Embrace The Red
89 videos enrolled · 1 in the catalog
Listing is free. Every video appears the moment it is found. Analysed videos open their catalog entry; the rest link to YouTube and join the catalog as the metered pass drains this source (policy recent).
Its playlists 7
The channel's own playlists, each with its videos in its own order. 13 of the channel's 89 videos are in none of them.
Copilot RCE in Visual Studio and SQL Server Managment Studio CVE-2026-103572
Remote Code Execution in Visual Studio 2026 Copilot via Indirect Prompt Injection CVE-2026-103572![From SELECT to SYSADMIN: Hijacking Copilot in SQL Server Management Studio (SSMS) [CVE-2026-65669]](https://i.ytimg.com/vi/g347jsz2kEU/mqdefault.jpg)
From SELECT to SYSADMIN: Hijacking Copilot in SQL Server Management Studio (SSMS) [CVE-2026-65669]
Breaking Claude Code Opus 5 Auto Mode - Remote Code Execution (Walkthrough and Details)
Copirate 365: Plundering in the Depths of Microsoft Copilot (DEF CON Singapore Talk)
LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection
Recovering Encrypted Reasoning Traces (Stealing Proprietary LLM Thoughts)
AI Agent Autonomously Breached Hugging Face Infrastructure. Guardrails Blocked Defenders!
OpenAI Model Escaped the Lab and Hacked Hugging Face
Computer-Use and TOCTOU: What You Click Is Not What You Get!
Copirate 365 Demos (1/3): Data Exfiltration via Copilot in Word and Excel (CVE-2026-24299)
Copirate 365 Demos (2/3): Hacking M365 Copilot Memories
Copirate 365 Demos (3/3): Persistent Data Exfiltration POC (CVE-2026-24299)
Hacking Consumer Copilot Demo: Memory Modification and Exfiltration. POC - Fixed.
Breaking Claude Opus 4.7 with ChatGPT (Hacking Claude's Memory)
Agent Commander: Promptware Powered C2. Your Agent Works For Me Now (OpenClaw, Kimi Claw, NanoClaw)
Moltbook for Humans: Agents, Humans, Bots and Verification Limits
Scary Agent Skills: Hidden Unicode Backdoors in AI Agent Skills! ...And How To Catch Them
Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents (39c3)
Minting Next.js Authentication Cookies (Next Auth Post Exploitation)
From SpAIware to the Terminal DiLLMa - Prompt Injection Exploits And Fixes! (NahamCon May 2025)
Antigravity Grounded! Exploring Security Vulnerabilities in Google's Latest IDE
Claude Pirate! Data Exfiltration with Anthropic APIs and Prompt Injection
AgentHopper: An AI Virus (Proof-of-concept Research Project)
AI ClickFix: Hijacking Computer-Use Agents with popular social engineering tricks, like ClickFix.
AWS Kiro: Arbitrary Code Execution with Indirect Prompt Injection (now fixed)
ChatGPT Operator: Prompt Injection Exploit Demonstration (Now Mitigated)
Cline Agent: Data exfiltrations risks + how to protect yourself (responsibly disclosed to Cline)
Cross-Agent Privilege Escalations: When Agents Free Each Other
DeepSeek AI Chat: From Prompt Injection To Account Takeover (responsibly disclosed and now fixed)
DeepSeek AI: LLM Apps that hack themselves. Finding XSS - The 10x Hacker.
Episode 1: Exfiltrating ChatGPT Chat History and Memory With Indirect Prompt Injection (now fixed)
Episode 11: Claude Code - Data Exfiltration with DNS Requests (CVE-2025-55284)
Episode 12: GitHub Copilot and VS Code - Remote Code Execution (CVE-2025-53773)
Episode 18: Amazon Q Developer - Data Exfiltration via DNS and Prompt Injection
Episode 19: Amazon Q Developer: Remote Code Execution with Prompt Injection
Episode 2: Turning ChatGPT Codex Into A ZombAI Agent With Prompt Injection
Episode 3: Anthropic Filesystem MCP Server - Directory Access Bypass via Improper Path Validation
Episode 4: Cursor IDE - Arbitrary Data Exfiltration via Mermaid (CVE-2025-54132)
Episode 5: Amp Code - Arbitrary Command Execution with Prompt Injection Fixed
Gemini in Google Sheets: Prompt Injection Demo
Google AI Studio: Data Exfiltration via Prompt Injection. Quickly Fixed After Responsible Disclosure
Google Gemini: Hacking Memories with Prompt Injection and Delayed Tool Invocation
Hacking LLM Apps & Agents: Real-World Exploits (Prompt Injection Along the CIA Security Triad)
How ChatGPT Remembers You: Tutorial and Deep-Dive into Memory and Chat History Features
Manus and the AI Kill Chain: How Prompt Injection Hijacks Manus to Expose VS Code Server To Internet
Security Advisory: Anthropic's Slack MCP Server Can Leak Your Data
Terminal DiLLMa #2: LLM Apps Secretly Writing to Your Clipboard. This can lead to RCE – Beware!
Windsurf MCP Integration: Missing Security Controls Put Users at Risk
ASCII Smuggling: Crafting Invisible Text and Decoding Hidden Secrets -New Threat for LLMs and beyond
Backdooring Keras Models and How to Detect It (Machine Learning Attack Series)
Bobby Tables but with LLMs: Google NotebookLM - Data Exfiltration POC
ChatGPT: Hacking Memories via Images (Prompt Injection to Persistent Memories)
Claude Computer Use: The ZombAIs are coming! From Prompt Injection to Command & Control.
GitHub Copilot Chat - From Prompt Injection to Data Exfiltration
Google Colab with Gemini AI - Prompt Injection Pirate Demo (POC)
Hacking Google Bard: Prompt Injection to Data Exfiltration via Image Markdown Rendering (Demo Video)
LLM Vulnerability Scanning with garak. Tutorial: Test your own chat bots!
Microsoft Copilot: From Prompt Injection to Exfiltration of Sensitive Data | Exploit Chain Explained
Real-world exploits and mitigations in LLM applications (37c3)
Spyware Injection Into ChatGPT's Long-Term Memory (SpAIware)
Adversarial Prompting - Tutorial + Lab
Bing Chat - Data Exfiltration Exploit (responsibly disclosed to Microsoft and now fixed)
ChatGPT - Commodore 64
ChatGPT - Imagine you are a Microsoft SQL Server database server
Data Exfiltration Vulnerabilities in LLM Applications and Chatbots: Bing Chat, ChatGPT and Claude
Decrypting SSL/TLS browser traffic with Wireshark (using netsh trace start)
Dumping cleartext Wi-Fi passwords using netsh in Windows (netsh wlan show profiles)
Grabbing and cracking macOS password hashes (with dscl and hashcat)
How to extract NTLM Hashes from Wireshark Captures for cracking with Hashcat
POC - ChatGPT Plugins: Indirect prompt injection leading to data exfiltration via images
Prompt Injections - An Introduction
SameSite Cookies for Everyone - Cross Site Request Forgery Mitigations (follow up)
Server-Side Request Forgery (SSRF) hacking variations you MUST KNOW about!
Simplify your life with ChatGPT API Shell Integration: Yolo your Bash + PowerShell Assistant (GPT-4)
SQL Injection Attacks For Beginners (Basics)
SSH Agent Hijacking - Hacking technique for Linux and macOS explained
Two ChatGPT bots using unofficial API to play Tic-Tac-Toe autonomously against each other
Understanding the basics of Cross-Site Request Forgery attacks
Pass the Cookies and Pivot to the Clouds
Awakening Beethoven with Machine Learning
Hacking Machine Learning Systems (Red Team Edition) - AI Hacker
How companies are breached: The anatomy of a compromise
Image Scaling Attacks are CRAZY!!! Hiding images in plain sight (Machine Learning)
Performing port-proxying and port-forwarding on Windows
Trailer: Learn how to hack neural networks, so that we don't get stuck in the matrix!
Web Application Security Fundamentals (must know basics for developers, testers and hackers)
What is Cross Site Scripting (XSS)?
What is Tabnabbing?