12-CONTROL IMPLEMENTATION GUIDE

Agentic commerce security checklist

A production checklist for the moment between an AI agent choosing a purchase and your system executing the order or payment.

Published by MandateShield · Updated July 24, 2026

The boundary in one sentence

Re-evaluate the final purchase against explicit human authority immediately before execution, outside the language model, and retain the outcome.

01

Convert intent into explicit limits

Store a numeric maximum, currency scope, permitted merchant or payee and a short expiry.

02

Identify the acting agent

Use a stable agent ID and protocol-native credential binding instead of a display name.

03

Bind the final merchant

Compare the actual seller or payee at checkout with the approved merchant scope.

04

Evaluate the final total

Include taxes, fees, shipping and currency before checking the hard spending cap.

05

Prove current consent

Tie explicit human consent to the same mandate and material checkout facts.

06

Keep authority short-lived

Reject expired mandates and review unusually long authorization windows.

07

Bind intent to execution

Carry a digest of the approved intent or cart so material changes cannot pass silently.

08

Enforce outside the model

Do not ask the language model to decide whether its own payment should bypass policy.

09

Consume each attempt once

Persist an idempotency key behind an atomic uniqueness constraint across retries and regions.

10

Fail closed on missing evidence

Use REVIEW or BLOCK when identity, intent, merchant or currency evidence is absent.

11

Retain minimal decision evidence

Store decision, reason codes and receipt without card numbers or personal shopping data.

12

Keep fraud and processing separate

Run authorization alongside—not instead of—fraud, sanctions and processor controls.

Turn the checklist into a test

Score the current architecture, then run a live purchase against overspend, merchant substitution, expired authority, missing consent and prompt injection.