voice-ai-integration

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime-configured external LLM endpoint (e.g. https://api.openai.com/v1/chat/completions) which the ConvoAI agent calls during execution to generate responses that directly control the agent's prompts/behavior, and the llm configuration (url) is a required dependency for creating/ running agents.