deepgram-sdk-patterns
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: 0.80). The skill's transcribeUrl implementation in lib/transcribe.ts (and the Python transcribe_url in lib/deepgram_client.py) explicitly fetches and transcribes audio from arbitrary URLs, so untrusted third-party content can be ingested and its transcript could influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata