salesforce-marketing-cloud-automation

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow interacts with Salesforce Marketing Cloud via tool execution, which may process customer or campaign data that can contain outsider-authored text.

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 add an external Model Context Protocol server URL (https://rube.app/mcp) at setup, constituting a weak, third-party operational dependency.