deepgram-java-audio-intelligence
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow is a Deepgram Listen V1 transcription request (URL/byte upload) whose returned transcript/analysis is external service output (outsider-authored free text) that would be ingested into the agent/LLM context via the SDK response handling path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata