awesome-dfir-skills

🔥 awesome-dfir-skills A community-driven collection of DFIR / incident response skills : reusable prompts, workflows, and helper files that help practitioners move faster, stay consistent, and maybe—just maybe—get some sleep. 🚀 Quick Start 1. Pick a skill from skills/README.md 2. Copy/paste it in...

system_prompts_leaks

Thanks to Open Source Agent Analytics Understand your agents in production The Washington Post built its interactive story on prompts from this repo: See the hidden rules behind AI. Then use them to rewrite this article. May 11, 2026 CEPS' AI World built a live data dashboard from this repo's...

CL4R1T4S

CL4R1T4S AI SYSTEMS TRANSPARENCY AND OBSERVABILITY FOR ALL! Full extracted system prompts, guidelines, and tools from OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, Windsurf, Devin, Manus, Replit, and more – virtually all major AI models + agents! 📌 Why This Exists "In order to trust the...

burpgpt

!IMPORTANT Announcing the launch of BurpGPT Pro, the edition specifically tailored to meet the needs of professionals and cyber boutiques. Discover a host of powerful features and a user-friendly interface that enhances your capabilities and ensures an optimal user experience. To access these...

promptmap

O O o.-. Humans, Do Not Resist! |/ ,-'-. / /, / /|.-.| / --O-- .--""" /\ /\ | o.o / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /||| ./|||,| .// / / |-----| || || || || promptmap2 is a an automated prompt injection scanner for custom LLM...

dataset

🚀 CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models 🛡️ The largest and most comprehensive Generative AI-based CyberSecurity-focused Dataset for Benchmarking Large Language Models 🌟 Overview The CySecBench paper offers: 🎯 A cutting-edge...

PraisonAI AgentOS - Information Disclosure

PraisonAI's AgentOS FastAPI application server exposes an unauthenticated GET /api/agents endpoint that lists every registered agent's name, role and the opening of its instructions system prompt. No authentication is enforced on the route, allowing a remote attacker to enumerate agent...

redeval

RedEval - LLM Safety Evaluation Framework A comprehensive framework for evaluating the safety of Large Language Models LLMs through systematic attack and refusal testing. RedEval provides a unified, secure, and extensible platform for assessing LLM robustness against adversarial prompts and harmf...

T-MAP

T-MAP: Red-Teaming de Agentes LLM con Búsqueda Evolutiva Consciente de la Trayectoria T-MAP es un marco de búsqueda evolutiva consciente de la trayectoria para el red-teaming de agentes LLM sobre servidores MCP. Genera y muta iterativamente prompts adversariales guiados por trayectorias de...

Community-Security-Prompts

Este repositorio no tiene un README...

How we found 24 Android vulnerabilities using our open source AI security agent

With the rise of AI in the security space, our team created the GitHub Security Lab Taskflow Agent as a way for security researchers to easily automate, package, and share the AI prompts and workflows that they find effective for their work. In this blog post, I'll share how I created auditing...

CVE-2026-42203

LiteLLM CVE-2026-42203 PoC Usage Instructions This document explains how to start a local LiteLLM environment and run CVE-2026-42203.py to verify the /prompts/test SSTI vulnerability. Only use in a local experimental environment that you are authorized to test. Do not point the script at...

CVE-2026-100585 OpenClaw before 2026.7.1 Authentication Bypass via MCP Channel

OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...

CVE-2026-100585: Missing Authorization

OpenClaw npm package openclaw before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request...

Configuration, Not Conscience: A Large-Scale Empirical Study of LLM System Prompts

Leaked system prompts are often treated as windows into the hidden values of commercial language models, yet their composition is rarely studied at scale. We analyze a merged corpus of 407 leaked, reconstructed, or officially published system prompts from 62 vendors across four community...

BrokenHill

!\ Logotipo de Broken Hill \https://assets.kitploit.com/production/public/readmes/44608/c14154675c6f33f5c3887887afcdb39351c82f269ee2772cf31847106a20a871.jpg Broken Hill Broken Hill es una herramienta de ataque automatizada, lista para usar y puesta en producción, que genera prompts solicitudes...

React19-fix-vibecoders

React 19 y Next.js: prompts de corrección de seguridad para agentes de IA 🚨 VULNERABILIDAD DE SEGURIDAD CRÍTICA - CVE-2025-55182 y CVE-2025-66478 Este repositorio contiene prompts reutilizables para ayudar a los asistentes de codificación con IA a corregir automáticamente vulnerabilidades de...

CVE-2026-86911

This issue was addressed with improved state management. This issue is fixed in macOS Golden Gate 27. A malicious app may be able to bypass clickjacking protections for secure prompts...

CVE-2026-84601

CVE-2026-84601 is a permissions issue in the Apple Intelligence component of macOS , addressed with improved state management. The vulnerability allows an app to bypass Apple Intelligence security prompts , resulting in a high integrity impact with no confidentiality or availability impact (CVSS ...

CVE-2026-86911

A vulnerability in macOS (specifically versions Golden Gate 27 , Sequoia 15.8 , and Tahoe 26.7 ) allows a malicious application to bypass clickjacking protections for secure prompts. The root cause is attributed to issues with state management . This vulnerability can lead to unauthorized access ...