visa-best-practices
Warn
Audited by Snyk on Apr 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly instructs fetching https://sandbox.mcp.visa.com/mcp/doc/llms.txt at runtime for "all code examples" and "workflow implementations," which is high-confidence evidence the external file would be fetched and could directly supply instructions or executable code that control agent behavior.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is a specific integration guide for Visa Developer Platform and Visa Intelligent Commerce, including explicit details for card enrollment, purchase instructions, payment credentials, MCP/Visa API endpoints, sandbox/certification/production URLs, and authentication/encryption methods for making API calls. This is expressly about integrating with a payment gateway (Visa) and enabling payment flows, not a generic tool. Therefore it grants direct financial execution capability.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata