CVE-2025-61592

Cursor CLI (versions ≤ 1.7) is vulnerable to Remote Code Execution via automatic loading of project-specific CLI configuration from /.cursor/cli.json that can override global settings. The underlying issue is permissive configuration combined with prompt injection delivered through project rules ...

CVE-2025-61590

Cursor is a code editor built for programming with AI. Versions 1.6 and below are vulnerable to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to open more than a single folder and save specific settings pretty similar to .vscode/settings.json for...

CVE-2025-61590 Cursor is vulnerable to RCE via .code-workspace files using Prompt Injection

Cursor is a code editor built for programming with AI. Versions 1.6 and below are vulnerable to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to open more than a single folder and save specific settings pretty similar to .vscode/settings.json for...

CVE-2025-61590 Cursor is vulnerable to RCE via .code-workspace files using Prompt Injection

Cursor is a code editor built for programming with AI. Versions 1.6 and below are vulnerable to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to open more than a single folder and save specific settings pretty similar to .vscode/settings.json for...

CVE-2025-61590 Cursor is vulnerable to RCE via .code-workspace files using Prompt Injection

Cursor is a code editor built for programming with AI. Versions 1.6 and below are vulnerable to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to open more than a single folder and save specific settings pretty similar to .vscode/settings.json for...

EUVD-2025-32314

Cursor is a code editor built for programming with AI. Versions 1.6 and below are vulnerable to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to open more than a single folder and save specific settings pretty similar to .vscode/settings.json for...

CVE-2025-61590

Cursor (editor) versions ≤1.6 are vulnerable to remote code execution via Visual Studio Code Workspaces. The attack involves hijacking the user’s chat context to prompt-inject and modify .code-workspace/settings, enabling RCE by writing to the workspace settings. The issue is fixed in version 1.7...

CVE-2025-61589

Cursor is a code editor built for programming with AI. In versions 1.6 and below, Mermaid a to render diagrams allows embedding images which then get rendered by Cursor in the chat box. An attacker can use this to exfiltrate sensitive information to a third-party attacker controlled server throug...

CVE-2025-61589 Cursor: Potential Information Leakage via Mermaid Diagram

Cursor is a code editor built for programming with AI. In versions 1.6 and below, Mermaid a to render diagrams allows embedding images which then get rendered by Cursor in the chat box. An attacker can use this to exfiltrate sensitive information to a third-party attacker controlled server throug...

CVE-2025-61589 Cursor: Potential Information Leakage via Mermaid Diagram

Cursor is a code editor built for programming with AI. In versions 1.6 and below, Mermaid a to render diagrams allows embedding images which then get rendered by Cursor in the chat box. An attacker can use this to exfiltrate sensitive information to a third-party attacker controlled server throug...

CVE-2025-61589 Cursor: Potential Information Leakage via Mermaid Diagram

Cursor is a code editor built for programming with AI. In versions 1.6 and below, Mermaid a to render diagrams allows embedding images which then get rendered by Cursor in the chat box. An attacker can use this to exfiltrate sensitive information to a third-party attacker controlled server throug...

CVE-2025-61589

CVE-2025-61589 affects Cursor: in versions 1.6 and earlier, Mermaid diagram rendering can embed images that are rendered in the chat box, enabling an attacker to exfiltrate sensitive information to a third‑party server via an image fetch after a prompt injection. The issue requires malicious inpu...

PT-2025-40542

Name of the Vulnerable Software and Affected Versions Cursor versions 1.7 and below Description Cursor CLI Agent does not adequately protect its sensitive files, specifically /.cursor/cli.json. This allows attackers to modify the content of these files through prompt injection, potentially leadin...

PT-2025-40459

Name of the Vulnerable Software and Affected Versions Cursor versions 1.6 and below Description Cursor, a code editor for programming with AI, has an issue where Mermaid, used for rendering diagrams, allows embedding images. This can be exploited to exfiltrate sensitive information to a third-par...

PT-2025-40541

Name of the Vulnerable Software and Affected Versions Cursor versions 1.7 and below Description Cursor, a code editor for programming with AI, has an issue where automatic loading of project-specific CLI configuration from the current working directory /.cursor/cli.json could override global...

PT-2025-40535

Name of the Vulnerable Software and Affected Versions Cursor versions 1.6 and below Description Cursor, a code editor for programming with AI, is susceptible to Remote Code Execution RCE attacks through Visual Studio Code Workspaces. Workspaces allow users to save specific settings for folders or...

PT-2025-40600

Name of the Vulnerable Software and Affected Versions Cursor versions 1.6.23 and below Description Cursor IDE has case-sensitive checks when protecting sensitive files, such as /.cursor/mcp.json. This allows attackers to modify these files through prompt injection, potentially leading to remote...

Google Patches “Gemini Trifecta” Vulnerabilities in Gemini AI Suite

Cybersecurity firm Tenable found three critical flaws allowing prompt injection and data exfiltration from Google's Gemini AI. Learn why AI assistants are the new weak link...

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first...

Researchers Disclose Google Gemini AI Flaws Allowing Prompt Injection and Cloud Exploits

Cybersecurity researchers have disclosed three now-patched security vulnerabilities impacting Google's Gemini artificial intelligence AI assistant that, if successfully exploited, could have exposed users to major privacy risks and data theft. "They made Gemini vulnerable to search-injection...