azure-ai-voicelive-java
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The runtime workflow shown is a real-time WebSocket voice session that ingests user audio and events (including transcription/text) into the session via
session.receiveEvents()/setInputAudioTranscription(...), where outsider-authored content originates as participant speech.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata