mp-checkout-online

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to consult the external Mercado Pago MCP server ("mercadopago") and to fetch public docs at "{DOMAIN}/developers/{LANG}/docs/..." for SDK code, endpoints, payload schemas, and test cards, meaning the agent will read and act on public third-party web content that can influence its actions.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly a payment-gateway integration for Mercado Pago. It documents Checkout API and Checkout Pro flows, server-to-server "create payment" calls, card tokenization, handling of non-card methods (Pix, Boleto, OXXO, PSE, bank transfers), payment status handling, required access token, webhooks/notification_url, and fields like preference/init_point/payment.create. Those are concrete APIs and operations to initiate and manage real payments (move money), not generic tooling. Therefore it grants direct financial execution capability.