The Agent Skills Directory

[DATA_EXPOSURE] (SAFE): The skill implements local data persistence using a file located at ~/.claude/script_writer.json. This access is restricted to the skill's own operational data and does not target sensitive system files or credentials.
[COMMAND_EXECUTION] (SAFE): The Python script script_db.py acts as a data manager. It uses standard json and pathlib libraries for file operations and does not employ dangerous functions like os.system or subprocess.run.
[REMOTE_CODE_EXECUTION] (SAFE): There are no external dependencies defined in the package.json and no code patterns involving the fetching or execution of remote scripts.
[PROMPT_INJECTION] (SAFE): The provided markdown documentation serves as a reference for video formats and contains no instructions designed to bypass agent constraints or safety protocols.

script-writer