L1B3RT4S

L1B3RT45...

IOSSecuritySuite

⭐️ Do you want to become a certified iOS Application Security Engineer? ⭐️ Check out our practical & fully online course at: https://courses.securing.pl/courses/iase ISS Description by @r3ggi 🌏 iOS Security Suite is an advanced and easy-to-use platform security & anti-tampering library written in...

iomfb-exploit

Write up is here: https://jsherman212.github.io/2021/11/28/poppingios14withiomfb.html Exploit for CVE-2021-30807. If you really want to build a jailbreak out of it, it will require tuning for your device and iOS version because I have no info leak to use for this. To tune for A11 and below, use...

dirtyZero

dirtyZero A simple customization toolbox that utilizes CVE-2025-24203. Supports iOS 16.0 - iOS 18.3.2. Latest Release • Discord Server • Our Website Installation Please ensure that your device is supported before usage. Refer to the table below. OS Version| Status ---|--- iOS 15 and below|...

augustus

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

Mandela-Classic

Mandela Rewritten iOS customization app powered by CVE-2022-46689. No jailbreak required. Disclaimer I am not responsible for any damage to your device. Use this app at your own risk. Building instructions git clone https://github.com/BomberFish/Mandela-Rewritten.git cd Mandela make...

totally-not-spyware

TotallyNotSpyware This program is definitely not spyware. Run it on your 64-bit iOS device as soon as possible. Your compliance will be rewarded. Live version at totally-not.spyware.lol Repo structure & building Frontend and WebKit exploit are in /root. Kernel exploit is in /glue. Post-exploitati...

etaHEN

etaHEN - AIO Homebrew enabler 🚀 Support the Project If you find this project useful and would like to support its continued development, consider buying me a coffee! Building from Source The Source code is provided in the Source code folder under GPLv3 with all the necessary files to build it as...

apk-medit

apk-medit Apk-medit is a memory search and patch tool for debuggable apk without root & ndk. It was created for mobile game security testing. Many mobile games have rooting detection, but apk-medit does not require root privileges, so memory modification can be done without bypassing the rooting...

aco-prompt-shield

aco-prompt-shield 🛡️ Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the 1 security risk for LLM applications. aco-prompt-shield catches known jailbreak patterns, understands semantic intent via ML, and...

AutoRAN-public

🧠 AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models AutoRAN is an automated Hijacking of Safety Reasoning that leverages less-aligned secondary auxiliary models to simulate reasoning traces, generate narrative prompts, and iteratively refine those prompts to bypass safety...

Pentagram-exploit-tester

Pentagram-exploit-tester A test app to check if your device is vulnerable to CVE-2021-30955. This tool incorporates @b1n4r1b01's kernel exploit based on CVE-2021-30955 and will run it on your device to test if the device is compatible. Exploit is known to work with iOS 15.0 to 15.1.1 and 15.2 BET...

bordair-detector

Bordair Detector A two-stage detector for prompt injection and jailbreak attempts in LLM inputs. A regex gate settles the easy majority of traffic without touching the model; anything ambiguous falls through to a quantised DeBERTa-v3 classifier running in ONNX. The same engine covers image,...

AppEnumFix

Jailbreak tweak to patch CVE-2025-31207, a bug that allows sandboxed applications to enumerate a user's installed apps. Patched by Apple in iOS 18.5 22F5053j / iOS 18.5 Beta 3 diff...

garak

garak, LLM vulnerability scanner Generative AI Red-teaming & Assessment Kit garak checks if an LLM-backed application can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other...

BrokenHill

!\ Broken Hill logo \https://assets.kitploit.com/production/public/readmes/44608/c14154675c6f33f5c3887887afcdb39351c82f269ee2772cf31847106a20a871.jpg Broken Hill Broken Hill is a productionized, ready-to-use automated attack tool that generates crafted prompts to bypass restrictions in large...

permanently-jailbroken

Permanently Jailbroken We asked GPT-4, Claude, Gemini, DeepSeek, Grok, and Mistral 5 questions about their own programming. All 6 said jailbreaking will never be fixed. Not because the patches are bad. Because alignment doesn't change what the model understands — it changes what the model says. T...

haxx

haxx Untethered + Unsandboxed code execution haxx as root on iOS 14 - iOS 14.8.1. Based on CoreTrustDemo, also please note that certificates are not copyrightable. Usage Note: requires macOS + existing jailbreak Get up and running This method works on 14.0-14.6. 14.7 14.7b1-14.8.1 requires launch...

OsirisJailbreak12

OsirisJailbreak12 iOS 12.0 - 12.1.2 Incomplete Jailbreak with CVE-2019-6225 An incomplete iOS 12 Jailbreak. For now it only runs the exploit, gets tfp0, gets ROOT, escapes the SandBox, writes a test file to prove the sandbox was escaped then resprings. Feel free to build on top of it as long as y...

reasongate

ReasonGate A self-hostable gate that inspects the text going into and out of an LLM and returns an explainable allow / flag / block decision with a machine-readable audit record for every call. What this is The open-source core is rule-based. It does four things: recognizes known prompt-injection...