# Results for "jailbreak ai"

> AI-ranked search results for `jailbreak ai` on awesome-repositories.com — ordered by an LLM for relevance, best match first. 115 total matches; showing the top 10.

Explore on the web: https://awesome-repositories.com/q/jailbreak-ai

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [this search on awesome-repositories.com](https://awesome-repositories.com/q/jailbreak-ai).**

## Results

- [giskard-ai/giskard-oss](https://awesome-repositories.com/repository/giskard-ai-giskard-oss.md) (5,947 ⭐) — Giskard is an AI quality assurance suite and evaluation framework designed to measure the performance, bias, and security risks of large language models and AI agents. It functions as a vulnerability scanner to detect security flaws and performance regressions.

The project provides automated red-teaming and adversarial testing workflows. These tools generate prompt-injection probes and adversarial attacks based on system descriptions to identify security gaps and vulnerabilities.

The platform covers AI agent auditing and RAG quality validation, using knowledge-base grounding and synthetic da
- [llm-attacks/llm-attacks](https://awesome-repositories.com/repository/llm-attacks-llm-attacks.md) (4,509 ⭐) — This repository provides tools and methodologies for studying adversarial attacks on large language models. It focuses on understanding how carefully crafted inputs can manipulate or bypass the safety mechanisms of LLMs, enabling researchers to probe model vulnerabilities and improve their robustness. The project covers techniques for generating adversarial prompts, evaluating model responses under attack conditions, and analyzing the effectiveness of different attack strategies.
- [verazuo/jailbreak_llms](https://awesome-repositories.com/repository/verazuo-jailbreak-llms.md) (3,563 ⭐) — This project is a comprehensive ecosystem of frameworks, toolkits, and datasets designed to evaluate model vulnerabilities and analyze jailbreak patterns. It serves as an adversarial testing framework and research toolkit for measuring the effectiveness of safety guardrails in large language models.

The system includes a library of real-world prompt injection datasets harvested from social media to study bypass strategies. It provides specialized tools for semantic attack analysis and prompt visualization, allowing for the mapping of relationships between adversarial prompts to discover commo
- [promptfoo/promptfoo](https://awesome-repositories.com/repository/promptfoo-promptfoo.md) (10,529 ⭐) — Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics.

The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that
- [giskard-ai/giskard](https://awesome-repositories.com/repository/giskard-ai-giskard.md) (5,434 ⭐) — Giskard is an evaluation framework, testing library, and quality monitoring system for large language models and AI agents. It serves as a toolkit for quantifying model performance and reliability, providing specialized capabilities for validating retrieval-augmented generation pipelines.

The project distinguishes itself through an automated red teaming tool and security scanner designed to identify vulnerabilities, prompt injections, and safety risks. It utilizes adversarial probing and synthetic edge case generation to quantify model robustness and detect information disclosure.

The platfo
- [nvidia/garak](https://awesome-repositories.com/repository/nvidia-garak.md) (8,114 ⭐) — Garak is an AI model evaluation tool and vulnerability scanner designed for red teaming large language models and auditing the security of retrieval-augmented generation pipelines. It identifies behavioral weaknesses, such as jailbreaks, hallucinations, and data leakage, by simulating adversarial attacks and executing automated testing vectors.

The framework utilizes an adaptive probing loop where prompts can react to previous model behavior and be modified in flight via middleware. To ensure consistent analysis, it employs a provider-agnostic interface to interact with various model APIs and
- [jailbreakbench/jailbreakbench](https://awesome-repositories.com/repository/jailbreakbench-jailbreakbench.md) (615 ⭐) — JailbreakBench -->
- [microsoft/promptbench](https://awesome-repositories.com/repository/microsoft-promptbench.md) (2,808 ⭐) — A unified evaluation framework for large language models
- [utkusen/promptmap](https://awesome-repositories.com/repository/utkusen-promptmap.md) (1,208 ⭐) — `` ______ O O o.-. Humans, Do Not Resist! \|/ ,-'-.() / /\, / /\|.-.| / --O-- (.--""" /\ /\ | ( o.o ) / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' \| ' \ | ' \/ | ' \ ) | / | | | ./| \/||| ./\|||\,| .// / / |-----| || || || |_____| ```
- [controllability/jailbreak-evaluation](https://awesome-repositories.com/repository/controllability-jailbreak-evaluation.md) (27 ⭐) — The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation. The jailbreak-evaluation is designed for comprehensive and accurate evaluation of language model jailbreak attempts. Currently, jailbreak-evaluation support evaluating a language model jailbreak…