The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several built-in shell commands to interact with the file system, including ls, find, du, mkdir, and mv. These commands are used to scan directories, calculate disk usage, identify file types, and perform file moves or renames. While these are powerful operations, the skill instructions mandate user confirmation before significant changes or deletions are executed.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection through the processing of untrusted file metadata.
Ingestion points: The skill ingests untrusted data in the form of filenames and file type descriptions returned by ls, find, and the file utility.
Boundary markers: There are no explicit boundary markers or XML-style delimiters used when the output of directory listings is interpolated into the agent's context.
Capability inventory: The skill possesses the capability to move files (mv), create directories (mkdir), and potentially delete files (implied in the duplicate removal workflow).
Sanitization: The skill does not implement sanitization or escaping for filenames that might contain malicious instructions intended to influence the agent's subsequent organizational logic.

file-organizer