skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides structural templates and guidelines for creating AI agent skills, including references for workflow patterns and output consistency.- [COMMAND_EXECUTION]: The skill includes Python scripts (init_skill.py, package_skill.py, quick_validate.py) designed to be executed by the agent to automate file system tasks such as directory initialization, structure validation, and ZIP packaging. These scripts use standard Python libraries (pathlib, zipfile, argparse) and perform actions consistent with their documentation.- [SAFE]: No evidence of prompt injection, data exfiltration, or malicious obfuscation was found. The logic used in the provided scripts is transparent and relies on standard library functions.- [SAFE]: The skill employs a structured 'Plan-With-Files' TODO methodology to manage the multi-step process of skill creation, which acts as a safety and quality gate for the development process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 12:03 PM