The Agent Skills Directory

[SAFE]: No security issues detected. The skill consists of instructions for integrating with a third-party service and does not contain malicious code or dangerous commands.\n- [NO_CODE]: The skill is entirely composed of Markdown instructions and metadata; it does not ship with any executable scripts or binary files.\n- [EXTERNAL_DOWNLOADS]: The skill mentions the Rube MCP server endpoint (https://rube.app/mcp) and documentation links for Composio. These are legitimate resources for the intended service and are used for manual configuration by the user.\n- [COMMAND_EXECUTION]: The workflow describes the use of specific Model Context Protocol tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. These tools provide a structured and restricted interface for API automation rather than arbitrary shell access.

elorus-automation