vapi-demo
Warn
Audited by Snyk on Oct 23, 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 workflow sets up a Vapi observer server that receives runtime webhook payloads from external voice calls (transcripts, conversation updates, and call reports), which ingest outsider-authored free text into the agent's UI panels.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill imports the Vapi Web SDK from
https://esm.sh/@vapi-ai/webat runtime in assets/webcall-button.html, representing an ordinary third-party CDN dependency with common/reputable unofficial provenance.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata