twilio-conversation-intelligence
Warn
Audited by Snyk on May 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: 0.90). The skill ingests untrusted, user-generated conversation content captured by the Conversation Orchestrator (Voice, SMS, WhatsApp, RCS, Chat) and explicitly runs Language Operators (e.g., Next Best Response, Sentiment) on each COMMUNICATION or CONVERSATION_END which can influence webhook actions and suggested agent responses, creating a clear avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata