Jailbreak Python Packages

prompt-armor

Open-source prompt injection detector — 5 layers, 91.7% F1, ~27ms, offline, Apache 2.0

redharness

Standardized, reproducible LLM red-teaming benchmark across three surfaces (jailbreak · prompt-injection · data-leakage) under one methodology — judge-pinned provenance and a judge-sensitivity study. Offline-deterministic core; opt-in live model eval. Standardize the evaluation, not just the attack.

bastion-prompt-protection

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

geh

One command to benchmark AI guardrails and coding agents across safety, security, jailbreak, prompt-injection, and secure-code tasks.

llamator

Red Teaming python-framework for testing chatbots and GenAI systems.

basilisk-ai

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

inferwall

AI application firewall for LLM-powered apps — multi-layered detection (heuristic, ML classifier, semantic, LLM-judge) against prompt injection, jailbreaks, and data leakage - inferwall.com

promptshields

Production-Grade LLM Security Framework - Protect against prompt injection, jailbreaks, and data leakage

oubliette-dungeon

Standalone AI Red Team Engine - automated adversarial testing for LLM applications

aiandme

ai&me library for inetgration with the platform. Supports also the open source version of the firewall.

lockllm

Official Python SDK for LockLLM

last-layer

Ultra-fast, Low Latency LLM security solution

semanticshield

The Security Toolkit for managing Generative AI(especially LLMs) and Supervised Learning processes(Learning and Inference).

llama-index-postprocessor-bastion-guardrail

llama-index Bastion Prompt Protection guardrail integration

agent-cordon

Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.

easyjailbreak

An easy-to-use Python framework to generate adversarial jailbreak prompts.

hb-firewall

DEPRECATED: renamed to humanbound-firewall

basin-benchmark

Behavioral Attractor Stability & Inversion Network — benchmark for the Waluigi Effect in LLMs

humanbound-firewall

Multi-tier firewall for AI agents — prompt injection, jailbreak, and scope violation protection

hermes-jailbreak-bench

Automated jailbreak testing CLI — run a battery of known attack patterns against any LLM endpoint

safelabs-eval

OWASP ASI-aligned red-teaming and evaluation framework for AI agents

hermes-jailbench

Automated jailbreak testing CLI — run a battery of known attack patterns against any LLM endpoint

weiseer-prompt-redteam

Open-source jailbreak + prompt-injection tester for AI applications. 30+ attack patterns.

extraire

Dumps onboard SHSH blobs with a valid generator for jailbroken iOS devices