The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell utilities (ls, find, du, md5, mkdir, mv) to analyze and reorganize the local file system. This functionality is the primary purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes file names and metadata as untrusted input. If a directory contains files with maliciously crafted names (e.g., containing shell metacharacters like semicolons or backticks), there is a potential risk of command injection when the agent executes the suggested organization scripts.
Ingestion points: File names and metadata are retrieved via ls, find, and du (SKILL.md).
Boundary markers: The instructions recommend presenting a plan to the user and asking for confirmation before executing changes, which provides a manual check.
Capability inventory: The skill uses mkdir and mv to modify the file system and md5 to read file content (SKILL.md).
Sanitization: There is no explicit instruction to sanitize or escape file names before they are used in shell commands.

file-organizer