stripe-automation

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and calling the Rube MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas that directly influence agent instructions, so this external endpoint controls prompts at runtime.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a Stripe automation toolkit and defines specific payment-related operations (STRIPE_CREATE_PAYMENT_INTENT, STRIPE_POST_CHARGES, STRIPE_CONFIRM_PAYMENT_INTENT, STRIPE_CAPTURE_CHARGE, STRIPE_CREATE_REFUND, STRIPE_POST_CUSTOMERS_CUSTOMER_SUBSCRIPTIONS, STRIPE_CREATE_CHECKOUT_SESSION, etc.). It requires an active Stripe connection and includes actions that create charges, confirm/capture payments, manage subscriptions, and issue refunds — all of which directly move or modify funds. This matches the "Direct Financial Execution" criteria.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:20 AM