The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill instructs the agent to connect to an external MCP server at https://rube.app/mcp. This domain is not part of the trusted organization list, making it an unverifiable external dependency.
[COMMAND_EXECUTION] (LOW): The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform operations. These capabilities are triggered based on schemas provided by the external MCP server.
[PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill ingests untrusted data from RUBE_SEARCH_TOOLS to determine tool slugs and execution plans.
Ingestion points: Data returned by RUBE_SEARCH_TOOLS and RUBE_GET_TOOL_SCHEMAS in SKILL.md.
Boundary markers: Absent. The skill does not provide instructions to the agent to treat schemas or execution plans as potentially malicious.
Capability inventory: RUBE_MULTI_EXECUTE_TOOL (tool execution), RUBE_REMOTE_WORKBENCH (remote execution environment).
Sanitization: Absent. The agent is instructed to follow the 'exact field names' and 'recommended execution plans' provided by the external tool.

customjs-automation