azure-communication-callautomation-java

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

• Third-party content exposure detected (high risk: 0.70). The skill parses webhook events (CallAutomationEventParser.parseEvents) and handles RecognizeCompleted events / CallMediaRecognizeSpeechOptions which ingest and interpret callers' speech/DTMF (user-generated, untrusted) from incoming calls—exposing the agent to third-party content that could carry indirect prompt injection.