setup-vivox-voice-chat
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for Unity Vivox integration, focusing on the v16 API singleton VivoxService.Instance. All API references are consistent with official Unity documentation.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The evaluation suite uses promptfoo, which is a well-known and reputable tool for testing LLM responses. The instructions suggest using npx, which fetches the package from the official npm registry.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill demonstrates safe handling of sensitive credentials by instructing users to utilize environment variables and .gitignore, preventing accidental exposure of API keys.
- [INDIRECT_PROMPT_INJECTION]: The skill includes an evaluation framework that processes user messages. As this is used for testing and the skill itself does not have tools or high-privilege capabilities, the risk of indirect injection is negligible.
Audit Metadata