Geek-skills-c-drive-cleaner

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (analyze_disk.py, find_large_files.py, clean_temp.py) to perform its core functions of disk analysis and maintenance.
  • [DATA_EXPOSURE]: The scripts access various system and user directories, such as C:\Windows\Temp, %LOCALAPPDATA%, and $Recycle.Bin, to identify files and calculate storage consumption. This data access is necessary for the skill's primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it reads and displays filenames and directory structures from the local file system.
  • Ingestion points: Local file system metadata is read using os.scandir and os.walk within all provided scripts.
  • Boundary markers: No delimiters or safety instructions are used to separate scanned filenames from the agent's instructions.
  • Capability inventory: The skill has the capability to delete files and directories via the clean_temp.py script.
  • Sanitization: Filenames are processed and printed without specific sanitization or escaping mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 03:21 PM
Security Audit — agent-trust-hub — Geek-skills-c-drive-cleaner