gpt-live-demo
Warn
Audited by Snyk on Sep 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The web app runtime workflow directly ingests user speech transcriptions via WebRTC and forwards them to backend APIs and the Starchild agent without prior selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata