ray-voice

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a persona and writing style for the AI agent without attempting to bypass safety filters or perform malicious actions. The persona instructions focus on colloquial tone, Taiwanese Mandarin usage, and clear explanations using metaphors.- [SAFE]: The provided script scripts/check-voice.mjs is a zero-dependency utility that performs local text analysis. It imports only standard Node.js modules (node:fs, node:path, node:url, node:util) and does not involve network requests, sensitive file access, or dynamic code execution.- [SAFE]: Installation and update procedures described in the documentation involve standard git operations and tools from trusted organizations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:56 AM
Security Audit — agent-trust-hub — ray-voice