setup-vivox-voice-chat

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of incoming text messages and participant display names, which constitutes an indirect prompt injection surface. * Ingestion points: VivoxMessage.MessageText and VivoxParticipant.DisplayName are received via events in references/text-chat.md and references/events-and-participants.md. * Boundary markers: The skill does not define specific delimiters for separating user-generated content from agent instructions in the provided snippets. * Capability inventory: The skill focuses on UI display and audio management; no high-risk capabilities like shell execution or file system writes are present. * Sanitization: The documentation recommends server-side sanitization for DisplayName in references/init-and-login.md but does not explicitly detail sanitization for MessageText.
  • [EXTERNAL_DOWNLOADS]: The skill references authoritative documentation from the official Unity documentation service. * Source: Fetches guidelines and API details from https://docs.unity.com/en-us/vivox-unity/llms.txt.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 12:24 PM