skills/jpropato/siba/file-organizer/Gen Agent Trust Hub

file-organizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill relies on executing various shell commands (ls, find, du, mkdir, mv) to analyze and manipulate the filesystem. While these commands are necessary for the skill's primary purpose, they represent a significant capability tier.
  • DATA_EXPOSURE (LOW): The skill's core functionality involves scanning user directories and file metadata (names, sizes, paths). This exposes the structure and contents of the user's filesystem to the agent.
  • PROMPT_INJECTION (LOW): As a Category 8 Indirect Prompt Injection surface, the skill ingests untrusted data in the form of filenames and file content to 'understand context'.
  • Ingestion points: target_directory paths and file names/types via ls and find commands in SKILL.md.
  • Boundary markers: The instructions mention using markdown blocks for plans, but no explicit delimiters are used to protect the agent from malicious filenames.
  • Capability inventory: The skill uses mv (file-write/move) and various read commands across the instructions.
  • Sanitization: No explicit sanitization of filenames or directory paths is mentioned before interpolation into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM