The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system.

Two critical Cursor IDE vulnerabilities, dubbed DuneSlide, let prompt injection break the editor's command sandbox with no ...

Researchers have discovered two vulnerabilities in the widely used Cursor AI-enabled integrated development environment (IDE) ...

Abstract: The Internet of Things (IoT) devices have brought invaluable convenience to our daily lives. However, they also introduce significant security challenges. Common vulnerabilities in numerous ...

Last Tuesday, Microsoft patched a vulnerability it rated as max critical in its M365 Copilot AI platform. On Monday, the researchers who discovered the vulnerability and reported it to Microsoft ...

OpenAI announced a new feature that it says will provide additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in web pages and other content sources.

OpenAI has begun rolling out Lockdown Mode, an optional security setting designed to offer users advanced protection from prompt injection attacks. For the unfamiliar, prompt injection is a form of ...

Add Decrypt as your preferred source to see more of our stories on Google. Prompt injection is the number one security risk for AI applications. The attack works by tricking a chatbot into following ...

The controversy over vibe coding reached a new high this week after a developer added hidden instructions to his open source Java testing app to sabotage projects performed by AI coding agents. The ...

A large-scale campaign is exploiting a critical SQL injection vulnerability (CVE-2026-26980) in Ghost CMS to inject malicious JavaScript code that triggers ClickFix attack flows. The campaign was ...

AI agents have fundamentally changed the threat model of AI model-based applications. By equipping these models with plugins (also called tools), your agents no longer just generate text; they now ...

AI agents are now being weaponized through prompt injection, exposing why model guardrails are not enough to protect enterprise data. Last week, researchers at Google and Forcepoint reported that ...