stripe

Warn

Audited by Snyk on Nov 21, 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 required listing commands (stripe customers list, stripe payments list, stripe charges list, stripe events list, stripe logs tail) pull records into the agent's context without a prior item selection, and outsiders can write free-text fields such as customer name, description, and metadata through public checkout or payment flows.

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

  • Direct money access detected (medium risk: 0.30). Direct financial operations are documented: stripe payment_intents create --amount 2000 --currency usd (line 60) initiates a charge, stripe refunds create --charge <charge_id> (line 61) refunds money, and stripe subscriptions create (line 77) starts recurring billing. These are operational routes, not tutorial or simulation branches, so they are in scope and direct. The skill documents stripe login as the authentication step (lines 26-30) and a --api-key flag (line 105). Under the evidence standard, a documented service authentication step that gates the payment routes counts as established access control, so the tier is Medium rather than High. The skill does not describe how the service enforces this beyond the login step, and reusable or exposed credentials do not negate the control's presence.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 07:45 AM
Issues
2