Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily
Lakera Gandalf AI challenge's step by step walkthrough, showcasing real-world prompt injection techniques and LLM security insights.
Proof of Concept (PoC) demonstrating prompt injection vulnerability in AI code assistants (like Copilot) using hidden Unicode characters within instruction files (copilot-instructions.md). Highlights risks of using untrusted instruction templates. For educational/research purposes only.
FRACTURED-SORRY-Bench: This repository contains the code and data for the creating an Automated Multi-shot Jailbreak framework, as described in our paper.
Add a description, image, and links to the prompt-injection-llm-security topic page so that developers can more easily learn about it.
To associate your repository with the prompt-injection-llm-security topic, visit your repo's landing page and select "manage topics."