visa-acceptance-best-practices

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires fetching and reading the public page https://developer.visaacceptance.com/llms.txt before answering or writing code, so external third-party webpage content can directly influence the agent's actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching and reading https://developer.visaacceptance.com/llms.txt at runtime and using its contents to guide responses, so external content directly controls prompts and is a required dependency.

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

• Direct money access detected (high risk: 1.00). This skill is explicitly designed for payment gateway integration and transaction handling. It guides accepting payments, payment processing (card and in-person), integrating digital wallets (Apple/Google Pay), recurring billing/stored credentials, webhooks/security keys, and platform services. It references REST APIs, sandbox API keys, and authentication details — concrete, payment-specific interfaces used to process transactions. This is not a generic tool; its primary purpose is moving/processing money.