Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy

Large Language Models LLMs are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs may introduce critical vulnerabilities in these systems. Here, we explore the impact of prompt-injection attacks targeting consensus...

Linux Distros Unpatched Vulnerability : CVE-2019-11697

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - If the ALT and a keys are pressed when users receive an extension installation prompt, the extension will be installed without the install prompt delay that kee...

CVE-2025-54130

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

CVE-2025-54130 Cursor Agent is vulnerable prompt injection via Editor Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

CVE-2025-54130

CVE-2025-54130 (Cursor) affects Cursor, a code editor with AI features. In versions

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

CVE-2025-54135

Cursor before v1.3.9 allows prompt-injection via MCP MCP server data to auto-run and write to ~/.cursor/mcp.json, enabling RCE when processing external content. Affected: Cursor AI code editor (Cursor) in-workspace file writes without user approval; dotfiles require approval but new dotfiles do n...

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code...

From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format

Existing cybersecurity playbooks are often written in heterogeneous, non-machine-readable formats, which limits their automation and interoperability across Security Orchestration, Automation, and Response platforms. This paper explores the suitability of Large Language Models, combined with Prom...

CVE-2025-54135: Improper Neutralization of Special Elements used in an OS Command

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

CVE-2025-54130: Improper Authorization

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions less than 1.3.9. If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive editor files, such as the...

CVE-2025-54132

Cursor is a code editor built for programming with AI. In versions below 1.3, Mermaid which is used 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 serve...

CVE-2025-54131

Cursor is a code editor built for programming with AI. In versions below 1.3, an attacker can bypass the allow list in auto-run mode with a backtick or $cmd. If a user has swapped Cursor from its default settings requiring approval for every terminal call to an allowlist, an attacker can execute...

A Survey on Data Security in Large Language Models

Large Language Models LLMs, now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often...

📄 Malicious XDG Desktop File

This Metasploit module creates a malicious XDG Desktop .desktop file. On most modern systems, desktop files are not trusted by default. The user will receive a warning prompt that the file is not trusted when running the file, but may choose to run the file anyway. The default file manager...

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

Large language model LLM agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface: adversaries can manipulate tool metadata -- such as names,...