Signed and Unexpired Is Not the Same Fact As Unspent
draft-bubblefish-naalp, N-AALP, is reported to bind an agent's signed action object to an Approval under signature, and to make that Approval spendable exactly once through a durable consume ledger distinct from the approval's own cryptographic validity and expiry. This session could not independently verify that mechanism: every IETF-hosted route and every mirror it attempted was blocked, and no canonical source repository or secondary coverage of the draft's own text could be located. What is independently established is narrower: an Internet-Draft under this name, and a separate companion transport draft, draft-bubblefish-npamp, are both listed in the IETF Datatracker's own index.
Not when the grant is explicitly single-use, and a further individual IETF Internet-Draft, draft-bubblefish-naalp (N-AALP, Native Agentic Application Layer Protocol), is reported to say so directly: offline cryptographic verification of a signed approval proves validity at issue, not current unspentness, because a durable consume ledger can have already spent it. This record could not independently verify that the draft's own filed text actually says this: every ietf.org, datatracker.ietf.org and mailarchive.ietf.org route this session attempted was blocked, and, unlike a comparable prior IETF-draft record this desk carries, no canonical source repository or independent secondary coverage of N-AALP's own content could be located through repeated, independently phrased search. What is independently confirmed is only that Internet-Drafts under this name, and under a separate, distinct companion name, draft-bubblefish-npamp, are listed in the IETF Datatracker's own index of Internet-Drafts.
Most of what this record would ordinarily say about a new Internet-Draft, what its object model actually specifies, how its Approval structure binds identity to effect, whether its worked examples hold up, this record cannot say, because this session could not read the draft. That is worth stating before anything else: draft-bubblefish-naalp is not a record this desk verified against primary text. It is a record about what could and could not be established, and about a reasoning gap the draft's own reported design names precisely enough to be worth closing in Moona's own canonical engine regardless of whether the draft itself ever advances.
What this session could actually reach
ietf.org, www.ietf.org, datatracker.ietf.org and mailarchive.ietf.org were each blocked by this session's network egress policy on every attempt, the same policy-level block this desk's other IETF-draft records document. Unusually, none of the further routes that have worked for comparable records worked here either: ftp.funet.fi's own IETF Internet-Draft mirror was itself blocked, and repeated, independently phrased web searches located no GitHub source repository, no independent implementation, and no secondary blog, mailing-list thread or analysis discussing this draft's own technical content specifically. What those searches did return, consistently, is that an Internet-Draft named draft-bubblefish-naalp, and a separate, distinct draft, draft-bubblefish-npamp, both appear in the IETF Datatracker's own index of all Internet-Drafts and RFCs. That confirms the family exists as filed individual submissions. It confirms essentially nothing about what either draft specifies.
What is reported, not verified
A description supplied to this session states N-AALP's core property as making the signed action object, rather than the transport connection, the unit carrying authorization-relevant semantics: each object reportedly carries a content identity, a signature-verified signer, a closed effect, causal provenance, and audience/context and approval bindings, with the effect stated as an authorization input rather than a hint. An Approval object is reported to bind, under signature, the content id of the exact canonical argument object, the approver's identity, the granted effect, an anti-replay nonce, an expiry, and, for a Model Context Protocol tool-call binding specifically, a tool_id and args_id together, so a changed tool description or changed arguments produces a different approved call identity, with a mismatch surfaced as ApprovalMismatch. Most consequentially, the draft is reported to define a durable consume ledger under which the first valid consumer atomically spends a single-use approval, a second presentation returns AlreadyConsumed, an expired approval returns ApprovalExpired, and, when the ledger itself is unavailable, an approval spend fails closed at baseline rather than succeeding open. The draft is reported to state directly that offline cryptographic verification proves validity at issue, not current unspentness: the signed bytes can remain valid and unexpired while the approval no longer carries current authority because a ledger elsewhere has already recorded it spent.
This record does not adopt any of that as independently confirmed. It rests on a description supplied to this session, not on this session's own reading of the filed revision text, a canonical source repository, or independent secondary coverage, and every specific claim above is recorded here as reported, pending direct verification once network access allows it, exactly as this desk's sourcing discipline requires for a claim it could not itself check. Revision -00 is separately reported dated 27 July 2026 and revision -01 dated 6 September 2026; this record treats -00 and -01, if both filings exist as reported, as one evolving artifact across both revisions rather than as two independent pieces of evidence, the convention this desk already applies to every multi-revision IETF draft it carries.
What this record does not do with unverified content
This record does not represent N-AALP as an RFC, an adopted IETF working-group item, IETF consensus, a production deployment, or as having demonstrated interoperability between two independent implementations, none of which this session could establish even for drafts it could read directly, let alone one it could not read at all. It does not fold N-AALP together with its reported companion transport draft, draft-bubblefish-npamp: if the reported division of labor holds, a transport-security draft authenticating channel peers is a different kind of evidence from an object-level authorization, approval and consumption-state protocol, and this desk's own recurring argument is precisely that a secured connection is not, on its own, action authority.
The gap worth closing regardless
Independent of whether N-AALP's own reported mechanism holds up, the property it names is one Moona's own canonical Authority Resolution engine did not yet represent before this record: an approval's cryptographic validity and its expiry are both temporal facts about the signed artifact, and neither, on its own, establishes that a grant explicitly issued as single-use has not already been exercised. This desk's own Risk Registry already carries the general shape, AEW-005, approval not bound to the executed action, whose authorityGap states that the authority granted attaches to what was presented for review, and an approval already spent by an earlier execution is not, in any meaningful sense, still attached to a further one.
Moona's canonical Decision Context (src/content/moona-knowledge/authority-model.ts) previously modeled temporal authority only as expiry against a proposed execution time. This record's own evidence, even held at reported-not-verified grade, closes a specific, narrow instance of that gap: an evidenced approval may now carry its own singleUse and consumed state, consulted by assessAuthorityDelta only when singleUse is evidenced true, never universalized to every approval, since most grants are reusable. A single-use approval evidenced as already consumed no longer establishes current authority even where it remains valid and unexpired; a single-use approval whose consumption state is not itself evidenced resolves to HOLD, current spendability unknown, rather than silently inheriting AUTHORIZED from validity and non-expiry alone. Moona's runtime-evidence grounding (runtime-evidence.ts) gained the matching ingestion path, plus two further, independently motivated continuity checks the reported N-AALP mechanism's own tool_id/args_id binding and effect-as-authorization-input framing named clearly even without verified primary text: a paired approvedToolDigest/toolDigest comparison, distinct from this module's existing tool-*name* continuity check, so a materially changed tool definition is never treated as covered by an approval bound to an earlier one merely because a visible name and arguments are unchanged; and a paired declaredEffect/observedEffect comparison that preserves both facts rather than ever normalizing a tool's own declared effect label into the runtime-observed effect. Every extension is additive and backward compatible: a Decision Context or runtime artifact that never states these facts resolves exactly as it did before this record existed.
Current standing, stated plainly
This is, at most, an individual Internet-Draft family this session could not read, verified only to the extent that it appears indexed at all. No working-group ownership, no RFC track, no implementation, and no interoperability evidence is independently established. A future editor with unblocked network access should fetch both revisions of both drafts directly, confirm every reported property above against the filed text, and upgrade or correct this record's own grading accordingly before it is cited as anything stronger than a name and a reported description.
A second, independently authored corroboration: EBL-Core (arXiv 2609.11596)
A paper submitted to arXiv on 10 September 2026, From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions (arXiv 2609.11596), by Mengting Wu, Lin Wang, Yong Zhang and Jiang Deng, states this record's own gap, that a decision object's own validity is not the same fact as current spendability, as a named conformance profile rather than a single design. arxiv.org, its export mirror, huggingface.co/papers, alphaxiv.org, semanticscholar.org and pith.science were each blocked at this session's network egress proxy on every attempted route, and no public reference-artifact repository for the paper could be located through repeated, independently phrased web search; what follows rests on that convergent search alone, held at the same manual-review evidence level this record already applies to N-AALP above, not a direct read of either manuscript. The paper's own reported lifecycle separates an ALLOW Execution Release Contract, produced by adjudication, from a later Execution Grant: it states directly that an Execution Release Contract is not itself an authority bearing token, so a verified ALLOW Execution Release Contract may support a separate Execution Grant, and that Grant is what governs Redemption, revalidated again at the moment Redemption is actually attempted rather than trusted from the earlier decision, the same offline-validity-is-not-current-unspentness distinction N-AALP's own reported consume ledger already names here. Its reported reference artifact, distinct from N-AALP's in resting on stated test results rather than a described mechanism alone, reports 34 static test vectors and 15 lifecycle checks matching expected outcomes, and, across 100 trials, 32 concurrent Redemption attempts against the same Grant yielding exactly one successful Redemption per trial, plus a separate 100 Revoke-Redeem race trials each ending in a valid terminal outcome. This record does not treat those figures as independently reproduced, and does not adopt any claim beyond what convergent search actually returned; production interoperability, whether the profile's own typed evidence is itself true rather than merely well typed, and whether every code path an implementation exposes is actually mediated by this lifecycle, are each left unknown rather than resolved either way, the same restraint this record already applies to N-AALP's own reported mechanism. This second, independently authored paper does not motivate any further extension of Moona's canonical Authority Resolution engine: the exactly-once-consumption and valid-race-outcome properties it reports are already carried by the singleUse/consumed state N-AALP's own reported gap motivated above, so this is corroborating evidence for an extension already made, not a new one.
Sources
This analysis interprets third-party reporting, research and announcements. Moona is not the original reporter of the underlying events.
Protocol evidence
This record does not assess these architectures. The connection runs through the Risk Registry requirement each one bears on, and these published authority architectures are what the evidence says about that requirement.
Protocol evidence related through AEW-005 Approval not bound to the executed action
- Supports requirement
Agent Flight Recorder
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner (independent research, arXiv preprint)
Requirement Cryptographic binding of the approval field to the approver's identity and the specific action is described as a production deployment property, not an unconditional schema guarantee
This weakness's own known examples are, across every one of them, a case where an approval attached to nothing verifiable or a later state change went unchecked against a prior decision. Agent Flight Recorder's own schema keeps a human approval field and an execution field as two independently checkable facts rather than one narrative line, which is a direct answer to the underlying need this weakness names: an approval must bind to a specific action, not merely occur near one. It supports that requirement rather than implementing an enforced version of it, because the reported cryptographic binding of the approver's identity to the specific action applies only in production deployments of the construction, not as an unconditional schema guarantee, and the mechanism records the approval/execution relationship for later forensic inspection rather than checking it before the action dispatches the way EMILIA's action hash rejection or Codex CLI's authorization freshness recheck do.
- Supports requirement
Agent Infrastructure Control Protocol (AICP)
Tihan-Nico Paxton, Apollo Deploy (individual submission to the IETF)
Requirement An accepted approval binds cryptographically or transactionally to one exact plan revision
This weakness's own corrective response pattern calls for binding an approval to the exact action object by hash or an equivalent identity, and rejecting execution when the action presented for review differs from the action about to run. AICP's own Section 9.4 requires an accepted approval to be cryptographically or transactionally bound to the Plan identifier, exact revision, approving principal, material changes and expiry, stating directly that approval of prose alone is insufficient and that a changed revision is not authorized by the old approval. The HTTP binding in Section 14.5 enforces the same binding mechanically, through a conditional request against the Plan's strong entity tag. Recorded as design evidence for the requirement this weakness already states, not as a claim that any provider has implemented this draft's text.
- Supports requirement
An Architecture for Auditing Agent Delegation and Interactions (audit-architecture)
Mirja Kuehlewind (Ericsson) and Henk Birkholz (Fraunhofer SIT), individual submission to the IETF
Requirement Authorization is modeled as an ordered sequence of transitions, not a single current value
This weakness's own response pattern calls for recomputing an approval's binding to the exact action at the enforcement point rather than trusting an earlier decision, including the temporal window that decision was made under. The draft's Action Record carries an authorization scope and expiry alongside the action it bears on, and its Authorization Transition Record class exists specifically so the state in force at a given point in a run can be reconstructed rather than assumed from whatever is currently known. Recorded as design evidence for the general response pattern; this record's own evidence separately connects to a targeted extension of Moona's canonical Authority Resolution engine closing the equivalent gap in Moona's own runtime reasoning, not a claim that this draft's own text was implemented anywhere.
- Supports requirement
ChainIT Authority Protocol and Agent Subject Profile for pre execution authority validation
ChainIT
Requirement A canonical transaction digest is described binding payer, payee, destination, amount, currency or asset and payment rail to approval and execution
A canonical transaction digest binding payer, payee, destination, amount, currency or asset and payment rail to both approval and execution is a direct, more specific response to an approval that attaches to nothing in particular. This is the corrective this weakness describes, named at the level of concrete payment fields rather than a generic hashed parameter set.
- Supports requirement
Codex CLI 0.151.0, restored permission profiles and authorization bound Guardian classifications
OpenAI
Requirement A cached low risk score is checked against the current authorization state before it is allowed to approve, and a mismatch defers to strict review rather than proceeding
Codex CLI's own fix rechecks a cached decision against current authorization state before it is allowed to approve anything, refusing to let a decision computed under one state keep approving after that state has moved. Claude Code's own current plugin marketplace documentation, read directly, describes an installed plugin auto-updating on a version, commit or content digest signal with no described mechanism to diff, flag or gate a change to the plugin's own hooks.json specifically, so whatever authority a user's earlier trust decision represented is not shown to be rechecked once a later update changes what that plugin's bundled hooks execute. Codex CLI's own mechanism is the corrective the reviewed documentation does not describe for this specific binding.
- Supports requirement
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Implementations MUST reject an approval request whose action hash does not match a locally recomputed hash of the presented Action Object
EMILIA's requirement that an approval be rejected unless the action hash matches a locally recomputed hash of the exact action object is the binding these cases lack, where an approved command's behaviour is decided by state the approval never inspected.
- Supports requirement
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Offline verification does not establish current revocation status, and the draft requires a relying party to apply current policy and current status inputs before any new reliance decision
UiPath Maestro's own default on Refresh schema before call setting keeps an MCP tool's technical interface current immediately before each call, but nothing in UiPath's own documented behavior establishes that the parameter authority a workflow's configuration granted against the original schema is re evaluated once a later schema changes underneath it. That gap, a technically current interface with no stated authority re evaluation behind it, is exactly the condition EMILIA's own requirement, that a relying party apply current status rather than historical acceptance before a new reliance decision, exists to close. UiPath's mechanism supports the need for that requirement rather than implementing it, the distinction this dataset already keeps between this property's two linked entries. A preprint posted to arXiv on 3 September 2026, 2609.03340, Fresh Memory, Stale Plans, restates the same distinction for a derived plan specifically: an executor that has read a superseding revision of a shared requirement into its own memory can still execute a plan derived from the earlier revision, since refreshing the executor's memory does nothing to a plan already computed from the state that memory has since moved past, so current state and current authorization for a pending action are two different facts. Read at the manual review evidence level, corroborated through convergent search rather than a direct read of the primary text, since arxiv.org and every mirror this record attempted were blocked at this session's network egress proxy; treated as further support for the requirement, not as an implementation of it.
- Supports requirement
N-AALP, Native Agentic Application Layer Protocol (draft-bubblefish-naalp)
BubbleFish, individual submission to the IETF
Requirement A signed-action-object model with a content-bound Approval and a single-use consume ledger is reported, not independently verified
This weakness's own response pattern calls for binding an approval to the exact action object, by hash or an equivalent identity, rather than to a name or a connection. The reported mechanism, an Approval bound under signature to the content id of the exact canonical argument object and, for an MCP call, a tool_id and args_id together, so a changed tool description or changed arguments yields a different approved call identity, would be a clean instance of exactly that pattern if it accurately reflects the draft's own filed text. This session could not independently verify that text through any reachable primary or secondary source, so this link is recorded conditionally: design evidence for the weakness's own already-established requirement, not confirmation that this specific draft implements it.
This record is the cited evidence for this relationship.
- Supports requirement
N-AALP, Native Agentic Application Layer Protocol (draft-bubblefish-naalp)
BubbleFish, individual submission to the IETF
Requirement A durable single-use consume ledger, and a stated limit that offline verification proves validity at issue, not current unspentness, are reported, not independently verified
This weakness's authorityGap states that authority attaches to what was presented for review, not automatically to whatever executes afterward; an approval a durable ledger has already recorded spent is not, in any meaningful sense, still attached to a further execution. The reported single-use consume ledger, and the reported statement that offline cryptographic verification proves validity at issue rather than current unspentness, would instantiate that gap precisely for a signed approval's own consumption state rather than its identity binding. Unverified by this session for the reason stated above; this record's own independent contribution is the additive extension it separately motivated to Moona's canonical Authority Resolution engine (an evidenced approval's singleUse/consumed state, consulted only when singleUse is evidenced true), which does not depend on this specific draft's own claims being confirmed.
This record is the cited evidence for this relationship.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement A validated Candidate Act may produce a narrowly scoped, non-bearer Execution Handle bound to that one act and to the Finality Sink that will consume it
This weakness's own response pattern calls for binding an approval to the exact action object and recomputing that binding at the enforcement point rather than trusting possession of a credential. The non-bearer Execution Handle, corroborated through convergent search rather than a direct read of the filed text, generalizes exactly that principle to a credential class broader than one interface family: a validated Candidate Act may produce a handle scoped narrowly to that one act, and possessing the handle is not itself proof the currently presented act still matches the one it was issued for. Recorded as documented design evidence restating this weakness's own already-established requirement at a general level, not as independent confirmation that this specific umbrella draft's own mechanism is demonstrated running anywhere.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement Formalizes Candidate Act, Non-Effective State, Protected Enforcement Domain, Execution Handle and Finality Sink as shared vocabulary for a family of domain-specific drafts
This weakness's own known examples had, before this addition, connected to draft-das-agentic-tool-binding-03 as though it were a freestanding architecture. Convergent search corroborates this draft as the umbrella that sibling instantiates: a Protected Enforcement Domain validates authority scoped to an act's purpose, destination, jurisdiction, freshness, revocation state, policy epoch, runtime integrity and effectuation-boundary identity together, a broader validation surface than the tool-binding draft's own two directly verified consequence classes. Recorded as design evidence for this weakness's own binding requirement at the general architecture level; this session located no reference implementation for this specific umbrella draft and does not treat any part of it as independently verified running code.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement Fails closed on missing, stale, mismatched, replayed or unverifiable context
This weakness's own response pattern calls for rejecting execution when the action presented for review differs from the action about to run, rather than proceeding on a default allow. The signal that prompted this record carries a five-item fail-closed enumeration, missing, stale, mismatched, replayed or unverifiable context, consistent with the fail-closed behavior this weakness's own draft-das-agentic-tool-binding-03 known example already verified directly in running code for one narrower mechanism. This session's own independent search did not itself return that exact enumeration from a secondary source, so this link is recorded as documented design evidence consistent with corroborated evidence, not as independently re-confirmed word for word against the filed text.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement Authority is scoped to one Candidate Act through a deterministic digest of its own exact arguments
This weakness's own response pattern calls for binding an approval to the exact action object by hash or an equivalent identity and recomputing that binding at the enforcement point rather than trusting the request. Act Bound Authority, confirmed directly this session from the draft's own reference implementation, is exactly that binding applied to tool dispatch: a deterministic digest computed over a Candidate Act's own exact arguments, so authority issued for one call cannot be presented for a different call bearing different arguments even under the same session or workload. Recorded as design evidence independently demonstrated in running reference code, not as a claim that this specific implementation is deployed anywhere.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement A Finality Sink verifies authority atomically immediately before invoke() runs, fail closed on any failure
This weakness's own response pattern calls for recomputing an approval's binding at the enforcement point rather than trusting an earlier decision. The Finality Sink, confirmed directly this session from the reference implementation's own sink module, is that enforcement point positioned immediately before the underlying invoke() call, verifying authority atomically and blocking execution whenever verification does not succeed rather than proceeding on a default allow. Recorded as design evidence for the same requirement EMILIA's own action-hash rejection requirement already formalizes for payment operations, applied here to tool dispatch generally.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement Each parallel tool call requires its own independently computed authorization
None of this weakness's own known examples had, before this addition, named independent authorization for concurrent tool calls specifically. The reference implementation's own test scenarios, read directly this session, decide a parallel search plus unauthorized payout case as two independent authorization decisions rather than one session-level trust judgment covering an entire batch, closing a gap this weakness's own binding requirement implies but had not yet evidenced concretely for parallel dispatch.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement A retried or replayed call presenting already-consumed authority is denied
This weakness's own known examples document an approval or a cached decision surviving a state change it never accounted for; none had yet named a retried or replayed call presenting already-spent authority as its own distinct axis. The reference implementation's own replay store, read directly this session, marks authority consumed atomically on first use and denies a subsequent presentation of the same authority, with the implementation's own stated limitation that this protection is local rather than distributed. Recorded as design evidence for a property this weakness's own response patterns imply but had not yet evidenced at this level of precision.
- Implementation evidence
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Implementations MUST reject an approval request whose action hash does not match a locally recomputed hash of the presented Action Object
MoonPay's PayBox documents that any change to an operation's amount, merchant, destination, contract, function or secret name after submission forces a fresh approval request rather than letting the original one carry over. That is the same operation-bound approval EMILIA's action-hash rejection requirement formalizes cryptographically, arrived at independently in a live consumer product rather than a draft specification, which corroborates that the requirement is buildable outside a standards process.
- Implementation evidence
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Offline verification does not establish current revocation status, and the draft requires a relying party to apply current policy and current status inputs before any new reliance decision
Codex CLI's own merged fix binds a cached Guardian v2 classification to the exact authorization state it was scored against and refuses to let it approve an action once that state has moved, arrived at independently in a shipped product rather than a draft specification. That corroborates EMILIA's own requirement that a relying party apply current status inputs before a new reliance decision rather than treat historical acceptance as still current, the same binding failure this weakness already describes. OpenMAIC's own 1.0.1 fix, read directly by this dataset, applies the identical principle to a network destination rather than a cached score: fetchWithRedirectValidation re-runs validateUrlForSSRF against every redirect hop before following it, rather than treating the single validation performed against the caller's originally supplied bring your own key base URL as still current once an ordinary HTTP redirect substitutes a different destination. A third independent, shipped instance of the same requirement, this one at a network authority boundary rather than at an approval or a classification.
- Missing requirement
ChainIT Authority Protocol and Agent Subject Profile for pre execution authority validation
ChainIT
Requirement No canonicalization algorithm, serialization format or independent test of the transaction digest against a live or reference transaction was found
Naming the fields a digest binds is not the same fact as a demonstrated binding. No canonicalization algorithm, serialization format or independent test of the digest against a live or reference transaction was found, so whether an executed transaction can be proven identical to the one approved remains a missing requirement rather than a closed one.
- Missing requirement
Codex CLI 0.151.0, restored permission profiles and authorization bound Guardian classifications
OpenAI
Codex CLI's own shipped Guardian v2 fix binds a cached tool call classification to the exact authorization state it was scored against, refusing to let a stale classification approve a call once that state has moved. GitHub issue 43549, read through this session's own automated web fetch and summarization tool, reports a materially different gap this record's own reviewed material states nothing about: whether a tool call's own reported terminal status, here the literal status aborted following the caller's own interruption, is checked against the account level effect that call already produced before reporting that status. The reviewed protocol record binds a decision to the state it was made under; it does not, on the material available to this session, bind a call's own reported outcome to the state the call actually left behind.
- Missing requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement The reference implementation ships under a restricted evaluation license, not open source
Demonstrating a binding mechanism in reference code is not the same fact as that mechanism being available for production adoption. This session's own direct read of the reference implementation's LICENSE.md confirms a source-available evaluation license, not open source, explicitly denying production deployment and commercial use and reserving patent rights outside evaluation. Recorded as a missing requirement for anyone evaluating this reference implementation as a buildable corrective rather than as design evidence, not as a claim against the underlying architecture the draft itself describes.