skills/koryaga/persona/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • SAFE (SAFE): No malicious patterns detected. The scripts are standard utility tools for developers following best practices.
  • DATA_EXPOSURE (INFO): The package_skill.py script archives the contents of a directory into a .skill (zip) file. Users should ensure no sensitive files (like .env or SSH keys) are present in the skill folder before packaging, though this is expected behavior for a packaging tool.
  • DYNAMIC_EXECUTION (SAFE): YAML parsing in quick_validate.py uses yaml.safe_load(), which is resistant to arbitrary code execution attacks common in YAML deserialization.
  • INDIRECT_PROMPT_INJECTION (LOW): The scripts ingest content from SKILL.md to validate metadata. While the ingestion surface exists, the script performs validation (regex, length checks, and key whitelisting) and has limited capabilities (only packaging files already present on disk), posing minimal risk.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:05 PM