Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Безопасное подтверждение платежей AI-агента: четыре проверяемых рубежа

说明与用途

该原型展示了四个安全层(受限会话、意图绑定、身份验证单次批准和外部签名)如何保护支付 AI 代理,防止替换、重放和绕过批准检查的攻击。

问题

Modal approval in payment AI agents does not prove identity, binding, freshness, or prevent credential misuse, leading to potential fraud.

结果

The prototype demonstrates that each security layer prevents specific attack vectors; removing any layer causes the corresponding test to fail.

工作流

  • 1. Create a bounded session with payee allowlist, currency, limits, expiry, and approver public key.
  • 2. Agent requests payment; signer builds intent and stores it.
  • 3. Signer computes intent_hash and signs a domain-separated message with approver’s private key.
  • 4. Approver verifies signature, checks nonce, and ensures single-use.
  • 5. Signer executes intent only after all checks pass, using external signing to access payment credentials.
  • 6. Tests run with pytest to ensure each layer fails if removed.

证据

Secure human approval for a payment agent: bounded session, intent binding, authenticated one-time approval and external signing, each one with a test you can run.

来源

The agent never gets general payment capability. It gets a session, a narrow and expiring grant created by a human or an admin process.

来源

The signer builds a payment intent and stores it. The intent records payee ID, amount, currency, reference, session ID and a fresh intent ID.

来源

The approval is an Ed25519 signature made with a private key that only exists on the approver's device.

来源

  • 记录日期: 2026-10-07T18:55:58.575Z