ComingUp
VoiceGoat – A vulnerable voice agent for practicing LLM attacks

VoiceGoat – A vulnerable voice agent for practicing LLM attacks

Apr 29, 2026 Security & Privacy
llm attacks penetration testing voice security

Gallery

VoiceGoat – A vulnerable voice agent for practicing LLM attacks

About

VoiceGoat is an open-source voice agent designed to be vulnerable to attacks, allowing users to practice and test Large Language Model (LLM) attacks in a controlled environment. It provides a simulated voice interface for penetration testers and security researchers to experiment with various attack scenarios. VoiceGoat is available on GitHub for download and use.

Comments (0)

No comments yet. Be the first to comment!