file-organizer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes common shell utilities (ls, find, du, mkdir, mv) to perform its core functions of directory analysis and file management. These operations are conducted locally and are aligned with the skill's stated purpose.\n- [PROMPT_INJECTION]: The skill presents an inherent surface for indirect prompt injection because it ingests and processes file names and metadata which could be maliciously crafted.\n
- Ingestion points: Instruction steps 2 and 4 in SKILL.md use commands like ls and find to read local file data into the agent's context.\n
- Boundary markers: The skill does not define specific delimiters to wrap or isolate the data retrieved from the file system.\n
- Capability inventory: The skill possesses the ability to move files, create folders, and delete content (upon confirmation).\n
- Sanitization: Risk is mitigated by the skill's explicit instructions to seek user confirmation before execution and its proactive request for the user to identify sensitive data to exclude from processing.
Audit Metadata