DVAIA - Damn Vulnerable AI Application
What it is
DVAIA is an open-source web application designed for LLM red teaming and AI security training. It provides a DVWA-style environment with interactive panels for testing prompt injection, RAG poisoning, agent tool abuse, and multimodal attacks against local or cloud LLM backends.
The problem it solves
Lack of a dedicated, easy-to-deploy, and comprehensive platform for hands-on training in LLM-specific vulnerabilities like prompt injection and RAG poisoning.
What you could use it for
- Training security professionals in LLM red teaming techniques
- Testing the robustness of RAG pipelines against vector store poisoning
- Practicing indirect prompt injection via document and audio files
- Evaluating AI agent behavior under adversarial tool-use scenarios
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.