ninox-automation

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow calls RUBE_SEARCH_TOOLS (and potentially RUBE_GET_TOOL_SCHEMAS) against the external Rube MCP server, which can return tool schemas/content as readable text that the agent ingests into its LLM context; this is outsider-authored (Rube/Composio) data not authored by the operating user.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime connection to the external MCP endpoint https://rube.app/mcp to perform RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS / RUBE_MULTI_EXECUTE_TOOL calls that discover and invoke remote tool logic (i.e., executing remote tool actions that control agent behavior), so this URL is a required runtime dependency that can execute remote code/control prompts.