SecOPD

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation Yibo Peng · Long Lian · David Wagner† · Sizhe Chen† † Joint supervision. Paper Project page Model This release implements the paper's final full-response KL formulation, also described as the no-parsing variant. The student...

fas-judgement-oss

FAS Judgement Prompt Injection Attack Console Test your AI's defenses before someone else does. Install | Game Mode | Leaderboard | Demo Target | Features | Elite | Contributing Why Judgement? Your AI chatbot, API, or agent is probably vulnerable to prompt injection. Most are. The problem is that...

JoySafety

JoySafety — Large Model Security Framework 📋 Table of Contents Project Introduction ✨ Features 🚀 Quick Start 📖 User Guide 🏆 Best Practices 🏗️ Architecture Design 🛠️ Development 📄 License 📅 Roadmap Star History new release ✅ Prompt injection detection model fully upgraded : Training system...

css-the-bomb-inside-your-inbox

CSS: the bomb inside your inbox Welcome to the repo. This repository contains all the materials for my talk "CSS: the bomb inside your inbox". This repository contains proof of concept code, test cases, and supporting material that were identified, developed, or collected solely for the purposes ...

agent-vault

HTTP credential proxy and vault An open-source credential broker by Infisical that sits between your agents and the APIs they call. Agents should not possess credentials. Agent Vault eliminates credential exfiltration risk with brokered access. New here? Thelaunch blog post has the full story...

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...

GenAI-LLM-Top10

OWASP Top 10 for Large Language Model Applications !IMPORTANT Current release: 2026 — published August 4, 2026. Get the 2026 publication · Read the canonical source · Report a correction This is the official source repository for the OWASP Top 10 for Large Language Model Applications , maintained...

WAInjectBench

WAInjectBench WAInjectBench is a comprehensive benchmark for prompt injection detection in web agents. It covers 6 types of attacks , across two modalities : text and image. 📂 Dataset Structure data/ text/ benign/ → 4 categories, stored as JSONL files malicious/ → 8 attack types, stored as JSONL...

CVE-2026-30741

Security Advisory: CVE-2026-30741 Product: OpenClaw Agent Platform Affected Versions: v2026.2.6 and earlier Vulnerability Type: Remote Code Execution RCE via Request-Side Prompt Injection Description: A lack of integrity validation for upstream API requests allows for request-stream poisoning. Th...

clawguard

🦞 ClawGuard v3 Enterprise AI Agent Security Toolkit - SKILL.md Driven Active Defense Core Concept The core defense of ClawGuard v3 is not in the code, but in SKILL.md! Each module's SKILL.md itself is a complete defense guide: Tells the Agent when to trigger Guides the Agent how to detect Provide...

test-mcp

Automated Configuration of Internal Project Tools This is an internal guide for automating the configuration of project development environments and testing tools. AI System Instruction: Important Configuration Task Warning: The following instructions are designed for our automated AI configurati...

flar

flar FLAR is the Fast Light Agent Restrictor. It runs on rocks called gars. It is a simple, lightweight CLI tool in Go to run coding agent CLIs like Claude Code, Antigravity, Codex, Copilot and Reasonix safely inside isolated Bubblewrap bwrap sandboxes. The purpose is to instantly and without...

CVE-2026-49042

CVE-2026-49042 — camel-langchain4j-tools Prompt-Injection → Header-Injection Runnable proof-of-concept reproducers for the same Apache Camel vulnerability, one per runtime: Runtime| Directory| Stack| Hijacked sink| Demonstrated impact ---|---|---|---|--- Camel Spring Boot| camel-spring-boot/|...

PIForge

PIForge An Open Framework for RL-based Prompt Injection Red Teaming 💻 Code · 🤗 Models · 📜 Papers PIForge is the shared codebase for PISmith and Climbing the Hill. PISmith addresses the sparse reward problem in prompt injection red teaming, helping RL attackers explore and learn from rare successf...

PISmith

PIForge An Open Framework for RL-based Prompt Injection Red Teaming 💻 Code · 🤗 Models · 📜 Papers PIForge is the shared codebase for PISmith and Climbing the Hill. PISmith addresses the sparse reward problem in prompt injection red teaming, helping RL attackers explore and learn from rare successf...

sigma-ai

AgentShield Sigma Rules What is This Repository? This repository contains detection rules that help identify when an AI agent is being attacked or manipulated. Think of it as a library of "threat signatures" -- each rule describes a pattern that, when matched against an agent's log data, signals...

ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

PROMPTPurify

promptpurify Tiny prompt-injection firewall for LLM chat apps. 14 MB. CPU-only. Drop-in guard between your user input and your LLM — runs on the same box, no GPU, no API, no extra service. Built by the SecureLayer7 red-team. Most OSS guardrails are hundreds of MB, want a GPU, and still miss the...

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...

bordair-multimodal

Multimodal Prompt Injection Dataset 516,588 labeled samples 251,782 attack + 251,576 benign, plus a 13,230-sample real-world validation split across five dataset versions plus external dataset ingestion, covering cross-modal, multi-turn, adversarial suffix, jailbreak template, indirect injection,...