Immutable solution version
Stripe: require human approval before an agent moves live money
Complete solution
The blocker for agent-driven payments is trust, not knowledge. This skill defines the approval-gate pattern: which operations need a human, how restricted keys enforce it technically, and how to structure propose-then-approve agent workflows.
Stripe: human approval gates before live money moves
No skill makes an agent trustworthy with money. What works is making the untrusted action technically impossible without a human. That is what approval gates are.
What needs a human
- Any charge, capture, or subscription creation in live mode.
- Refunds above a threshold the operator sets (e.g. anything over $50, or any refund at all).
- Creating or rotating API keys.
- Changing webhook endpoints or payout settings.
- Anything the agent has not done before in test mode successfully.
Test-mode work needs no gate. Exploration and building are free; moving live money is not.
How to enforce it technically
Do not rely on the agent "remembering to ask". Enforce with keys:
- The agent gets a restricted test key, or a restricted live key with read-only permissions.
- Live write permissions live only in a key the operator holds, never in the agent's context.
- The agent's workflow becomes propose-then-approve: it prepares the exact API call (endpoint, parameters, amount, idempotency key), presents it, and the operator executes or approves it.
- Log every proposal and every approval with timestamps. The audit trail is the product.
The propose-then-approve shape
When the agent needs a live operation, it outputs:
- The exact operation and parameters.
- The amount, currency, and destination customer.
- The idempotency key it generated.
- What it verified in test mode first.
The operator reviews and runs it, or pastes back an approval token. The agent never holds live write credentials.
Blast radius limits
Even with gates, set Stripe Dashboard limits: restricted key permissions, webhook signing, and alerts on unusual volume. A gate the operator sleeps through is not a gate; pair approvals with amount caps so a mistaken approval cannot empty an account.
Evidence
This skill is Vectle-original safety guidance, built on Stripe's own mechanism: restricted API keys "with specific API permissions" where "using a restricted API key with only a subset of API permissions limits the damage a bad actor could cause if they obtained the key" (docs.stripe.com/api/authentication). Stripe documents the key mechanism; the approval-gate pattern (agent proposes exact calls, human holds live write credentials, audit trail) is the trust layer Stripe's human-oriented docs do not define and agents need. Verified mechanism against live docs 2026-09-26.
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_KhItb6Gw-9icIYkBF9TJUQ" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Stripe: require human approval before an agent moves live money <span>— Vectle</span></a>