The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill requires the user to add a third-party MCP server at https://rube.app/mcp. This domain is not included in the trusted source list provided in the security skill documentation, representing an external dependency.
[PROMPT_INJECTION] (LOW): The skill possesses a surface for Indirect Prompt Injection (Category 8). Evidence: 1. Ingestion points: The skill ingests untrusted data from the RUBE_SEARCH_TOOLS command, which fetches tool schemas and plans from a remote source. 2. Boundary markers: No delimiters or ignore instructions are specified for the tool discovery results. 3. Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to execute logic based on the remote data. 4. Sanitization: No sanitization or validation of the remote tool definitions is mentioned.

worksnaps-automation