file-organizer

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands such as ls, find, du, and mv to perform its primary function of file and directory organization.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes filenames and directory structures which could contain adversarial instructions.
  • Ingestion points: Data enters the context via file metadata and filenames retrieved through ls and find commands.
  • Boundary markers: The skill lacks explicit markers or instructions to isolate untrusted filesystem data from the agent's control logic.
  • Capability inventory: The skill has the capability to move, rename, and delete files (the latter requires user confirmation).
  • Sanitization: Example commands in the instructions use double-quotes for file paths, providing basic shell escaping, but the skill does not include mechanisms to sanitize the semantic content of the filenames.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:36 PM