The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the @useclawlink/cli package from the NPM registry using npx. This tool is the primary interface for the integration.
[COMMAND_EXECUTION]: Shell commands are used to manage the lifecycle of the integration, including login, connect, and run for executing API actions.
[PROMPT_INJECTION]: The skill processes task titles and notes from the Google Tasks API, which constitutes a surface for indirect prompt injection.
Ingestion points: External data enters the agent context through methods such as googletasks_list_tasks and googletasks_get_task in SKILL.md.
Boundary markers: The skill instructs the agent to "confirm with the user before any write," providing a manual safety checkpoint.
Capability inventory: The agent has access to destructive capabilities such as googletasks_delete_task and googletasks_clear_tasks via SKILL.md.
Sanitization: No explicit programmatic sanitization of task content is described.

google-tasks