file-organizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected.
  • Ingestion points: Target directories (e.g., Downloads, Documents, Home folder) where the skill reads filenames, paths, and metadata from the local file system.
  • Boundary markers (absent): The skill instructions do not specify the use of delimiters or 'ignore' instructions when processing file lists or metadata.
  • Capability inventory: The skill uses file system operations including mv (moving), renaming, and deletion of files.
  • Sanitization (absent): No explicit sanitization or escaping of filenames is mentioned before they are processed by the LLM.
  • Mitigation: The skill includes a 'SAFETY WARNING' requiring explicit user confirmation before any file deletion, which serves as a critical human-in-the-loop safeguard.
  • [COMMAND_EXECUTION] (SAFE): Use of local system utilities for intended functionality.
  • The skill utilizes common system tools like shasum, cksum, or md5sum to perform duplicate detection. These operations are performed locally and are necessary for the skill's primary purpose of file organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM