The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes task content and descriptions retrieved from the Todoist API, which serves as a vector for indirect prompt injection if those tasks contain malicious instructions.
Ingestion points: Task content, descriptions, and labels retrieved via td task list --json, td task view, and related agenda commands.
Boundary markers: Absent. The instructions do not specify delimiters or warnings to treat task content as untrusted data.
Capability inventory: The skill has the ability to write, update, and delete tasks via the td CLI, and facilitates network communication with the Todoist API.
Sanitization: No sanitization or validation of the retrieved task data is performed before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to download the todoist-cli tool from its official repository on GitHub (https://github.com/Doist/todoist-cli). This is a legitimate requirement for the skill's primary functionality.
[COMMAND_EXECUTION]: The skill executes various shell commands using the td CLI utility to manage Todoist tasks, including listing, creating, modifying, and deleting user data.

todoist-3