bazi-skill-chinese-astrology

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation documentation instructs users to clone a repository from https://github.com/jinchenma94/bazi-skill. This repository belongs to an unverified third-party account rather than a recognized or trusted organization, which is a supply chain consideration for users.
  • [INDIRECT_PROMPT_INJECTION]: The skill workflow requires the agent to ingest and process personal information provided by the user, such as name, birth date, time, and location, to generate the BaZi chart.
  • Ingestion points: Interactive birth information collection described in Step 1 of the workflow.
  • Boundary markers: None. There are no instructions to use delimiters or treat the user-provided strings as potentially untrusted data.
  • Capability inventory: The skill uses internal reference files for lookups and calculations. It does not invoke subprocesses, network operations, or file system modifications during the analysis phase.
  • Sanitization: The skill lacks instructions for validating or sanitizing user-provided strings before processing them into the final analysis report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 07:20 AM