azure-communication-callautomation-java

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly ingests untrusted caller-generated content via webhook event handling (CallAutomationEventParser.parseEvents in the "Handle Events (Webhook)" section) and by starting speech/DTMF recognition (CallMedia.startRecognizing / RecognizeCompleted), which the agent is expected to read/interpret and which can influence call routing and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 01:22 PM