file-organizer

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages built-in shell commands such as ls, find, du, md5, mkdir, and mv to explore and organize the file system. These actions are performed within the context of directories provided by the user, such as Downloads or Documents.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present where file names or metadata could influence the agent's logic.
  • Ingestion points: Directory listings and file metadata are gathered via ls, find, and file commands in SKILL.md.
  • Boundary markers: The agent is explicitly instructed to propose an 'Organization Plan' and wait for user confirmation before executing any changes.
  • Capability inventory: File system operations include mkdir, mv, and deletion of duplicate files as described in the instructions.
  • Sanitization: The skill relies on human-in-the-loop verification of the proposed structure and planned changes rather than automated input sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:09 AM
Security Audit — agent-trust-hub — file-organizer