qimen-dunjia-oracle
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs deterministic calculations based on local reference files (
references/calculation-rules.md) and interprets them using provided guides. It does not make any external API calls or network requests. - [SAFE]: Data persistence is handled through a local
MEMORY.mdfile within the skill directory to store user preferences, which is a standard pattern for agent memory and does not involve sensitive system files. - [SAFE]: The skill contains no executable scripts, shell commands, or external package dependencies, significantly reducing the attack surface for remote code execution or privilege escalation.
- [SAFE]: The instructions include a comprehensive "Forbidden Expression List" that explicitly prohibits the AI from making absolute predictions, death forecasts, or using scaring tactics, demonstrating a focus on safety and ethical output.
Audit Metadata