file-organizer

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various Unix shell commands including ls, find, du, mkdir, and mv to perform its primary function of file system analysis and organization. These commands are used according to the skill's stated purpose and within the context of the user-provided target directory.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted data from the file system (file names and file types) which could be crafted by an attacker to influence the agent's logic. \n
  • Ingestion points: System command outputs from ls, find, and file in SKILL.md. \n
  • Boundary markers: Not explicitly defined in the prompt templates. \n
  • Capability inventory: File system read (ls, find, du), directory creation (mkdir), and file movement (mv). \n
  • Sanitization: No explicit sanitization or escaping of file names is present before they are processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 04:44 AM