Stripe Payments
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface\n
- Ingestion points: The skill processes external data from Stripe webhook events (e.g.,
payment_intent.succeeded,invoice.payment_failed) and customer-provided information such as names and email addresses used in customer creation flows.\n - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the untrusted data inputs in the provided configuration or code examples.\n
- Capability inventory: The skill utilizes tools including
stripe_charges,stripe_customers,stripe_subscriptions, andstripe_invoices, which have the ability to modify payment records and customer data.\n - Sanitization: No explicit sanitization, validation, or filtering of the external webhook payloads or user inputs is described in the core workflows or automation settings.
Audit Metadata