mailchimp-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill routinely calls Mailchimp APIs that return user-generated content (e.g., the required MAILCHIMP_GET_LISTS_INFO call to fetch audience/list names and members and the MAILCHIMP_GET_CAMPAIGN_CONTENT endpoint to retrieve campaign HTML) and instructs the agent to read/resolve those results as part of workflows, so untrusted third-party content can influence ID resolution and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires adding and calling the external MCP server https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly determine agent instruction/tool behavior, making it a required runtime dependency that can control prompts.