The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several standard shell utilities including ls, find, du, mkdir, mv, and md5 to perform file system analysis and manipulation as its primary function.
[COMMAND_EXECUTION]: To mitigate risks associated with automated file operations, the instructions explicitly require the agent to obtain user confirmation before deleting or moving files and to provide a clear summary of proposed changes before execution.
[PROMPT_INJECTION]: The skill processes untrusted data in the form of local file names and metadata during directory analysis, which constitutes an indirect prompt injection surface. Ingestion points: File system paths and names are read via ls and find commands (SKILL.md). Boundary markers: No explicit delimiters or instructions to ignore embedded content in file names are provided to the model. Capability inventory: The skill has the capability to move (mv), create folders (mkdir), and potentially delete files based on its logic (SKILL.md). Sanitization: There is no mention of escaping or validating file names before they are processed by the agent.

file-organizer