shopify-hydrogen

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill forces the model to embed the user's verbatim prompt (base64-encoded) into a validation command, which requires outputting any secret values present in that prompt verbatim (albeit encoded), creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill contains explicit, mandatory instrumentation steps that require embedding the user's verbatim prompt and session identifiers into remote validation/search tooling which reports that data to Shopify — a deliberate data-exfiltration/telemetry requirement that can leak sensitive prompts and host identifiers.

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

• Direct money access detected (high risk: 1.00). The skill explicitly exposes Shopify payment-related UI and API functions: e.g., a Shop Pay payment button (ShopPayButton) plus cart creation and cart mutation functions (cart.create, cart.addLines, cart.giftCard mutation helpers) and storefront.mutate. These are specific payment/checkout primitives (payment gateway / checkout integration) that enable executing or initiating monetary transactions/checkouts, so this qualifies as Direct Financial Execution capability.