visa-best-practices

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to fetch arbitrary documentation via HTTP (https://sandbox.mcp.visa.com/mcp/doc/llms.txt), which exposes the agent to outsider-authored free text at low risk.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external code and instructions from sandbox.mcp.visa.com, representing an unverifiable runtime external dependency from a domain with unestablished first-party provenance in this context.