The Agent Skills Directory

[SAFE]: The skill utilizes standard command-line tools (ls, find, du, mv, mkdir) to perform file management tasks that are central to its stated purpose. These operations are executed within the scope of the user-requested directories.
[SAFE]: The skill's instructions explicitly require user confirmation before deleting any files or implementing a proposed organization plan, which serves as a safeguard against unintended data loss.
[SAFE]: No evidence of network exfiltration, hardcoded credentials, or remote code execution was found. The skill operates locally on the user's file system.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of filenames and metadata (via ls and find). While malicious filenames could theoretically attempt to influence the agent's behavior, the risk is minimal as the skill's logic is focused on structural organization and always involves a 'Propose Plan' stage where the user reviews changes before execution.

file-organizer