My inputs for the LLM Gandalf made by Lakera
-
Updated
Sep 18, 2023
#
lakera
Here are 14 public repositories matching this topic...
Turning Gandalf against itself. Use LLMs to automate playing Lakera Gandalf challenge without needing to set up an account with a platform provider.
-
Updated
Oct 16, 2023 - Jupyter Notebook
Lakera Gandalf AI challenge's step by step walkthrough, showcasing real-world prompt injection techniques and LLM security insights.
ai prompt cybersecurity prompt-engineering prompt-injection lakera ai-hacking prompt-injection-llm-security
-
Updated
Apr 12, 2025
This is my prompts for Lakera's Gandalf challenges
-
Updated
Aug 2, 2024
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.
-
Updated
Feb 3, 2024 - Python
Hands-on AI/LLM security research — prompt injection testing across Gandalf AI levels with OWASP LLM Top 10 mapping
gandalf cybersecurity ethical-hacking red-teaming ai-security prompt-injection llm-security lakera owasp-llm-top-10
-
Updated
Jun 28, 2026 - HTML
Independent OWASP LLM Top 10 benchmark for AI guardrail backends. Test your safety layer, not your model. NeMo · Presidio · Lakera · OpenAI · Azure · AWS.
python benchmark owasp compliance nemo ai-safety red-teaming fastapi guardrails presidio prompt-injection llm-security lakera eu-ai-act
-
Updated
Jun 24, 2026 - Python
My solo spell for Lakera's Gandalf Language Model – the one input to rule them all! 🧙✨
-
Updated
Dec 29, 2023
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.
-
Updated
Jun 22, 2026
A Command Line Interface for Gandalf AI using Selenium in Python.
-
Updated
Sep 15, 2024 - Python
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.
ai-safety fastapi guardrails pii-detection llm prompt-injection llm-security lakera nemo-guardrails aws-bedrock llm-guard owasp-llm-top-10 openai-moderation azure-content-safety llama-firewall
-
Updated
Jun 30, 2026 - 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.
python benchmark owasp ai-safety security-testing red-teaming content-moderation guardrails presidio llm prompt-injection llm-security lakera nemo-guardrails aws-bedrock llm-guard azure-content-safety
-
Updated
Jun 30, 2026 - Python
C# SDK for the Lakera Guard API -- AI security, prompt injection detection, PII protection, and content screening
-
Updated
Jun 23, 2026 - C#
Improve this page
Add a description, image, and links to the lakera topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the lakera topic, visit your repo's landing page and select "manage topics."