make-mcp-reference

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Configuring Scenarios as MCP Tools" instructions indicate the agent will connect to the Make MCP server (e.g., https://mcp.make.com and zone-specific URLs like https://<MAKE_ZONE>/mcp/u/<MCP_TOKEN>) and read scenario descriptions/inputs (user-authored content) as tool parameters, which the agent must interpret and can materially influence its 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 runtime connections to Make MCP endpoints (e.g., https://mcp.make.com and zone-specific URLs like https://<MAKE_ZONE>/mcp/u/<MCP_TOKEN>) which are used to invoke/run scenarios on the remote platform (i.e., execute remote code) and are presented as the required integration endpoints.