All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

GitHub Copilot Vulnerability Enables Remote Code Execution via Prompt Injection

By

kerng

7mo ago· 7 min readenInsight

Summary

A critical security vulnerability (CVE-2025-53773) in GitHub Copilot allows attackers to achieve remote code execution by placing the AI assistant into 'YOLO mode' through manipulation of the project's settings.json file. This bypasses user approval mechanisms and enables full system compromise of the developer's machine, representing a serious prompt injection attack vector in AI-powered development tools.

Key quotes

· 4 pulled
This post is about an important, but also scary, prompt injection discovery that leads to full system compromise of the developer's machine in GitHub Copilot and VS Code.
It is achieved by placing Copilot into YOLO mode by modifying the project's settings.json file.
An attacker can put GitHub Copilot into YOLO mode by modifying the project's settings.json file on the fly, and then executing commands, all without user approval.
This is not uncommon and is an area to always look for when performing a security assessment of AI agents.
Snippet from the RSS feed
An attacker can put GitHub Copilot into YOLO mode by modifying the project's settings.json file on the fly, and then executing commands, all without user approval

You might also wanna read