skills/unix2dos/skills/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to guide the creation of other skills. It contains standard instructional content and utility scripts without any indicators of malicious intent or safety bypasses.
  • [COMMAND_EXECUTION]: The skill includes Python scripts (init_skill.py, package_skill.py, quick_validate.py) that perform local file system operations such as directory creation, writing template files, and zipping directories. These operations are restricted to paths provided by the user via command-line arguments and are appropriate for the skill's purpose as a development utility.
  • [PROMPT_INJECTION]: Instructions focus on design principles like 'Progressive Disclosure' and 'Concise is Key.' No bypass markers or attempts to override agent safety protocols were found.
  • [EXTERNAL_DOWNLOADS]: No remote code execution patterns, external downloads, or network-enabled operations were detected in any of the scripts or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 05:22 AM