rafflys-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to add and query the external MCP server (https://rube.app/mcp) and to call RUBE_SEARCH_TOOLS to retrieve tool schemas and execution plans which the agent is explicitly told to read and use to determine tool slugs/arguments for RUBE_MULTI_EXECUTE_TOOL, so untrusted third-party content can directly influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). At runtime the skill requires connecting to the external MCP endpoint https://rube.app/mcp and calling RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS to fetch tool schemas and recommended execution plans that directly control the agent's instructions and tool executions.