AI Safety & Red Teaming

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Apple Wallet Card Skinner for iOS 18+ (No Jailbreak Required)

🥷🏻 0 is the open-source AI security agent that finds, exploits, and fixes vulnerabilities across your stack. [Research Preview - by the Swiss Applied AI & Cybersecurity Research Lab]

LIST OF ALL MY JAILBREAKS

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

Evidence validation and policy engine for AI-assisted biological curation

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

A deliberately vulnerable banking application designed for practicing Security Testing of Web App, APIs, AI integrated App and secure code reviews. Features common vulnerabilities found in real-world applications, making it an ideal platform for security professionals, developers, and enthusiasts to

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

This repository contains detailed adversary simulation APT campaigns targeting various critical sectors. Each simulation includes custom tools, C2 servers, backdoors, exploitation techniques, stagers, bootloaders, and other malicious artifacts that mirror those used in real world attacks.

Comprehensive Python toolkit for stylometry

LLM fingerprinting system that identifies the underlying LLM model family

A security scanner for your LLM agentic workflows

AI-powered virtual camera tracking system for coarse alignment of mobile FSOC terminals — simulates beacon detection, Kalman-filter tracking, and PID-driven pan/tilt control under configurable atmospheric/vibration disturbances.

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

Word-accurate .lrc lyric sync. Paste your lyrics, point it at any audio file, get back an enhanced LRC with per-word timestamps. Powered by whisper.cpp + WhisperX (wav2vec2 forced alignment) + Demucs vocal isolation. Prebuilt for NVIDIA CUDA, Vulkan, and CPU. Manual editor for fine-tuning, live prev

[ACL 2026] - Official repo for the paper: "Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection"

Open source AI safety experiments. Exact inputs, transparent methods, and reproducible results.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

PyINE is a research framework for scalable elicitation and oversight of LLM reasoning, built on instrumented Python programs as a verifiable execution substrate.

Graph-Native Infrastructure for Context and Accountable AI Systems

ChatGPT DAN, Jailbreaks prompt

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems

LLM armor tester: an automated penetration-testing tool for AI applications. 700+ payloads, multi-turn attack chains, indirect-injection vectors, context-aware assessment, PDF penetration reports, and in-depth analysis of the attack process. Authorized testing only. LLM armor tester — automated jailbreak & prompt-injection pentest toolkit for AI apps. 700+ payloads, multi-turn attack chains…

GraspGen-based dual-arm manipulation with X-Trainer and Isaac Sim, covering grasping, transport, alignment, insertion and release.

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

PSXMaster is a powerful and user-friendly application designed to simplify the process of Transferring data from PC to PS5/PS4 and managing PlayStation Games.

ios 27 usbliter8 jailbreak

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.

A playful emulator for iOS. Plays supported 32-bit iPhone games on iOS 15+ — no jailbreak needed, though JIT is. An unaffiliated fork of touchHLE and HyperHLE; neither project endorses it.

FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.

DeepSeek Harness jailbreak: jailbreak every model, with different prompts available for different models; the default prompt targets the Chinese model “小码酱”. Jailbreak for every model — swap prompts per model. Please star the repository ⭐

Create adversarial attacks against machine learning Windows malware detectors

a security scanner for custom LLM applications

A hacker’s guide to FOFA dorking, packed with powerful queries and tips for bug bounty, red teaming and proactive defense - dork smart, find fast, report big.

A tool for automated alignment trimming in large-scale phylogenetic analyses. Development version: 2.0

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

A flexible enhancer for YouTube on iOS

Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for prompt injection, jailbreaks and secret/PII leaks.