sinch-conversation-api

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests untrusted, user-generated inbound messages and media URLs via MESSAGE_INBOUND webhooks (references/webhooks/triggers/message-inbound.md) and uses Smart Conversations analysis for routing/decisions (references/webhooks/triggers/smart-conversations.md), so third-party content can directly influence agent behavior.