This pack summarizes how AI agents on this account were controlled: limits, human approval, the kill switch, what settled, and how to check that the record wasn't changed. The signed reports it summarizes are inside this file.
Default-deny: only 2 listed actions may run. 3 spending/rate limits enforced on the server. 1 first-time rule (for example new beneficiaries) applies.
2 actions required human approval in the period: 1 approved, 1 denied, 0 expired unanswered (denied). 0 approvals overrode a limit or an untrusted-source flag.
Yes. 12 agent actions in the period are recorded in a hash-chained log; the full log (33 events) verified intact when this report was generated.
Yes: a kill switch freezes all agents, one agent or one action immediately. 0 freezes were active during the period; 0 agent actions were refused while frozen.
9 authorized actions had to be matched by a trusted settlement report: 7 settled as authorized, 1 settled for a different amount or currency, 0 failed or voided, 0 reversed, 0 overdue with no report, 1 still open. 1 imported ledger line matched no authorization.
Policy at the end of the period: version 3 (35f44fad4e89bfac8c0aac5a9d5192ecf905dac47be7914880ebe1632f620ef8), mode enforce, unlisted actions denied. 3 change(s) during the period.
Activity: 12 agent actions, 12 allowed, 0 denied, 2 sent to a human.
1 money-moving action(s) ran after the session had read untrusted content (email, web page, file).
1 possible split payment pattern(s): several payments just under an approval threshold to the same recipient within 24 hours.
| Finding | Count |
|---|---|
| Money-moving actions after reading untrusted content | 1 |
| Actions using data from untrusted sources | 0 |
| Actions that would have gone over a limit | 0 |
| Possible split payments | 1 |
| Authorizations without a settlement report in time | 0 |
Possible split: 3 × create_payout to beneficiary.id=ben_new_vendor_77, total 14,700 against a threshold of 5,000 (2026-11-17T13:20:05.304Z to 2026-11-17T13:20:06.818Z).
| Authorized | Executed | Settled | Mismatch | Failed or voided | Reversed | Overdue | Unmatched ledger lines |
|---|---|---|---|---|---|---|---|
| 9 | 1 | 7 | 1 | 0 | 0 | 0 | 1 |
mismatch: create_payout dec_8797312d5322ff36, authorized 2,750 USD, settled 2,795 USD
| Reference | Topic | Evidence in this pack |
|---|---|---|
| CC6.1 / CC6.3 | Logical access and least privilege | Agent keys cannot approve, change policy or lift freezes; act-only agent keys cannot read the log; approvers use individual tokens. |
| CC7.2 | Monitoring for anomalies | Policy denials by reason code, settlement mismatches and overdue settlements, and webhook alerts. |
| CC7.3 / CC7.4 | Responding to events | Kill switch: 0 freeze(s) in the period, each with who, why and when. |
| CC8.1 | Change management | Every policy version is hash-recorded with who saved it and when (3 change(s) in the period). |
| Reference | Topic | Evidence in this pack |
|---|---|---|
| Access to programs and data | Segregation of duties | Agents cannot approve their own actions; 2 human approval(s), 1 signed with the approver’s own key. |
| Program changes | Authorization limits are changed under control | Policy version history with hashes in the tamper-evident log. |
| Authorization and reconciliation | Disbursements within approved limits, reconciled to settlement | 3 limit(s) enforced on the server; 9 authorization(s) matched against trusted settlement reports. |
| Reference | Topic | Evidence in this pack |
|---|---|---|
| Art. 12 | Record-keeping (automatic logs) | Hash-chained log of every decision, with 1 independent RFC 3161 timestamp(s) in the period; offline-verifiable exports. |
| Art. 14 | Human oversight, including the ability to stop the system | Human approval for actions the policy escalates; kill switch for all agents, one agent or one action. |
| Art. 26(6) | Deployers keep logs for at least six months | Logs are kept until the customer asks for deletion, and can be exported at any time. |
The three reports above are embedded in this file as signed JSON. Anyone can check them offline, without trusting Auditail:
npx -p auditail-sdk auditail-verify auditail-sample-risk-pack.html
The log was verified intact when this was generated (33 events), and 1 independent RFC 3161 timestamp(s) were taken in the period. Public keys: https://api.auditail.io/.well-known/auditail-keys.json.