The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The execution script scripts/run.py uses standard Python libraries (pathlib, argparse) for file path resolution and directory management. It performs a controlled copy of internal template assets to a specified workspace directory without spawning shell commands or executing arbitrary code.
[PROMPT_INJECTION] (SAFE): No patterns of prompt injection, role-play bypasses, or instructions to ignore safety guidelines were detected in the skill's markdown or template files. The instructional content is restricted to functional guidance for workspace initialization.
[EXTERNAL_DOWNLOADS] (SAFE): The skill does not perform any network requests or download external content. All assets are bundled locally within the assets/workspace-template/ directory.
[DATA_EXFILTRATION] (SAFE): There are no mechanisms for data exfiltration. The script only moves local template files to a user-defined path within the local file system and does not interact with sensitive directories like ~/.ssh or environment variables.

workspace-init