file-organizer

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands including ls, find, du, mv, mkdir, and md5 to perform its primary functions. These operations grant the agent extensive visibility and modification rights over the user's local file system.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from the file system (filenames, paths, and file metadata).
  • Ingestion points: File system metadata (filenames, directory structures, and file type information gathered via the file command) in local directories specified by the user.
  • Boundary markers: Absent. There are no instructions to the agent to treat filenames or file metadata as untrusted data or to ignore potential instructions embedded in filenames.
  • Capability inventory: The skill possesses the ability to read, move, rename, and suggest deletions for files across the user's home directory and other sensitive locations.
  • Sanitization: Absent. Filenames and metadata are passed directly into the agent's context without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:10 AM
Security Audit — agent-trust-hub — file-organizer