == T[i-1].header.token_id for all i > 0.
3. Verify that all tokens in the chain share the same session_id.

This pattern provides joint authorization auditably without requiring a threshold signature scheme. Each principal's authorization is a distinct signed artifact. A future version of HDP (v0.2) is planned to introduce simultaneous multi- signature primitives using threshold signature schemes. The parent_token_id field thus serves two distinct purposes: supersession, where a re-authorized token replaces an earlier one (), and joint authorization, where both the parent and child tokens remain valid (this section). HDP v0.1 does not tag which relationship a given parent_token_id expresses; applications MUST determine it from context, typically by checking whether the parent token is still within its validity period and has not been superseded. A future version may add an explicit relationship type. Note also that a superseded token's session_id MAY be overridden on re-authorization, whereas the tokens in a joint-authorization chain MUST share one session_id.

Transport The HTTP header field names defined below do not use the "X-" prefix, in accordance with .

HTTP Header: HDP-Token HDP tokens MAY be transmitted in HTTP requests and responses using the HDP-Token header. The header value is the base64url encoding (RFC 4648, no padding) of the UTF-8 JSON serialization of the complete token object.

HDP-Token HTTP Header Example

Implementations MUST NOT include tokens in URL query parameters, as this exposes sensitive data in server logs and browser history.

Token by Reference: HDP-Token-Ref When token size is a concern (e.g., large chains), the token MAY be stored server-side and referenced by its token_id using the HDP-Token-Ref header.

HDP-Token-Ref HTTP Header Example

Implementations using token-by-reference MUST secure the token store and use transport-layer security (TLS) for all reference resolution.

Key Distribution: Well-Known Endpoint Issuers that wish to publish their Ed25519 public keys for automated discovery SHOULD serve a JSON document at /.well-known/hdp-keys.json with the following structure: " } ] } ]]> This format is intentionally minimal. Implementations MAY extend it with additional metadata. The alg field MUST be "Ed25519" for HDP v0.1 keys. Consumers MUST reject entries with unrecognized alg values. Consumers MUST validate that the decoded public key is exactly 32 bytes.

Privacy Considerations

Minimum-Disclosure Principal Fields The principal object may contain PII (email address, display name). Issuers SHOULD apply the principle of minimum disclosure when constructing tokens that will traverse multiple agents. Specifically:

• Use id_type: "opaque" with an application-internal identifier rather than embedding the user's email address in tokens that will be sent to third-party agents.
• Omit display_name when the receiving agent does not require a human-readable identity.

The token structure separates the identity fields (principal) from the audit-relevant fields (header, scope, chain). Implementations MAY strip the principal object when forwarding tokens to agents that do not require principal identity, while preserving the integrity of the signature chain. Note that stripping principal invalidates the root signature; stripped tokens MUST be clearly marked as audit-only records and MUST NOT be presented for signature verification. The same principle applies to the agent_id field in hop records (). An issuer or extending agent MAY use opaque, per-delegation identifiers for agent_id. Each delegate can still be held accountable by the delegator that assigned its identifier, step by step along the chain, because the opaque agent_id and its action_summary are bound into the signed, tamper-evident chain, without exposing a stable real-world identity to downstream verifiers.

Data Retention and the Right to Erasure HDP tokens may constitute personal data under applicable privacy regulations (e.g., GDPR Article 4(1)) when the principal.id or principal.display_name fields contain directly or indirectly identifying information. Implementations SHOULD:

• Store tokens with explicit retention periods derived from header.expires_at.
• Provide deletion mechanisms that remove stored tokens upon erasure requests.
• Use opaque identifiers in principal.id where possible, maintaining a separate mapping that can be destroyed independently of the token audit log.

Proof of Humanity The optional principal.poh_credential field MAY carry a credential attesting that the principal is a human (e.g., a Worldcoin World ID proof, a CAPTCHA session token, or a biometric attestation identifier). The HDP protocol does not define the semantics of this field; verification is entirely application-defined. When a PoH verifier is configured, the verification pipeline MUST validate the credential as the final step (after session binding) and MUST reject the token if validation fails. The verifier callback SHOULD be idempotent and SHOULD NOT have side effects.

Security Considerations

Threat Model HDP is designed to provide provenance and tamper evidence, not runtime enforcement. An agent that exceeds its declared scope is still a bad actor; HDP creates an evidence trail, not a capability boundary. Applications requiring runtime enforcement MUST implement it at the application layer using the HDP token as audit input.

Token Forgery A forged token (one whose header, principal, or scope fields do not match the original issuance) will fail Step 3 of the verification pipeline (root signature check). The security of this step relies on the unforgeability of Ed25519 signatures and the collision resistance of SHA-512 (used internally by Ed25519). An attacker who does not possess the issuer's private key cannot produce a valid root signature for a modified token.

Chain Tampering Modification, reordering, or removal of any non-trailing hop is detectable: it either breaks the hop sequence check (Step 4) or invalidates the hop signatures of all subsequent hops (Step 5), because each hop signature covers all previous hops and the root signature. Insertion of a fabricated hop will similarly fail unless the attacker possesses the issuer's private key. Removal of one or more trailing hops is a distinct case that these checks do not detect; see .

Chain Truncation and Completeness Each hop signature covers only the hops that precede it and the root signature. Consequently, deleting one or more hops from the end of the chain, or presenting an earlier and shorter copy of a token, yields a token that still passes every step of the verification pipeline. HDP therefore provides tamper evidence for the hops that are present, but does not by itself prove that the chain is complete. Relatedly, a non-cooperating or compromised agent can decline to append a hop for an action it takes; HDP records declared delegation actions and cannot compel an agent to record one. HDP is an evidence trail, not an enforcement mechanism (). Applications that require completeness SHOULD establish the expected chain length or a terminal marker out of band: for example, by pairing HDP with an application-layer receipt or settlement step that records the final hop count, by setting scope.max_hops to the exact expected length where it is known, or by requiring each recipient to acknowledge the hop count it observed. A signed, monotonic chain-length commitment is a candidate mechanism for a future version.

Replay Attack Defense HDP provides two orthogonal replay defenses:

1. Expiry. Tokens are short-lived (expires_at, 24h default). An expired token is rejected at Step 2 regardless of network conditions.
2. Session binding. The token carries the session_id established out-of-band between issuer and verifier. A token is valid only within the session for which it was issued. Even a non-expired token cannot be replayed across sessions.

Together, these defenses ensure that a stolen token is useful to an attacker only within the original session and only before it expires. Applications with high security requirements SHOULD use short token lifetimes (minutes, not hours). Because session_id anchors the session-binding defense, it SHOULD be unguessable: issuers SHOULD generate session_id values with at least 128 bits of entropy from a cryptographically secure random source. A predictable session_id weakens replay protection.

Revocation Considerations HDP does not provide mid-chain revocation. The revocation model is deliberately coarse: a token becomes invalid when it expires () or when its session ends. There is no mechanism to revoke authorization for a single delegate in the middle of an otherwise valid chain without invalidating the whole token and re-authorizing (). A consequence is that proof that an action was authorized is not, by itself, sufficient to determine whether that authorization is still current. Deployments that require fine-grained, mid-chain revocation SHOULD keep token lifetimes short and rely on re-authorization, or layer a capability system that supports cascade revocation at the application layer. Retaining accountability for each delegate (for example through distinct per-hop identifiers, ) is what makes such application-layer revocation actionable.

Prompt Injection Prompt injection attacks attempt to cause an agent to act as if it received instructions from a legitimate principal, when in fact the instructions originate from adversarial content in the agent's environment (e.g., a malicious web page or document). HDP mitigates but does not fully prevent this attack. An HDP-aware agent SHOULD refuse to extend a token's chain with an action_summary that contradicts the token's scope.intent. However, the protocol cannot enforce this semantically; the comparison between action intent and token scope is application-defined. The mitigation HDP provides is evidentiary: an HDP-aware agent records each delegation action it takes as a signed hop, so an action carried out under a legitimately issued token leaves an auditable record, supporting post-hoc detection of prompt injection. This mitigation depends on agents actually recording their actions; an agent that omits a hop is discussed in .

Key Management The security of all HDP guarantees depends on the confidentiality of the issuer's Ed25519 private key. Implementations MUST:

• Store private keys in a secrets manager, HSM, or equivalent secure enclave. Private keys MUST NOT be stored in source code, configuration files, or environment variables in production.
• Use distinct key pairs per environment (development, staging, production).
• Support key rotation by issuing new tokens with a new kid while maintaining the old key in the verifier's registry until all tokens signed with it have expired.

Offline Verification Guarantee HDP makes a strong architectural guarantee: a correct implementation of the 7-step verification pipeline requires no network calls, no registry lookups, and no third-party contact. The complete trust state required for verification is:

• The issuer's Ed25519 public key (32 bytes).
• The current session identifier (string).
• The current time (for expiry checking).

This guarantee enables HDP verification in air-gapped environments, edge deployments with intermittent connectivity, and latency-sensitive contexts where a network round-trip before every action is unacceptable.

IANA Considerations

HTTP Header Field Registration This document requests registration of the following HTTP header fields in the "Hypertext Transfer Protocol (HTTP) Field Name Registry" maintained at <https://www.iana.org/assignments/http-fields/>.

Header Field Name:

HDP-Token

Status:

provisional

Reference:

This document,

Comments:

Carries a base64url-encoded HDP token for agentic delegation provenance.

Header Field Name:

HDP-Token-Ref

Status:

provisional

Reference:

This document,

Comments:

Carries the UUID token_id of an HDP token stored by reference.

Media Type Registration This document requests registration of the application/hdp-token+json media type in the "Media Types" registry, following the procedures of .

Type name:

application

Subtype name:

hdp-token+json

Required parameters:

N/A

Optional parameters:

N/A

Encoding considerations:

binary; the token is a UTF-8 JSON object .

Security considerations:

See of this document.

Interoperability considerations:

The token uses the "+json" structured syntax suffix ; generic JSON processors can parse it. HDP-specific semantics are defined in this document.

Published specification:

This document.

Applications that use this media type:

Agentic AI frameworks and services that exchange HDP delegation-provenance tokens.

Fragment identifier considerations:

N/A

Additional information:

Deprecated alias names: none. Magic number(s): none. File extension(s): none. Macintosh file type code(s): none.

Person & email address to contact for further information:

Asiri Dalugoda <protocol@helixar.ai>

Intended usage:

COMMON

Restrictions on usage:

None

Author:

Asiri Dalugoda

Change controller:

IETF

Well-Known URI Registration This document requests registration of the following entry in the "Well-Known URIs" registry, per .

URI suffix:

hdp-keys.json

Change controller:

IETF

Specification document:

This document,

Status:

provisional

Related information:

Serves a JSON document listing an issuer's Ed25519 public keys for HDP token verification.

Comparison with Related Work

IPP (draft-haberkamp-ipp-01) The Intent Provenance Protocol and HDP address the same root problem with different architectural trade-offs. The key differences are:

1. Revocation model. IPP requires agents to poll a central revocation registry at a configurable endpoint before every action, with a recommended interval of 5,000 milliseconds. If the registry is unreachable, agents cannot safely act. HDP uses short-lived tokens with session_id binding as the revocation mechanism; no registry polling is required at any point.
2. Trust anchor. IPP tokens contain a genesis_seal, a cryptographic artifact linking every token to the specification author's public key at https://ipp.khsovereign.com/keys/founding_public.pem. Self-hosted IPP deployments are cryptographically bound to this third-party key. HDP tokens carry no genesis seal and no spec-level attribution; any organization can issue and verify HDP tokens without anchoring to a third party.
3. Identity model. IPP mandates W3C DID Core-conformant principal identifiers. HDP supports id_type: "opaque" as a first-class option, making DID infrastructure optional rather than required.

These are design choices, not defects. Deployments with reliable connectivity to a central registry, existing DID infrastructure, and a requirement for mid-chain revocation may prefer IPP. Deployments that prioritize offline operability, self-sovereignty, and minimal infrastructure may prefer HDP.

OAuth 2.0 Token Exchange (RFC 8693) OAuth 2.0 Token Exchange defines a mechanism for exchanging one security token for another, including delegation and impersonation use cases. HDP and RFC 8693 are complementary rather than competing: RFC 8693 governs access token issuance and delegation in an OAuth 2.0 authorization server context, while HDP governs the provenance record that travels with an agentic task regardless of the authentication mechanism used. HDP tokens do not replace OAuth access tokens. An agent framework MAY use OAuth 2.0 for resource authorization and HDP for delegation provenance simultaneously.

JSON Web Token (RFC 7519) JSON Web Token provides a general-purpose signed claims format. HDP differs from JWT in three respects:

• HDP tokens carry an append-only, per-hop-signed delegation chain (chain) that has no equivalent in the JWT standard claims set.
• HDP uses RFC 8785 canonical JSON for signing payloads, rather than the base64url-encoded header.payload convention used by JWS . This allows direct JSON manipulation without base64 decoding.
• HDP's verification pipeline is domain-specific to agentic delegation (session binding, hop verification, max_hops) rather than general-purpose.

UCAN (User Controlled Authorization Networks) UCAN defines a capability-based authorization token system with chained delegation. HDP and UCAN share the concept of delegation chains but differ significantly in scope: UCAN is a general capability authorization system, while HDP is specifically a provenance record for human-authorized agentic tasks. HDP makes no claims about capability enforcement; UCAN tokens carry executable capabilities that are enforced by receiving systems. A UCAN delegation records the authorization provenance of a capability: who delegated what to whom. UCAN's separate Invocation and Receipt objects can record individual invocations and their results; HDP instead keeps the execution record inline in the delegation chain itself, as the signed action_summary declared at each hop, so that the human authorization and the subsequent declared actions travel together in a single offline-verifiable record. In this sense HDP complements capability systems rather than competing with them: a deployment MAY use UCAN (or ZCAP-LD, below) for capability delegation and HDP alongside it for the tamper-evident execution record.

ZCAP-LD (Authorization Capabilities for Linked Data) ZCAP-LD expresses delegated authorization capabilities as Linked Data, with invocation and delegation rooted in a controller's key. As with UCAN, a ZCAP-LD delegation chain captures the authorization provenance of a capability but not a record of the delegate's subsequent actions. HDP neither defines nor enforces capabilities; it records the human authorization event and the subsequent execution history. Deployments that already use ZCAP-LD MAY use HDP alongside it to supply the execution audit trail ZCAP-LD does not itself provide.

ODRL and the Verifiable Credentials Data Model The Open Digital Rights Language (ODRL) is a W3C Recommendation for expressing permissions, prohibitions, and constraints. Several fields in HDP's scope object () overlap with concepts ODRL already defines: authorized_tools and authorized_resources correspond to ODRL actions and targets, network_egress and persistence map to ODRL permissions or prohibitions, and quantitative limits such as max_hops map to ODRL constraints. HDP v0.1 deliberately retains a small, self-contained scope object rather than embedding an ODRL policy. The trade-off is explicit: the minimal object keeps tokens compact and implementable with only JSON and Ed25519, at the cost of the vocabulary reuse, policy composability, and tooling interoperability that ODRL provides. Deployments that already reason over ODRL policies will require a separate mapping to interpret HDP scopes. Because the chain-of-custody mechanism is payload-agnostic (), a future HDP profile MAY carry an ODRL policy as its payload in place of the native scope object. Such a profile would gain a natural binding to the Verifiable Credentials Data Model 2.0 , whose termsOfUse property can carry ODRL policies. This binding is identified as future work and is not specified in this document.

Normative References Harvard University Huawei Technologies Informative References Helixar Limited Helixar Limited UCAN Working Group

Complete Token Example The following is a complete HDP token with a two-hop delegation chain, for illustrative purposes. Signature values are truncated.

Change Log This section will be removed before publication as an RFC.

draft-helixar-hdp-agentic-delegation-01:

Incorporates review feedback from the W3C Credentials Community Group and a specification-consistency pass. Related Work () expanded with ODRL, a Verifiable Credentials Data Model 2.0 termsOfUse alignment note, and ZCAP-LD; the UCAN comparison identifies the execution audit trail as HDP's distinguishing contribution. Added (payload-agnostic chain-of-custody with agentic delegation as the reference profile). Corrected root signature verification to reset chain to empty before canonicalization, matching the signing procedure, and clarified that in v0.1 the issuer produces all root and hop signatures with a single key. Added (chain truncation and completeness), (revocation), session_id entropy guidance, and per-hop opaque-identifier privacy guidance (). The verification pipeline now also checks header.version, signature.alg, and parent_hop validity. Completed the IANA media-type registration template and added a Well-Known URI registration. Added missing normative and informative references. Renamed the HTTP header fields from X-HDP-Token and X-HDP-Token-Ref to HDP-Token and HDP-Token-Ref (). Editorial corrections. The token wire format is unchanged and remains HDP v0.1; the HTTP header field names changed.

draft-helixar-hdp-agentic-delegation-00:

Initial submission. Specifies HDP v0.1 token structure, signing, verification pipeline, re-authorization, multi-principal delegation, transport, privacy considerations, and security analysis.