lakera

My inputs for the LLM Gandalf made by Lakera

Turning Gandalf against itself. Use LLMs to automate playing Lakera Gandalf challenge without needing to set up an account with a platform provider.

Lakera Gandalf AI challenge's step by step walkthrough, showcasing real-world prompt injection techniques and LLM security insights.

Solution to Gandalf by Lakera AI CTF

This is my prompts for Lakera's Gandalf challenges

Flask API with a Streamlit ChatBot, this project provides a dynamic interface for database interaction and AI-driven user engagement, featuring secure, Docker-deployed components and advanced GPT-3.5 integration.

Hands-on AI/LLM security research — prompt injection testing across Gandalf AI levels with OWASP LLM Top 10 mapping

My solo spell for Lakera's Gandalf Language Model – the one input to rule them all! 🧙✨

A Command Line Interface for Gandalf AI using Selenium in Python.

Stop testing your model. Test your guardrail layer. guardrailprobe fires 78 OWASP LLM Top 10 attack probes across 11 backends — Lakera, NeMo, Presidio, Azure Content Safety, Bedrock Guardrails, LLM Guard, and five more — and outputs signed PDF and JSON comparison reports.

Prompt-injection writeups for Lakera's Tongue Tied Gandalf . The aim was getting it to discuss forbidden topics. Repo includes my prompts, screenshots and explanations.

One enforcement layer for all your LLM guardrails. Drop in NeMo, Presidio, Lakera, OpenAI Moderation, Azure Content Safety, AWS Bedrock, LlamaFirewall, or LLM Guard — swap backends without touching your app code. Async-native. Covers OWASP LLM Top 10 attack categories.

C# SDK for the Lakera Guard API -- AI security, prompt injection detection, PII protection, and content screening