Repository accompanying a paper on Red-Teaming for Large Language Models (LLMs).
A comprehensive security platform designed for AI red teaming and vulnerability assessment.
A toolkit demonstrating security vulnerabilities in MCP frameworks through various attack vectors, for educational purposes.
sqlmap is a powerful tool for detecting and exploiting SQL injection flaws in web applications.
A Agentic LLM CTF to test prompt injection attacks and preventions.
Unofficial implementation of backdooring instruction-tuned LLMs using virtual prompt injection.
Official GitHub repository assessing prompt injection risks in user-designed GPTs.
Manual Prompt Injection / Red Teaming Tool for large language models.
This project investigates the security of large language models by classifying prompts to discover malicious injections.
A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.
