The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It retrieves and processes data from the Emailoctopus API and has the capability to execute further actions based on that data.
Ingestion points: Data returned from the Emailoctopus API via the Rube MCP tools (SKILL.md).
Boundary markers: There are no instructions to use delimiters or ignore potentially malicious content within the API responses.
Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH for executing tasks (SKILL.md).
Sanitization: The instructions do not include steps for validating or sanitizing the content received from the external API.
[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at https://rube.app/mcp to provide its core functionality.
[COMMAND_EXECUTION]: The skill uses RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform automated actions and manage remote workflows on the Emailoctopus platform.

emailoctopus-automation