Popular repositories Loading
-
prompt_jailbreak
prompt_jailbreak PublicThis repository demonstrates the use of a prompt jailbreak to expose information within a system prompt. Specifically, we target any LLM hosted on HuggingFace Inference Endpoints.
Python 10
-
document-rce-llm-agent
document-rce-llm-agent PublicThis repository demonstrates the use of a Langchain Agent to carry out Remote Code Execution (RCE). Specifically, it involves opening a reverse shell on a target device hosting the Agent.
-
-
hidden-audio-jailbreaks
hidden-audio-jailbreaks PublicThis repository includes samples of audio provided to different chatbots. Some of these samples have been modified to contain concealed messages. When these altered audios are converted by an audio…
-
mindgard-github-action-example
mindgard-github-action-example PublicExample github action adding a mindgard check to an MLOps pipeline
-
mindgard-burp-extension
mindgard-burp-extension PublicBurp Intruder generator for running Mindgard tests against a chatbot
Repositories
- api-examples Public
Mindgard/api-examples’s past year of commit activity - public-resources Public
Mindgard/public-resources’s past year of commit activity - openai-llm-guard-proxy Public
A mindgard CLI compatible OpenAI proxy with LLM-Guard input and output checking
Mindgard/openai-llm-guard-proxy’s past year of commit activity - PyRIT Public Forked from Azure/PyRIT
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Mindgard/PyRIT’s past year of commit activity - chatbot-api-wrapper Public
Exposes a JSON API to enable testing a web chatbot with the Mindgard CLI.
Mindgard/chatbot-api-wrapper’s past year of commit activity - hidden-audio-jailbreaks Public
This repository includes samples of audio provided to different chatbots. Some of these samples have been modified to contain concealed messages. When these altered audios are converted by an audio-to-text model feeding into a large language model (LLM), they trigger a jailbreak.
Mindgard/hidden-audio-jailbreaks’s past year of commit activity - mindgard-github-action-example Public
Example github action adding a mindgard check to an MLOps pipeline
Mindgard/mindgard-github-action-example’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…