The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing the dex CLI to manage task lifecycles, archival, and directory configuration within the agent's environment.
[EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the @zeeg/dex package from the public NPM registry, which serves as the core utility for the skill's functionality.
[PROMPT_INJECTION]: The skill processes task data and external plan files which may contain embedded instructions, creating a surface for indirect prompt injection. 1. Ingestion points: Task data is read via commands like dex show, dex list, and dex plan from repository files and synced external items. 2. Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between data and embedded instructions. 3. Capability inventory: The skill possesses capabilities for repository file manipulation and network synchronization with GitHub and Shortcut APIs. 4. Sanitization: There are no mechanisms described for sanitizing or validating task descriptions or result summaries before they are processed by the agent.

dex