Black Hat USA 2026 | ChatMate: Remote Prompt Execution on AI Assistants through Sandbox Escaping
MentionsMicrosoftMicrosoft Azure
Plays from YouTube in privacy-enhanced mode — nothing loads from YouTube until you press play.
Imagine a user asks an LLM a question about a document. An attacker then gains an interactive prompt on the user's chat session, enabling the attacker to instruct the AI assistant to take actions on behalf of the victim. In this Briefing, we will reveal a novel vulnerability class we call "Remote Prompt Execution" where, similar to remote code execution, an attacker is able to "run" arbitrary prompts on the user's chat session. We will detail a full Copilot chain demonstrating a scenario where uploading a document to Copilot can lead to a full takeover of the Copilot's chat session.
Description from Black Hat.
Explained
The technology and terms in this story. Learn more
- TechnologyLLM · Large language modelAn AI model trained on huge amounts of text to understand and generate language, such as ChatGPT or Claude.
- AttackRemote code execution · RCEA flaw that lets an attacker run their own code on someone else's machine over the network.
- AttackPrivilege escalationGoing from limited access to more powerful access, such as from a normal user to administrator.