skill-creator-openai

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes Python scripts that perform local file system operations to facilitate skill development.
  • scripts/init_skill.py: Creates new directories and writes template markdown and Python files based on user input.
  • scripts/package_skill.py: Reads directory contents and uses the zipfile module to create a compressed .skill file.
  • scripts/quick_validate.py: Reads and parses YAML metadata from local files for structural validation.
  • [SAFE]: The skill implements robust input sanitization to prevent path traversal and other injection attacks.
  • The normalize_skill_name function in init_skill.py uses regular expressions to restrict skill names to lowercase alphanumeric characters and hyphens only.
  • This prevents an attacker from supplying malicious paths (e.g., ../../etc/) as a skill name.
  • [SAFE]: The validation logic uses yaml.safe_load to process skill metadata, protecting against YAML-based unsafe deserialization attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 08:10 PM