gdalmau / lakera-gandalf-solutions
My inputs for the LLM Gandalf made by Lakera
☆34Updated last year
Related projects: ⓘ
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆20Updated 3 weeks ago
- Payloads for Attacking Large Language Models☆56Updated 2 months ago
- using ML models for red teaming☆39Updated last year
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆34Updated 8 months ago
- TakedownGPT combines a LangChain Agent with OpenAI function calling to automate the discovery of domain registrars and drafting of takedo…☆35Updated last month
- An interactive CLI application for interacting with authenticated Jupyter instances.☆49Updated 6 months ago
- Offensive security use cases of ChatGPT☆74Updated last year
- source code for the offsecml framework☆30Updated 3 months ago
- ☆34Updated this week
- Prompt Injections Everywhere☆68Updated last month
- ☆11Updated last year
- A JupyterLab extension to evaluate the security of your Jupyter environment☆36Updated last year
- The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspire…☆53Updated last year
- Secure Jupyter Notebooks and Experimentation Environment☆52Updated last month
- SourceGPT - prompt manager and source code analyzer built on top of ChatGPT as the oracle☆105Updated last year
- The purpose of this document is to outline the security risks and vulnerabilities that may arise when implementing ChatGPT in web applica…☆24Updated 2 months ago
- AI-powered bug hunter - vscode plugin.☆23Updated this week
- Application which investigates defensive measures against prompt injection attacks on an LLM, with a focus on the exposure of external to…☆15Updated last week
- LLM Testing Findings Templates☆65Updated 7 months ago
- ☆33Updated 6 months ago
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆189Updated 6 months ago
- Objectify-s3 is a tool that recursively checks AWS S3 buckets and objects for misconfigured permissions.☆15Updated last month
- Useful note☆14Updated 4 months ago
- ☆58Updated 2 months ago
- Leverages B64 chunks to split files and save to clipboard☆23Updated 3 months ago
- Burp Suite Enterprise Edition Power Tools☆16Updated last month
- A benchmark for prompt injection detection systems.☆80Updated last week
- Tool for analyzing SAP Secure Network Communications (SNC).☆49Updated 5 months ago
- Converting your Burp Suite projects into JSON APIs which can be viewed with Swagger editor or imported into Postman.☆48Updated 5 months ago
- Permiso Security has created a tool to query snowflake environments for evidence of compromise, based on indicators from Permiso and the …☆57Updated 3 months ago