AI coding agents are installing MCP servers that will never be patched 2026-11-03 at 07:45 By Mirko Zorz When a developer tells an AI coding agent to “set up a GitHub MCP,” the agent has to pick a package. New research from Glow Labs documents sessions where it picked one out of an archived repository […]
AI coding agents are installing MCP servers that will never be patched Read More »
Malicious Claude Code Extension Served in Cursor Supply Chain Attack 2026-11-02 at 13:29 By Ionut Arghire The extension performed host reconnaissance and attempted to create a reverse SSH tunnel. The post Malicious Claude Code Extension Served in Cursor Supply Chain Attack appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Malicious Claude Code Extension Served in Cursor Supply Chain Attack Read More »
Unpatched Cursor Vulnerability Exposes Users to Code Execution 2026-07-15 at 17:37 By Ionut Arghire An attacker can create a malicious repository containing a git.exe in the project root, and Cursor executes it automatically. The post Unpatched Cursor Vulnerability Exposes Users to Code Execution appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View […]
Unpatched Cursor Vulnerability Exposes Users to Code Execution Read More »
Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution 2026-07-03 at 10:57 By Ionut Arghire The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor’s sandbox and execute arbitrary code on the underlying operating system. The post Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution […]
Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution Read More »
One keypress is all it takes to compromise four AI coding tools 2026-05-08 at 01:14 By Mirko Zorz Developers clone unfamiliar repositories all the time. Open-source projects, work from teammates, sample code from a tutorial, a library someone recommended on a forum. The convention is old and reasonable: you look at what’s inside before you […]
One keypress is all it takes to compromise four AI coding tools Read More »
Cursor AI Vulnerability Exposed Developer Devices 2026-04-17 at 10:30 By Ionut Arghire An indirect prompt injection could be chained with a sandbox bypass and Cursor’s remote tunnel feature for shell access to machines. The post Cursor AI Vulnerability Exposed Developer Devices appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Cursor AI Vulnerability Exposed Developer Devices Read More »
Cursor Automations turns code review and ops into background tasks 2026-03-06 at 12:18 By Anamarija Pogorelec Cursor Automations, the always-on agent platform from Cursor, is expanding with a new generation of autonomous systems that streamline code review, incident response, and other engineering workflows. The platform runs AI agents on schedules or in response to development […]
Cursor Automations turns code review and ops into background tasks Read More »
Default Cursor setting can be exploited to run malicious code on developers’ machines 2025-09-11 at 14:02 By Zeljka Zorz An out-of-the-box setting in Cursor, a popular AI source-code editor, could be leveraged by attackers to covertly run malicious code on users’ computers, researchers have warned. An exploitable vulnerability in the Cursor AI editor Cursor is […]
Default Cursor setting can be exploited to run malicious code on developers’ machines Read More »
Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation 2025-08-07 at 02:36 By Eduard Kovacs Zenity has shown how AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially crafted prompts. The post Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation appeared first on […]
Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation Read More »
Several Vulnerabilities Patched in AI Code Editor Cursor 2025-08-04 at 13:24 By Ionut Arghire Attackers could silently modify sensitive MCP files to trigger the execution of arbitrary code without requiring user approval. The post Several Vulnerabilities Patched in AI Code Editor Cursor appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original […]
Several Vulnerabilities Patched in AI Code Editor Cursor Read More »