velt-chat-sdk-adapter-best-practices

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests Velt webhook POST payloads (including outsider-authored comment text and author names) into the adapter via getChat().webhooks.velt(request, ...), which then passes that parsed free text into the agent/handlers/LLM context (e.g., message.text in onNewMention/onSubscribedMessage).