The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes task content, descriptions, and project data from Todoist via tools like TODOIST_GET_ALL_TASKS and TODOIST_GET_TASK. There are no boundary markers or instructions to ignore embedded commands within this data, which could allow an attacker to influence the agent's behavior through specially crafted task titles or notes.
[EXTERNAL_DOWNLOADS]: The skill directs the agent to connect to an external MCP server at https://rube.app/mcp. While this is the intended method for providing the skill's functionality, it involves routing task data through a third-party service outside the immediate local environment.

todoist-automation