GitHub Copilot Vulnerability Enables Remote Code Execution via Prompt Injection
By
kerng
Hot, fresh, and worth queueing round the block for.
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 pulledThis 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.
You might also wanna read

GitHub patches critical remote code execution vulnerability in under six hours after AI-assisted discovery
GitHub patched a critical remote code execution vulnerability in under six hours last month. The flaw, discovered by Wiz Research using AI m
GitHub Copilot: A Powerful AI Tool for Debugging Code
The article explores how GitHub Copilot, an AI-powered coding assistant, can significantly streamline the debugging process for developers.

How GitHub's Copilot Secret Scanning Uses AI to Detect Passwords in Code
The article details the development and functionality of GitHub's Copilot secret scanning feature, which uses AI to detect generic passwords
VS Code Remote-SSH Vulnerability Enables Lateral Movement from Developer Machines to Cloud Servers
A critical vulnerability in Visual Studio Code's Remote-SSH extension creates a post-compromise attack path enabling threat actors to pivot
cybersecuritynews.com·2d agoPrompt Injection Attacks: The Top Security Threat Hijacking AI Chatbots
Prompt injection attacks are a critical security vulnerability in AI systems where hidden instructions within user data (like emails or docu
ChatGPT prompt injection vulnerability allows web pages to serve as phishing payloads
A security researcher discovered a prompt injection vulnerability in ChatGPT where the AI cannot distinguish between its own generated conte
