azure-messaging-webpubsub-java

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

• Third-party content exposure detected (high risk: 0.70). The skill's examples and ChatService code (e.g., sendMessage, sendDirectMessage, broadcastToRoom and the use of client.sendToGroup/sendToAll) explicitly accept and process arbitrary user-supplied chat messages over Azure Web PubSub, exposing the agent to untrusted user-generated content that could carry indirect prompt injection.