create-master

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches historical Buddhist texts, knowledge graph entities, and dictionary definitions from the FoJin API at https://fojin.app. These downloads are essential to the skill's primary function of providing grounded, source-cited religious teachings.
  • [COMMAND_EXECUTION]: Uses internal Python and Node.js scripts (located in scripts/, tools/, and bin/) for administrative tasks. These include installing master personas to the local skills directory, validating CBETA source links, and running fidelity tests to ensure AI personas remain faithful to historical records.
  • [PROMPT_INJECTION]: Implements a defensive multi-layered instruction system, including a 'Layer 0' hard-rule set and 'HARD-GATE' sections in SKILL.md. These instructions prevent the AI from bypassing safety guidelines, assuming unauthorized religious status, or making fabricated doctrinal claims.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 08:09 PM