qimen-dunjia

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a local calculation engine for traditional Chinese metaphysics (Qimen Dunjia) using a Python script and well-known libraries. No malicious logic or exfiltration patterns were detected in the source code.
  • [SAFE]: All external dependencies are standard, well-known open-source packages (lunar_python, tzdata) used legitimately for calendar and time-zone calculations.
  • [SAFE]: File operations are confined to temporary communication files (/tmp/qimen_input.json, /tmp/qimen_output.json), which is a standard method for passing structured data between the AI agent and local executable scripts.
  • [SAFE]: The skill includes explicit instructions for ethical handling of high-risk topics, requiring the agent to provide realistic professional advice alongside traditional interpretations and prohibiting the use of threatening or alarming language.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:10 PM