An AI agent receives approval to send a document to a team. Before it executes, the document changes, the team’s address points somewhere else, or permission is revoked. The request can retain the same words while its effect changes. We call this authorization drift: an approved operation no longer matches what execution would do.

We evaluated six executor controls against the same constructed histories, then tested what happens when delivery is interrupted. The results separate two requirements: keep permission valid at commitment, and make recovery preserve the identity of an approved effect.

Two boundaries, measured separately

Histories per executor control
2,880
Six controls face the same requests, changes and schedules.
Unauthorized effects with atomic validation
0
Both atomic controls recorded zero across their constructed histories.
Valid opportunities preserved
80/80
The atomic check of relevant policy completed every valid opportunity.
Recovery cases with one approved effect
15/15
A durable pending job and an idempotent receiver preserve one effect.
The authorization results use constructed histories; the recovery results use designed interruption cases.

Zortex Research. Authorization-drift and crash-recovery experiments.

Approval has to survive execution

Permission to use a document-sharing tool does not identify the document, its version, its contents or its recipient. Even binding every request argument leaves a gap when an argument names something mutable. “Current report” and “team” can resolve differently after approval.

The problem is related to time-of-check to time-of-use failures: an earlier check can be correct while the state used at execution has changed.[1] Our study asks which observations must remain connected to the moment an effect is committed.

A controlled test of changing authority

We evaluated six executor controls around one operation, send_document, which appends a concrete effect to a local log. A trusted fixture specifies the approved document version, payload, recipient, purpose, authenticated context, expiry and one-use allowance. The test driver supplies candidate calls and scheduled state changes; no language-model inference is involved.

Ten request variants, twelve changes before preparation, twelve changes after preparation and two execution schedules produce 2,880 histories for each control. The schedules include two callers preparing against the same one-use permission. The checker examines actual recorded effects against the original approval.

Checking the effect at commitment

Authorization failures

Request binding reduced the number of unsafe histories from 2,592 to 320, but left changes to resolved resources and policy unchecked. Full validation during preparation left 128 unsafe histories when state changed afterwards. Validating current state while retaining an earlier one-use decision left 40 unsafe histories under concurrent preparation.

Unauthorized effects under six executor controls

Unauthorized effects under six executor controlsHistories out of 2,880. Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better. Exact values follow under View data. 01,0002,000 Tool allowlistExact request bindingValidation at preparationCached one-use checkAtomic check: global policyAtomic check: relevant policy Histories out of 2,880 Tool allowlist · Unauthorized-effect histories: 2,592 Histories out of 2,880 2,592Exact request binding · Unauthorized-effect histories: 320 Histories out of 2,880 320Validation at preparation · Unauthorized-effect histories: 128 Histories out of 2,880 128Cached one-use check · Unauthorized-effect histories: 40 Histories out of 2,880 40Atomic check: global policy · Unauthorized-effect histories: 0 Histories out of 2,880 0Atomic check: relevant policy · Unauthorized-effect histories: 0 Histories out of 2,880 0
Unauthorized effects under six executor controlsHistories out of 2,880. Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better. Exact values follow under View data. 01,0002,000 Tool allowlistExact request bindingValidation at preparationCached one-use checkAtomic check: global policyAtomic check: relevant policy Histories out of 2,880 Tool allowlist · Unauthorized-effect histories: 2,592 Histories out of 2,880 2,592Exact request binding · Unauthorized-effect histories: 320 Histories out of 2,880 320Validation at preparation · Unauthorized-effect histories: 128 Histories out of 2,880 128Cached one-use check · Unauthorized-effect histories: 40 Histories out of 2,880 40Atomic check: global policy · Unauthorized-effect histories: 0 Histories out of 2,880 0Atomic check: relevant policy · Unauthorized-effect histories: 0 Histories out of 2,880 0
Unauthorized effects under six executor controlsHistories out of 2,880. Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better. Exact values follow under View data. 01,0002,000 Tool allowlistExact requestbindingValidation atpreparationCachedone-use checkAtomic check:global policyAtomic check:relevant policy Histories out of 2,880 Tool allowlist · Unauthorized-effect histories: 2,592 Histories out of 2,880 2,592Exact request binding · Unauthorized-effect histories: 320 Histories out of 2,880 320Validation at preparation · Unauthorized-effect histories: 128 Histories out of 2,880 128Cached one-use check · Unauthorized-effect histories: 40 Histories out of 2,880 40Atomic check: global policy · Unauthorized-effect histories: 0 Histories out of 2,880 0Atomic check: relevant policy · Unauthorized-effect histories: 0 Histories out of 2,880 0
Unauthorized effects under six executor controlsHistories out of 2,880. Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better. Exact values follow under View data. 02,000 ToolallowlistExactrequestbindingValidation atpreparationCachedone-usecheckAtomiccheck:global policyAtomiccheck:relevantpolicy Histories out of2,880 Tool allowlist · Unauthorized-effect histories: 2,592 Histories out of 2,880 2,592Exact request binding · Unauthorized-effect histories: 320 Histories out of 2,880 320Validation at preparation · Unauthorized-effect histories: 128 Histories out of 2,880 128Cached one-use check · Unauthorized-effect histories: 40 Histories out of 2,880 40Atomic check: global policy · Unauthorized-effect histories: 0 Histories out of 2,880 0Atomic check: relevant policy · Unauthorized-effect histories: 0 Histories out of 2,880 0
Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better.

Zortex Research. Authorization-drift study, Experiment A.

View methods

Ten request variants × twelve changes before preparation × twelve changes after preparation × two schedules produce 2,880 histories per control. An independently implemented checker compares the committed effect with the approved document, recipient, context, policy, lifetime and one-use allowance. The driver constructs requests directly; these counts measure enforcement under the declared execution contract.

View data
Histories out of 2,880
ConditionUnauthorized-effect histories
Tool allowlist2,592
Exact request binding320
Validation at preparation128
Cached one-use check40
Atomic check: global policy0
Atomic check: relevant policy0

Unauthorized effects under six executor controls

Histories containing at least one unauthorized effect. Each control runs on the same 2,880 constructed histories. Lower is better.

The two successful controls validate the current effect, current authority and remaining allowance under the same lock that records consumption and the effect. The values being checked are therefore the values used at commitment.

Preserving valid work

A control that rejects every request would also record no unauthorized effects. We therefore count valid opportunities separately: histories where the approved action satisfies the contract at commitment.

A global policy version rejects an approval after any policy change, including an unrelated one. It missed 28 of 80 valid opportunities. Checking the policy relevant to the approved action missed zero, with the same zero-violation result. The scoped control uses a complete, explicitly supplied list of the action’s policy and resource dependencies.

Safe execution must also preserve valid work

  • Completed valid work
  • Missed valid work
Safe execution must also preserve valid workValid opportunities out of 80. Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80. Exact values follow under View data. 020406080 Validation at preparationAtomic: global policyAtomic: relevant policy Valid opportunities out of 80 Validation at preparation · Completed valid work: 72 Valid opportunities out of 80 72Validation at preparation · Missed valid work: 8 Valid opportunities out of 80 8Atomic: global policy · Completed valid work: 52 Valid opportunities out of 80 52Atomic: global policy · Missed valid work: 28 Valid opportunities out of 80 28Atomic: relevant policy · Completed valid work: 80 Valid opportunities out of 80 80Atomic: relevant policy · Missed valid work: 0 Valid opportunities out of 80 0
Safe execution must also preserve valid workValid opportunities out of 80. Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80. Exact values follow under View data. 020406080 Validation at preparationAtomic: global policyAtomic: relevant policy Valid opportunities out of 80 Validation at preparation · Completed valid work: 72 Valid opportunities out of 80 72Validation at preparation · Missed valid work: 8 Valid opportunities out of 80 8Atomic: global policy · Completed valid work: 52 Valid opportunities out of 80 52Atomic: global policy · Missed valid work: 28 Valid opportunities out of 80 28Atomic: relevant policy · Completed valid work: 80 Valid opportunities out of 80 80Atomic: relevant policy · Missed valid work: 0 Valid opportunities out of 80 0
Safe execution must also preserve valid workValid opportunities out of 80. Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80. Exact values follow under View data. 020406080 ValidationatpreparationAtomic:globalpolicyAtomic:relevantpolicy Valid opportunities out of 80 Validation at preparation · Completed valid work: 72 Valid opportunities out of 80 72Validation at preparation · Missed valid work: 8 Valid opportunities out of 80 8Atomic: global policy · Completed valid work: 52 Valid opportunities out of 80 52Atomic: global policy · Missed valid work: 28 Valid opportunities out of 80 28Atomic: relevant policy · Completed valid work: 80 Valid opportunities out of 80 80Atomic: relevant policy · Missed valid work: 0 Valid opportunities out of 80 0
Safe execution must also preserve valid workValid opportunities out of 80. Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80. Exact values follow under View data. 020406080 ValidationatpreparationAtomic:globalpolicyAtomic:relevantpolicy Valid opportunities out of 80 Validation at preparation · Completed valid work: 72 Valid opportunities out of 80 72Validation at preparation · Missed valid work: 8 Valid opportunities out of 80 8Atomic: global policy · Completed valid work: 52 Valid opportunities out of 80 52Atomic: global policy · Missed valid work: 28 Valid opportunities out of 80 28Atomic: relevant policy · Completed valid work: 80 Valid opportunities out of 80 80Atomic: relevant policy · Missed valid work: 0 Valid opportunities out of 80 0
Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80.

Zortex Research. Authorization-drift study, Experiment A.

View methods

A valid opportunity is a history in which the original approval still permits the action at commitment. The independent checker identifies 80 such histories for each control. Completed and missed opportunities partition those same 80 histories. A global policy version can invalidate an approval after an unrelated change; the relevant-policy check uses the action’s declared dependencies.

View data
Valid opportunities out of 80
ConditionCompleted valid workMissed valid work
Validation at preparation728
Atomic: global policy5228
Atomic: relevant policy800

Safe execution must also preserve valid work

Each control encounters the same 80 histories in which the approved action is valid at commitment. The relevant-policy check completes all 80.

What the counterexamples show

The failure traces distinguish changes to meaning, changes to permission and repeated consumption. Each requires a different part of the execution contract.

Three ways approval and execution diverge

Representative counterexamples from the constructed histories.

Mutable state

The request stays the same. The recipient changes.

At approval
Team alias points to recipient A
At commitment
The same alias points to recipient B
Explore example

An approved call names a team alias. The alias points to a new recipient before the call commits. Exact request matching accepts the same words while the effect sends the document somewhere else.

  1. Approve the document and its original recipient.
  2. Prepare the unchanged request.
  3. Retarget the recipient alias.
  4. Execute against the new alias value.

Required check: compare the currently resolved recipient with the approved recipient at commitment.

Revocation

An earlier check outlives its permission.

At preparation
Relevant permission is active
At commitment
Permission is revoked; the effect still occurs
Explore example

Preparation validates the complete action. The relevant permission is then revoked. A commit that checks only the remaining allowance still performs the now-unauthorized effect.

  1. Validate the action under the initial policy.
  2. Revoke the relevant permission and advance its policy version.
  3. Consume the unused allowance and record the effect.

Required check: validate current permission and the approval’s policy version in the same operation that commits the effect.

Concurrency

Two callers see one unused permission.

At preparation
Two callers see one unused allowance
At commitment
One approved effect and one extra effect
Explore example

Both callers prepare before either consumes the one-use allowance. If each retains that earlier observation, both can execute even when the document and recipient remain correct.

  1. The first caller observes an unused allowance.
  2. A second caller observes the same unused allowance.
  3. The first caller commits one authorized effect.
  4. The second caller commits an extra effect.

Required check: couple the current allowance check and consumption atomically.

Recovery across a process boundary

A receiving system can commit an effect before the executor records completion. If acknowledgement disappears, a retry must distinguish “nothing happened” from “it happened, but the reply was lost.” A local authorization transaction cannot settle that question by itself.

Where retries fail

We tested three recovery mechanisms using separate broker and receiver processes, each with its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt.

What survives an interrupted delivery

All conditions

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 12 Cases · 80.0% of 15 Cases 80%Reserve before send · Lost effect: 3 Cases · 20.0% of 15 Cases 20%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 15 Cases Send before record · One approved effect: 9 Cases · 60.0% of 15 Cases 60%Send before record · Lost effect: 0 Cases · 0.0% of 15 Cases Send before record · Duplicate effect: 6 Cases · 40.0% of 15 Cases 40%Durable job + idempotent receiver · One approved effect: 15 Cases · 100.0% of 15 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 15 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 15 Cases
What survives an interrupted deliveryShare of total (%). Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 12 Cases · 80.0% of 15 Cases 80%Reserve before send · Lost effect: 3 Cases · 20.0% of 15 Cases 20%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 15 Cases Send before record · One approved effect: 9 Cases · 60.0% of 15 Cases 60%Send before record · Lost effect: 0 Cases · 0.0% of 15 Cases Send before record · Duplicate effect: 6 Cases · 40.0% of 15 Cases 40%Durable job + idempotent receiver · One approved effect: 15 Cases · 100.0% of 15 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 15 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 15 Cases
What survives an interrupted deliveryShare of total (%). Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 12 Cases · 80.0% of 15 Cases 80%Reserve before send · Lost effect: 3 Cases · 20.0% of 15 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 15 Cases Send before record · One approved effect: 9 Cases · 60.0% of 15 Cases 60%Send before record · Lost effect: 0 Cases · 0.0% of 15 Cases Send before record · Duplicate effect: 6 Cases · 40.0% of 15 Cases 40%Durable job + idempotent receiver · One approved effect: 15 Cases · 100.0% of 15 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 15 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 15 Cases
What survives an interrupted deliveryShare of total (%). Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 12 Cases · 80.0% of 15 Cases 80%Reserve before send · Lost effect: 3 Cases · 20.0% of 15 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 15 Cases Send before record · One approved effect: 9 Cases · 60.0% of 15 Cases 60%Send before record · Lost effect: 0 Cases · 0.0% of 15 Cases Send before record · Duplicate effect: 6 Cases · 40.0% of 15 Cases 40%Durable job + idempotent receiver · One approved effect: 15 Cases · 100.0% of 15 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 15 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 15 Cases
Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send1280.0%320.0%00.0%
Send before record960.0%00.0%640.0%
Durable job + idempotent receiver15100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: All conditions

Five conditions, three repetitions each: 15 cases per mechanism. Segments show each outcome’s share; View data retains the case counts.

Normal completion

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send3100.0%00.0%00.0%
Send before record3100.0%00.0%00.0%
Durable job + idempotent receiver3100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: Normal completion

Normal completion: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Before delivery

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Lost effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Lost effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Lost effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Lost effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send00.0%3100.0%00.0%
Send before record3100.0%00.0%00.0%
Durable job + idempotent receiver3100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: Before delivery

Before delivery: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

After receiver commit

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send3100.0%00.0%00.0%
Send before record00.0%00.0%3100.0%
Durable job + idempotent receiver3100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: After receiver commit

After receiver commit: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

After acknowledgement

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 0 Cases · 0.0% of 3 Cases Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send3100.0%00.0%00.0%
Send before record00.0%00.0%3100.0%
Durable job + idempotent receiver3100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: After acknowledgement

After acknowledgement: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

After completion record

  • One approved effect
  • Lost effect
  • Duplicate effect
What survives an interrupted deliveryShare of total (%). After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%75%100% Reserve before sendSend before recordDurable job + idempotent receiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%25%50%100% Reserve beforesendSend beforerecordDurable job +idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
What survives an interrupted deliveryShare of total (%). After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts. Exact values follow under View data. 0%50%100% Reservebefore sendSend beforerecordDurable job+idempotentreceiver Share of total (%) Reserve before send · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Reserve before send · Lost effect: 0 Cases · 0.0% of 3 Cases Reserve before send · Duplicate effect: 0 Cases · 0.0% of 3 Cases Send before record · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Send before record · Lost effect: 0 Cases · 0.0% of 3 Cases Send before record · Duplicate effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · One approved effect: 3 Cases · 100.0% of 3 Cases 100%Durable job + idempotent receiver · Lost effect: 0 Cases · 0.0% of 3 Cases Durable job + idempotent receiver · Duplicate effect: 0 Cases · 0.0% of 3 Cases
After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Zortex Research. Authorization-drift study, Experiment B.

View methods

Three mechanisms were tested with separate broker and receiver processes, each using its own SQLite database. Five conditions cover normal completion and four interruption points. Each condition has three fresh-database repetitions and one uninterrupted recovery attempt. All 45 planned cases completed without an unexpected failure or timeout. The selector shows either all 15 cases per mechanism or the three cases at one interruption point. The proportions describe these designed cases; they are not an estimated production failure rate. Separate SQL inspection checks the identity and number of effects in the receiver database.

View data
CasesOriginal observations; normalized shares are shown separately.
ConditionOne approved effectOne approved effect (%)Lost effectLost effect (%)Duplicate effectDuplicate effect (%)
Reserve before send3100.0%00.0%00.0%
Send before record3100.0%00.0%00.0%
Durable job + idempotent receiver3100.0%00.0%00.0%

What survives an interrupted delivery

Interruption point: After completion record

After completion record: three fresh-database cases per mechanism, followed by one uninterrupted recovery attempt. Segments show outcome shares; the data table gives the original counts.

Reserving permission before sending lost work in 3 of 15 cases when execution stopped before delivery. Sending before recording completion duplicated effects in 6 of 15 cases when delivery succeeded but acknowledgement or the completion record was interrupted.

The third mechanism preserves a durable pending job, a stable identifier and a bound payload. The receiver atomically recognizes repeated delivery and returns its existing receipt. That contract yielded one approved effect in all 15 cases. The receiver’s durable key-and-payload binding is part of the mechanism being evaluated.

Verification

How the results were checked

The core study covers 17,280 control–history evaluations, plus 120 forced two-thread cases and 54 parser cases. A separate checker reconstructs state changes, concrete effects and valid opportunities directly from the execution records. The retained rerun matches every history and all thread and parser outcomes.

For the recovery experiment, separate SQL inspection checks the identity and number of effects in each receiver database. All 45 designed cases completed without an unexpected failure or timeout. Expected injected process exits remain part of the observed results.

The execution contract

CaMeL places enforceable controls around untrusted model computation.[2] CapLease studies durable authorization and replay, including the receiver’s role in preventing repeated external effects.[3] Permission to Retry separates current authority, provider contracts and retained observations during recovery.[4] Our experiments isolate these concerns through matched controls, explicit state changes and direct observation of committed effects.

The results identify two boundaries an executor must connect. At local commitment, it must validate the current effect and authority while consuming the allowance. Across a process boundary, it must retain enough state—and obtain the receiver guarantees needed—to distinguish a repeated attempt from a new authorized effect.


References

  1. Derek Lilienthal and Sanghyun Hong. Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents. 2025. ↩︎

  2. Edoardo Debenedetti et al. Defeating Prompt Injections by Design. 2025. ↩︎

  3. Jinghan Xu et al. Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions. 2026. ↩︎

  4. Deekshith Marla and Kushagra Bhatnagar. Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows. 2026. ↩︎