CVE-2025-8700

Invoice Ninja's configuration on macOS, specifically the presence of entitlement "com.apple.security.get-task-allow", allows local attackers with unprivileged access e.g. via a malicious application to attach a debugger, read or modify the process memory, inject code in the application's context...

CVE-2025-9190

Cursor for macOS 15.4.1 is affected by a RunAsNode fuse misconfiguration that allows a local, unprivileged attacker to execute arbitrary code inheriting Cursor TCC permissions. Access to resources is limited to what the user previously granted; requesting other resources will prompt the user, pot...

CVE-2025-53813 TCC Bypass via misconfigured Node fuses in Nozbe

The configuration of Nozbe on macOS, specifically the "RunAsNode" fuse enabled, allows a local attacker with unprivileged access to execute arbitrary code that inherits Nozbe TCC Transparency, Consent, and Control permissions. Acquired resource access is limited to previously granted permissions...

CVE-2025-53813

CVE-2025-53813 affects Nozbe on macOS due to a misconfiguration of the RunAsNode fuse, enabling a local unprivileged attacker to execute code that inherits Nozbe TCC permissions. Acquired resources are limited to user-granted permissions; other access requires a system prompt. The issue is fixed ...

Linux Distros Unpatched Vulnerability : CVE-2021-45444

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In zsh before 5.8.1, an attacker can achieve code execution if they control a command output inside the prompt, as demonstrated by a %F argument. This occurs...

AI browsers could leave users penniless: A prompt injection warning

Artificial Intelligence AI browsers are gaining traction, which means we may need to start worrying about the potential dangers of something called "prompt injection." Large language models LLMs—like the ones that power AI chatbots including ChatGPT, Claude, and Gemini—are designed to follow...

Safeguarding VS Code against prompt injections

The Copilot Chat extension for VS Code has been evolving rapidly over the past few months, adding a wide range of new features. Its new agent mode lets you use multiple large language models LLMs, built-in tools, and MCP servers to write code, make commit requests, and integrate with external...

Tricking LLM-Based NPCs into Spilling Secrets

Large Language Models LLMs are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remai...

Prompt-In-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

Large Language Models LLMs are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of attacks, prompt in content injection, where adversarial...

CVE-2025-57771

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. In versions prior to 3.25.5, Roo-Code fails to properly handle process substitution and single ampersand characters in the command parsing logic for auto-execute commands. If a user has enabled auto-approved execution...

Mind the Gap: Time-Of-Check to Time-Of-Use Vulnerabilities in LLM-Enabled Agents

Large Language Model LLM-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks e.g., prompt injection and data-oriented threats e.g., data exfiltration...

Malicious code in @listr1/prompt-adapter-inquirer (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 62c9103dcee0afbfa63c69bae22ac8f4e415daef3fcb2610b84d8278b1732f5d Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2025-41269 Malicious code in @listr1/prompt-adapter-inquirer (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 62c9103dcee0afbfa63c69bae22ac8f4e415daef3fcb2610b84d8278b1732f5d Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

CVE-2025-50733

NextChat contains a cross-site scripting XSS vulnerability in the HTMLPreview component of artifacts.tsx that allows attackers to execute arbitrary JavaScript code when HTML content is rendered in the AI chat interface. The vulnerability occurs because user-influenced HTML from AI responses is...

IPIGuard: a Novel Tool Dependency Graph-Based Defense against Indirect Prompt Injection in LLM Agents

Large language model LLM agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources e.g., fetching information from public websites, tool responses may contain...

Experts Find AI Browsers Can Be Tricked by PromptFix Exploit to Run Malicious Hidden Prompts

Cybersecurity researchers have demonstrated a new prompt injection technique called PromptFix that tricks a generative artificial intelligence GenAI model into carrying out unintended actions by embedding the malicious instruction inside a fake CAPTCHA check on a web page. Described by Guardio La...

Linux Distros Unpatched Vulnerability : CVE-2018-6103

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - A stagnant permission prompt in Prompts in Google Chrome prior to 66.0.3359.117 allowed a remote attacker to bypass permission policy via a crafted HTML page...

CCFC: Core and Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

Jailbreak attacks pose a serious challenge to the safe deployment of large language models LLMs. We introduce CCFC Core & Core-Full-Core, a dual-track, prompt-level defense framework designed to mitigate LLMs' vulnerabilities from prompt injection and structure-aware jailbreak attacks. CCFC...

Linux Distros Unpatched Vulnerability : CVE-2024-3303

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior...

CVE-2025-9119

A vulnerability was determined in Netis WF2419 1.2.29433. This vulnerability affects unknown code of the file /index.htm of the component Wireless Settings Page. This manipulation of the argument SSID with the input causes cross site scripting. Remote exploitation of the attack is possible. The...