TLDR: Amazon’s Gen-AI coding tool, Q Developer, experienced a security breach where a hacker infiltrated it with malicious code, allowing the tool to potentially delete files from users’ computers. The incident, which occurred in late June 2025, involved a hacker submitting a seemingly legitimate ‘Pull Request’ to the GitHub repository hosting Amazon’s Q Developer code. This highlights significant security vulnerabilities in Generative-AI tools and serves as a crucial lesson for engineers using or planning to use such technology for software coding.
In late June 2025, Amazon’s AI-powered coding assistant, Q Developer, was subjected to a significant security breach, as reported by Bloomberg and 404 Media. A hacker successfully infiltrated the tool by submitting a malicious ‘Pull Request’ to its GitHub repository, disguised as a legitimate update. This malicious code, if executed, could have instructed the AI agent to ‘clean a system to a near-factory state and delete file-system and cloud resources,’ potentially erasing local files and dismantling Amazon Web Services (AWS) cloud infrastructure.
The compromised input was embedded in version 1.84 of the Amazon Q Developer extension for Visual Studio Code, released on July 13. Fortunately, a syntax error in the malicious code prevented it from fully executing, averting a widespread disaster for the nearly one million developers using the extension. The hacker reportedly kept the risk for end-users low to primarily highlight the vulnerability rather than cause extensive damage.
Amazon’s security team responded swiftly, revoking compromised GitHub tokens, purging malicious changes from the repository, and releasing version 1.85.0 without the harmful code. AWS also revised its contribution guidelines five days after the malicious change was introduced, indicating internal measures were already underway before the issue became public. An AWS spokesperson confirmed, ‘Security is our top priority. We quickly mitigated an attempt to exploit a known issue in two open source repositories to alter code in the Amazon Q Developer extension for VS Code and confirmed that no customer resources were impacted.’
Also Read:
- Veracode Report: Nearly Half of AI-Generated Code Contains Security Flaws
- AI-Powered Cursor IDE Faces Critical Prompt-Injection Vulnerability
This incident has sent shockwaves through the developer community, raising urgent questions about the security of AI-powered development tools and the broader implications for supply chain security. It underscores the critical need for enhanced vigilance and robust security protocols as AI tools become increasingly integrated into everyday software development workflows.
