azure-ai-voicelive-py
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of
azure-ai-voicelive,aiohttp, andazure-identity. Whileazure-identityis an official library,azure-ai-voiceliveis a third-party community package not managed by the primary service provider. - [CREDENTIALS_UNSAFE]: Documentation identifies the use of
AZURE_COGNITIVE_SERVICES_KEYfor authentication but utilizes safe placeholder values (<api-key>) and explicitly recommends the more secureDefaultAzureCredentialfor production deployments. - [PROMPT_INJECTION]: The skill implements a real-time voice interface that processes audio transcripts, presenting a surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data from
event.transcript,event.delta, andevent.argumentsvia a WebSocket connection inSKILL.md. - Boundary markers: Examples use basic system instructions without explicit delimiters or warnings to ignore instructions embedded in the audio stream.
- Capability inventory: The skill enables bidirectional WebSocket communication, model-triggered function execution, and session state modification.
- Sanitization: There is no evidence of transcript sanitization or validation before the data is processed by the agent.
Audit Metadata