liuyao-yijing

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill operates entirely using local reference files (calculation-rules.md and interpretation-guide.md) to guide the agent's logic, avoiding external API dependencies or remote script execution.
  • [SAFE]: Data handling is restricted to reading and writing user preferences to a local MEMORY.md file, which follows standard practices for maintaining user context without exposing sensitive information.
  • [NO_CODE]: The skill contains only documentation and reference materials in markdown format; no executable scripts, binaries, or automated installation processes were found.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms (such as modifications to shell profiles or cron jobs) were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:49 AM
Security Audit — agent-trust-hub — liuyao-yijing