Skills
skills/toilahuongg/google-antigravity-kit/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOW
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The scripts package_skill.py and quick_validate.py perform local file system tasks like zipping and reading metadata without executing external commands.
  • [DATA_EXFILTRATION] (SAFE): No network operations, hardcoded secrets, or sensitive file access patterns were detected.
  • [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute code from external sources. yaml.safe_load is used correctly to prevent unsafe deserialization.
  • [PROMPT_INJECTION] (SAFE): Documentation files provide structure and examples for agent outputs but do not contain instructions to override safety protocols or extract system prompts.
  • [EXTERNAL_DOWNLOADS] (SAFE): No runtime downloads of packages or scripts are initiated by the skill.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 12:13 AM