deepgram-migration-deep-dive

Warn

Audited by Snyk on Mar 13, 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 skill calls DeepgramAdapter.transcribe(audioUrl) which uses client.listen.prerecorded.transcribeUrl to fetch and transcribe arbitrary audio URLs (see adapters/deepgram-adapter.ts and the validate-migration.ts testAudioUrls), so it ingests open/public third-party audio whose transcribed content is programmatically compared and used for routing/validation decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 11:54 AM
Issues
1