The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx @useclawlink/cli, which downloads and executes the ClawLink CLI tool from the public NPM registry at runtime.
[COMMAND_EXECUTION]: The skill functionality relies on the execution of shell commands through the @useclawlink/cli tool to perform actions such as logging in, connecting accounts, and running Todoist actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from a user's Todoist account, creating a surface for indirect prompt injection.
Ingestion points: Data retrieved from Todoist via actions like todoist_get_all_tasks, todoist_get_all_comments, and todoist_filter_tasks (SKILL.md).
Boundary markers: The instructions include a procedural note to "confirm with the user before any write," but there are no technical delimiters or instructions for the agent to ignore embedded commands in the fetched data.
Capability inventory: The skill uses shell command execution (npx) to perform both read and write operations (e.g., creating tasks, archiving projects) (SKILL.md).
Sanitization: The skill instructions do not define any sanitization or filtering protocols for the data fetched from the Todoist API before it is processed by the agent.

todoist