file-organizer

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including find, du, ls, mv, and mkdir to analyze and modify the local filesystem. While these are appropriate for the skill's stated purpose of file organization, they represent a significant capability tier.
  • [PROMPT_INJECTION]: The skill handles untrusted data from the local environment (filenames and file metadata) which provides a surface for indirect prompt injection.
  • Ingestion points: Filesystem metadata such as filenames, directory names, and file type information are ingested via find, ls, and file commands.
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions potentially contained within filenames or metadata.
  • Capability inventory: The skill allows for directory creation (mkdir), file movement (mv), and identifying files for deletion based on the ingested metadata.
  • Sanitization: Absent. There is no logic provided to escape, validate, or filter filesystem data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 07:52 AM
Security Audit — agent-trust-hub — file-organizer