prisma-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires calling RUBE_SEARCH_TOOLS against the external Rube MCP endpoint (https://rube.app/mcp) to fetch tool schemas, execution plans, and recommendations which the agent must read and use to construct tool calls, exposing it to potentially untrusted third-party content that can materially influence actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires contacting the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and recommended execution plans that directly determine agent prompts and tool execution.