wzry-build-advisor

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill is designed to provide game-related advice using local reference files. It does not access sensitive user data, perform unauthorized network requests, or execute dangerous commands.
  • [EXTERNAL_DOWNLOADS]: The documentation provides links to a public GitHub repository (github.com/LangGPT/wzry-atlas) for project maintenance. These are standard informational resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user input regarding game situations to provide customized advice. 1. Ingestion points: User messages in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file searching (grep) in SKILL.md. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 03:34 AM
Security Audit — agent-trust-hub — wzry-build-advisor