file-organizer

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes file names and file metadata from local directories, which represents a potential surface for indirect prompt injection if file names are crafted to influence agent behavior.
  • Ingestion points: Data enters the agent's context through directory analysis commands (ls, find) and file type identification (file) as specified in SKILL.md.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to treat analyzed file metadata as untrusted content.
  • Capability inventory: The skill has the capability to move (mv), create (mkdir), and delete (rm) files, although these actions are explicitly gated by user approval instructions in SKILL.md.
  • Sanitization: No sanitization or filtering of file names or metadata is performed before the agent processes the information.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 04:07 AM