creating-webhook-handlers

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and parses webhook payloads from external providers (e.g., Stripe, GitHub, Twilio, Slack) as shown in the Overview and Instructions (POST /webhooks/:provider capturing raw_body, parsing event.type, and dispatching handlers), so untrusted third-party content can directly influence routing and processing actions.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly targets payment gateways (mentions Stripe and uses stripe.webhooks.constructEvent()) and describes handling payment events like payment_intent.succeeded and charge.refunded to fulfill orders and process refunds. Those are provider-specific payment operations (financial execution-related), not just generic webhook handling. Therefore it qualifies as Direct Financial Execution capability.