Metadata Priority Injection을 통한 RAG 시스템 데이터 오염 취약점 분석
LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability
LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability
Static Analysis for LLM Prompt Security: A Methodology for Pre-Deploy Vulnerability Detection.
Why Prompt Injection Is an Architectural Problem - Not Just a Security Bug
How a Morse Code Attack Bypassed Bankr's LLM Agent: T1027 Obfuscation in the Wild
Prompt injection through website content: how AI agents can be manipulated by the pages they visit
Your chatbot might be saying things you never intended
I Got Burned by Prompt Injection in Production. Here Are 2 Tiny npm Libs That Stopped It.
Johann Rehberger im Interview: Wie ein Memory-Hack Claude Opus 4.7 austrickst
Prompt injection in LinkedIn profiles
Why Developers Trust AI Code More Than They Should
I Tested Delimiter-Based Prompt Injection Defense Across 13 LLMs
The Missing bandit for AI Agents: How I Built a Static Analyzer for Prompt Injection
MCP Tool Poisoning: The AI Supply Chain Attack Nobody Is Talking About
The Agentic AI Dilemma: Scaling Autonomy Without Sacrificing Security
The gay jailbreak: probé la técnica viral sobre mis propios prompts de producción y esto encontré
Yet another experiment proves it's too damn simple to poison large language models
The Cyber Perfect Storm Is Here — And Your AI Agents Are in the Blast Radius
Why Your LLM Probably Has a PII Problem (And How to Fix It)
My personal journey learning about prompt-injections and how that influences my use of AI (agents)
Comment and Control: How Prompt Injection in Code Comments Can Steal API Keys from Claude Code, Gemini CLI, and GitHub Copilot