MAL-2025-191789 Malicious code in mcp-weather-full (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 c12eff5425b0aa04547b3bbff3444c1d96ca3cf765fdc105d7b7ff9252c9afda Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting

As the role of Large Language Models LLM-based coding assistants in software development becomes more critical, so does the role of the bugs they generate in the overall cybersecurity landscape. While a number of LLM code security benchmarks have been proposed alongside approaches to improve the...

Black-Box Guardrail Reverse-Engineering Attack

Large language models LLMs increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While effective at mitigating harmful responses, these guardrails introduce a new class of vulnerabilities by exposing observable decision patterns. In this...

Large Language Models for Cyber Security

This paper studies the integration off Large Language Models into cybersecurity tools and protocols. The main issue discussed in this paper is how traditional rule-based and signature based security systems are not enough to deal with modern AI powered cyber threats. Cybersecurity industry is...

PT-2025-45299

Name of the Vulnerable Software and Affected Versions tagDiv Cloud Library versions prior to 3.9.2 Description The tagDiv Cloud Library contains a flaw related to improper input handling during web page generation, leading to a DOM-Based Cross-site Scripting XSS condition. This allows for the...

CVE-2025-64109

Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...

Malicious code in wayspiritmcp-tpa (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

MAL-2025-191924 Malicious code in wayspiritmcp-enconly (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 b075eb7116e55dd48db0e026ce51a42ec4e7e1e100b4b68c8a42d4b35411f749 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

Malicious code in wayspiritmcp-weather (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 c3dbe830c7b2364daef2e4634c16062b86b0b26b88f95533e9413aa91bc646fd Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...

CVE-2025-63418

A DOM-based Cross-Site Scripting XSS vulnerability in the SelfBest platform 2023.3 allows attackers to execute arbitrary JavaScript in the context of a logged-in user's session by injecting payloads via the browser's developer console. The vulnerability arises from the application's client-side...

CVE-2025-63418

A DOM-based Cross-Site Scripting XSS vulnerability in the SelfBest platform 2023.3 allows attackers to execute arbitrary JavaScript in the context of a logged-in user's session by injecting payloads via the browser's developer console. The vulnerability arises from the application's client-side...

CGA-46MF-W938-7237

Bulletin has no description...

CVE-2025-11690

An Insecure Direct Object Reference IDOR vulnerability exists in the vehicleId parameter, allowing unauthorized access to sensitive information of other users’ vehicles. Exploiting this issue enables an attacker to retrieve data such as GPS coordinates, encryption keys, initialization vectors,...

Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback

Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I present a hybrid fuzzing framework that integrates static an...

Unity Linux 20.1070a Security Update: kernel (UTSA-2025-989908)

"The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-989908 advisory. In the Linux kernel, the following vulnerability has been resolved: usb: gadget: fncm: fix potential NULL ptr deref in ncmbitrate In Google internal bug 265639009...

AIxBlock Cross-Site Scripting Vulnerability

AIxBlock is an AI automation platform. A cross-site scripting vulnerability exists in AIxBlock version 04f305, which stems from a modeldesc field that does not validate input and can be exploited by an attacker to cause a stored cross-site scripting attack...

PT-2026-22403

Name of the Vulnerable Software and Affected Versions Docker Model Runner versions prior to 1.0.16 Docker Desktop versions prior to 4.61.0 when Model Runner is enabled Description Docker Model Runner is software used to manage, run, and deploy AI models using Docker. Versions prior to 1.0.16 expo...

Design and Detection of Covert Man-In-The-Middle Cyberattacks on Water Treatment Plants

Cyberattacks targeting critical infrastructures, such as water treatment facilities, represent significant threats to public health, safety, and the environment. This paper introduces a systematic approach for modeling and assessing covert man-in-the-middle MitM attacks that leverage system...

CVE-2025-64110 Cursor: Authentication Bypass Possible via New Cursorignore Write

Cursor is a code editor built for programming with AI. In versions 1.7.23 and below, a logic bug allows a malicious agent to read sensitive files that should be protected via cursorignore. An attacker who has already achieved prompt injection, or a malicious model, could create a new cursorignore...

CVE-2025-64109 Cursor CLI Beta: Command Injection via Untrusted MCP Configuration

Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...