deepgram-prod-checklist
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The implementation (references/implementation.md) includes transcribeProduction(audioUrl) which calls deepgram.listen.prerecorded.transcribeUrl({ url: audioUrl }), clearly fetching and transcribing arbitrary external audio URLs (untrusted third‑party content) that the agent will read and which could influence downstream decisions or actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata