stripe
Warn
Audited by Snyk on Oct 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The Stripe integration skill allows fetching customer data, invoices, and events from a Stripe account, which can contain user-submitted free text from external customers.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an external npm package (
@membranehq/cli), which constitutes an operational dependency without sufficient first-party provenance.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill provides integration with Stripe via the Membrane CLI, supporting payment processing and financial management operations including handling transactions, subscriptions, payouts, and running arbitrary API requests/actions through the
membrane action runandmembrane requestcommands. These constitute direct financial operations. The skill relies on Membrane authentication (membrane login,membrane connection ensure), but lacks qualifying independent, service-enforced access control on the financial execution routes themselves (i.e., no separate transaction authorization or independent payment-gate validation enforced by the execution layer beyond standard API connection auth).
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata