The Agent Skills Directory

[SAFE]: No malicious patterns detected across the analyzed skill instructions.
[COMMAND_EXECUTION]: The skill utilizes standard Unix utilities including ls, find, du, mkdir, and mv to analyze directory structures and reorganize files. These operations are consistent with the skill's stated purpose of file management and are executed with explicit instructions for user confirmation.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data in the form of file names and system metadata. However, the risk is mitigated by instructions requiring the agent to present a clear organization plan and obtain user approval before executing any file moves or deletions.
Ingestion points: Reads directory contents and file metadata via ls, find, and du commands (SKILL.md).
Boundary markers: Uses markdown-formatted plans to separate analysis from proposed actions.
Capability inventory: File system write/move access via mkdir and mv, and potential deletion via user-confirmed rm patterns.
Sanitization: Instructions emphasize handling filename conflicts gracefully and logging moves for potential undo.

file-organizer