inngest-realtime

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

• Third-party content exposure detected (low risk: 0.10). This skill’s runtime flow ingests only application-published realtime messages on explicitly chosen channels/topics via useRealtime/subscribe (e.g., OrderStatusClient uses useRealtime({ channel: orderChannel(orderId), topics: ['step'], token: ... })), and it does not describe any mechanism where outsider-authored free text is automatically fetched or consumed without the app selecting a specific message source.

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

• Direct money access detected (high risk: 1.00). The skill includes explicit Stripe payment API calls (stripe.paymentIntents.create and stripe.paymentIntents.confirm) in an example workflow that captures and confirms payments. Those are specific payment gateway operations that enable moving money, so this skill grants direct financial execution capability.