tavus-cvi-ui
Warn
Audited by Snyk on Feb 15, 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). This skill embeds and loads conversation content from tavusapi.com (the conversation_url returned by the API and used by the Conversation component or iframe) and consumes user-generated utterances via useAppMessage (event.properties.content), so the agent will read/interpret untrusted third-party content that could carry indirect prompt injections.
Audit Metadata