Prompt Leaking
+5 XP
Category
LLM Hacking
107 articles
AI in Hacking
+5 XP
AI Red Teaming Guide 2026 — How Security Teams Test LLM Applications
AI red teaming guide 2026 — how security teams stress-test LLM applications for prompt injection, data leakage, misuse, and unsafe…
Prompt Injection
+5 XP
Microsoft Copilot Prompt Injection 2026 — Enterprise AI’s Biggest Security Risk
Complete guide to Microsoft Copilot prompt injection vulnerabilities in 2026. Covers the M365 data access scope, email injection, SharePoint injection,…
Prompt Injection
+5 XP
Indirect Prompt Injection 2026 — When Web Pages Attack Your AI Agent
Complete guide to indirect prompt injection attacks in 2026. Covers how adversarial instructions in web pages, documents, RAG databases, and…
AI in Hacking
+5 XP
AI Supply Chain Attacks 2026 — How Hackers Poison Models Before You Deploy Them
AI supply chain attacks 2026 — model poisoning on Hugging Face, pickle-based code execution on model load, training data poisoning,…
Prompt Injection
+5 XP
How Hackers Steal Your ChatGPT Conversation History — And How to Stop It
ChatGPT conversation history theft 2026 — how attackers use prompt injection and memory exploits to steal private conversations from ChatGPT…
Prompt Injection
+5 XP
GPT-4o Vision Hacking — How Attackers Inject Prompts Through Images
GPT-4o vision prompt injection 2026 — how attackers embed malicious instructions in images that AI assistants read, bypassing text-based safety…
AI in Hacking
+5 XP
RAG Poisoning — The AI Attack Nobody Is Talking About in 2026
RAG poisoning attacks 2026 — how attackers corrupt retrieval-augmented generation knowledge bases to inject malicious content into AI responses. Complete…
Prompt Injection
+5 XP
10 Prompt Injection Payloads Every Security Researcher Must Know in 2026
10 prompt injection payloads every security researcher must know in 2026 — direct override, context confusion, extraction, encoding, and indirect…
AI in Hacking
+5 XP
AI Agent Hijacking — How Attackers Take Over Autonomous AI Systems (2026)
AI agent hijacking attacks 2026 — how attackers seize control of autonomous AI agents through prompt injection, goal manipulation, and…