All repositories

Securitygreshake

llm-security

Materials for research on indirect prompt injection: how malicious instructions in emails, web pages and code break LLM-integrated apps. Includes attack demos.

Who it is for

For people who want to understand how LLM apps get attacked through external data.

How to start

  1. Read the Overview and Demonstrations sections of the README
  2. To run the code, install dependencies: pip install -r requirements.txt
  3. Open the linked paper and compare it with the demos

Steps are taken from the README. Check the current version in the repository before running them.

Stars over the last 30 days

+4Oct 25 — Nov 17
2,1482,152

Author's description

New ways of breaking app-integrated LLMs

data-privacy-stack

presidio

A framework that finds and masks personal data in text, images and tables. It detects the data, then redacts or replaces it so it can be safely sent to a model.

12Kstars+423 in 28 dPython

NVIDIA

garak

A vulnerability scanner for LLMs: it runs a model through a set of probes for prompt injection, data leakage, toxicity and other failures. Works as a command-line tool.

10Kstars+365 in 27 dPython

guardrails-ai

guardrails

A Python framework that checks LLM inputs and outputs with ready validators from Guardrails Hub and helps produce structured answers. It catches risks before a reply reaches the user.

7.6Kstars+61 in 28 dPython

NVIDIA-NeMo

Guardrails

NVIDIA's toolkit for programmable rails in LLM-based conversational systems. Rules live in config and control what the bot talks about and does.

7.5Kstars+154 in 28 dPython

microsoft

PyRIT

Microsoft's framework for proactively finding risks in generative AI systems. It helps automate red teaming against models and applications.

4.9Kstars+213 in 27 dPython

meta-llama

PurpleLlama

Meta's generative AI safety project: the Llama Guard and Prompt Guard filter models, the Code Shield scanner and the CyberSec Eval test suites. It pairs defense with attack-based testing.

4.5Kstars+39 in 28 dPython