Azure Ai Voicelive Py

• Outcome: Pass
• Latest audit: May 27, 2026, 9:48 PM
• Version:
  0.1.0

Overview

This is a documentation-only Azure voice SDK skill whose sensitive audio and credential use is expected for its stated purpose.

Install only if you intend to build an Azure-hosted voice application. Use least-privilege Azure credentials, avoid hardcoding API keys, obtain consent before recording or streaming speech, minimize sensitive spoken data, and review any real function or MCP tools before letting model-selected calls perform actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill instructs users to capture microphone audio and handle transcription events, but it does not clearly disclose that raw spoken audio and derived transcripts are transmitted to Azure's cloud service for processing. In a voice/streaming SDK skill, that omission can cause accidental exposure of sensitive spoken data, especially in environments where users may assume local-only processing.

VirusTotal

60/60 vendors flagged this skill as clean.