setup-vivox-voice-chat

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No prompt injection or safety bypass patterns were detected. The instructions follow standard technical guidance for SDK integration.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates safe credential management by explicitly warning the developer not to embed HMAC signing keys or Vivox app secrets in client-side code, recommending server-side token minting instead.
  • [EXTERNAL_DOWNLOADS]: The skill references official Unity documentation at docs.unity.com. These references are used for technical documentation mapping and are consistent with the skill's purpose.
  • [OBFUSCATION]: No malicious obfuscation, hidden characters, or homoglyph attacks were found. Technical mentions of obfuscation in the troubleshooting section correctly refer to standard Android build tools (R8/ProGuard).
  • [DATA_EXFILTRATION]: No unauthorized data collection or exfiltration patterns were identified. The network operations described are limited to standard Vivox service initialization, authentication, and messaging APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:55 PM
Security Audit — agent-trust-hub — setup-vivox-voice-chat