Researchers exploit flaws in five AI coding assistants’ browsers
Researchers at Forever Security found vulnerabilities in the embedded browsers of five AI coding tools: Cursor, GitHub Copilot, OpenAI’s Codex, Microsoft’s VS Code, and Anthropic’s Claude Desktop. Each tool violated at least one of three core browser security rules: running untrusted code, reading local files beyond their project folders, or allowing arbitrary address bar changes. In Codex and…
Key points
- Forever Security found five AI coding tools violated browser security rules, letting attackers read files or run code
- Codex and VS Code remain unpatched as of October 29, risking full-disk access via a single local file
- Cursor and Copilot patched their flaws in October, but OpenAI has not addressed Codex’s unpatched vulnerability
The story so far
2 episodes →- Researchers exploit flaws in five AI coding assistants’ browsersthis story
Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop
helpnetsecurity.com · 29 October 2026
Loading the full article…
This text was published by helpnetsecurity.com and written by Mirko Zorz. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Society & Work
All →- xAI offers Mississippi residents buyouts to avoid noise lawsuit · 3 src
- New York Times adds more AI features to its Cooking app. Users aren't thrilled · 2 src
- Opinion: AI overload leaves creators questioning its purpose · 1 src
- Unit 42 warns of hidden instructions in documents targeting AI agents · 1 src
- Pluto Security finds 31 malicious Hugging Face model repos with 29K downloads · 1 src
Comments
via GitHub Discussions