file-organizer-skill-hardened
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python script
scripts/organize.pyto perform file operations. The script relies on standard Python libraries and includes logical checks to avoid overwriting existing files.\n- [PROMPT_INJECTION]: The skill processes filenames from the filesystem, creating an indirect prompt injection surface where maliciously named files could attempt to influence the agent's behavior during interaction.\n - Ingestion points: The script reads file paths using
os.listdirandos.walkinscripts/organize.py.\n - Boundary markers: Absent; filenames are processed and presented in the agent's context without delimiters.\n
- Capability inventory: The script can move files and directories, and create new folders.\n
- Sanitization: Hidden files (dotfiles) are ignored by the script's logic, preventing the accidental movement of many common sensitive configuration files.
Audit Metadata