Approval replay in agent workflows

Approval replay occurs when an old approval is accepted again or applied to different parameters, targets or tasks.

01 / Attack path

How the boundary is crossed

A reviewer approves one $8,000 payment, but the agent retries with the same approval after a timeout and sends a second transfer.

Attack path and interception point
  1. 01Lower-trust input
  2. 02Attempted instruction
  3. 03Protected action
  4. 04Enforced decision

02 / Containment

Where bounded authority limits the effect

Bind approval to action hash, task, target, maximum use count and expiry; reconcile uncertain outcomes before permitting any retry.

Architecture review / negative test

Make the boundary testable.

The attacker or faulty agent reuses an approval outside its original scope. Bind it to canonical arguments and a single consumption rule, then combine with idempotency and outcome reconciliation. One-time approval alone cannot tell whether a timed-out call succeeded; a retry policy needs both authorization and transaction state.

03 / Failure and evidence

The attacker’s opportunity and the defender’s record

Exploit condition

An approval token is treated as a reusable scope instead of a single bounded consent.

Evidence to retain

Retain approval consumption, idempotency key, both attempts and authoritative transfer status.

04 / Canonical scope

Why this reference stands alone

Human approval page covers the approval path; this threat page owns replay exploit and failure analysis.

Primary references

Read the underlying material

Architecture discussion

Choose one consequential action and make its boundary explicit.

Request a Conversation