stigg-widgets

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow explicitly instructs fetching public Storybook content from https://widgets.stigg.io/index.json and then opening/supplementing with per-widget docs pages on docs.stigg.io, which are outsider-authored web sources whose readable text can be ingested into the agent’s LLM context.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly a billing/payments UI toolkit: it provides Paywall, Checkout, Customer Portal, PaymentDetailsSection, Invoices, credit-balance and auto-recharge widgets, and references checkout/payment flows. Those components are specifically designed to initiate and manage payment-related operations (checkout, subscriptions, credit recharges) even though the docs highlight using a publishable client key and server-side protections. Because the primary intent and APIs target payment/billing flows (checkout, invoices, auto-recharge), this qualifies as direct financial execution capability.