deepgram-prod-checklist
Warn
Audited by Snyk on Mar 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's runtime code (lib/deepgram-production.ts) calls deepgram.listen.prerecorded.transcribeUrl({ url: audioUrl }), which ingests/transcribes arbitrary external audio URLs provided at runtime, exposing the agent to untrusted third‑party content that could influence subsequent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata