azure-ai-voicelive-dotnet
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-05.
This Azure AI Voice Live SDK skill is primarily a documentation/reference skill with LOW to MEDIUM severity findings. The skill does not contain executable scripts or malicious code. The main concerns are: (1) missing metadata fields (license, compatibility, allowed-tools) that reduce transparency, (2) insufficient security guidance around API key management, and (3) an incomplete code example that could cause resource issues. The skill appears legitimate and aligns with its stated purpose of providing .NET SDK documentation for Azure voice AI services. No data exfiltration, prompt injection, or command injection threats were detected. The skill would benefit from completing the documentation, adding security best practices, and including proper metadata declarations.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
SkillSpector found no issues but could not fully inspect the package, usually because SKILL.md refers to a file that is not present, so it fails closed to CAUTION instead of SAFE. Read it as "not fully checked", not as a finding. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication. Use for voice assistants, conversational AI, real-time speech-to-speech, and voice-enabled chatbots. Triggers: "voice live", "real-time voice", "VoiceLiveClient", "VoiceLiveSession", "voice assistant .NET", "bidirectional audio", "speech-to-speech".
- Package
- 2 files, 21 KB
- SKILL.md
- 789 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Azure.AI.VoiceLive (.NET) · Installation · Environment Variables · Optional: API key if not using Entra ID · Authentication · Microsoft Entra ID (Recommended) · API Key · Client Hierarchy · Core Workflow · 1. Start Session and Configure · 2. Process Events · 3. Send User Message
Findings
MEDIUM Hardcoded API Key in Environment Variable Example Data Exfiltrationllm
The skill documentation instructs users to store Azure API keys in environment variables (AZURE_VOICELIVE_API_KEY). While environment variables are better than hardcoding in source, the documentation does not warn about the security risks of API key exposure or recommend the more secure Entra ID authentication method strongly enough.
SKILL.md
# Optional: API key if not using Entra ID
AZURE_VOICELIVE_API_KEY=<your-api-key>What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 8.3 KB |
references/acceptance-criteria.md | doc | 13 KB |
External hosts referenced
your-resource.cognitiveservices.azure.com github.com learn.microsoft.com www.nuget.org my-resource.cognitiveservices.azure.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit cfbcbbdc679c. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/microsoft/agent-skills
- Raw scan result: github-skills-azure-ai-voicelive-dotnet-scan.json
- Badge for your README:
- Request a re-scan