Reasoning Introduces New Poisoning Attacks yet Makes Them More Complicated

Early research into data poisoning attacks against Large Language Models LLMs demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the intermediate chain-of-thought CoT and its inherent trait of...

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System

LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt TIP, which...

Adversarial Bug Reports As a Security Risk in Language Model-Based Automated Program Repair

Large Language Model LLM - based Automated Program Repair APR systems are increasingly integrated into modern software development workflows, offering automated patches in response to natural language bug reports. However, this reliance on untrusted user input introduces a novel and underexplored...

An Empirical Study of Vulnerabilities in Python Packages and Their Detection

In the rapidly evolving software development landscape, Python stands out for its simplicity, versatility, and extensive ecosystem. Python packages, as units of organization, reusability, and distribution, have become a pressing concern, highlighted by the considerable number of vulnerability...

VulRTex: a Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report

Software vulnerabilities exist in open-source software OSS, and the developers who discover these vulnerabilities may submit issue reports IRs to describe their details. Security practitioners need to spend a lot of time manually identifying vulnerability-related IRs from the community, and the...

vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache

...

VULSOVER: Vulnerability Detection Via LLM-Driven Constraint Solving

Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models LLMs, leveraging their ability to understand code semantics has emerged as a promising direction for achieving more...

Human-AI Collaborative Bot Detection in MMORPGs

In Massively Multiplayer Online Role-Playing Games MMORPGs, auto-leveling bots exploit automated programs to level up characters at scale, undermining gameplay balance and fairness. Detecting such bots is challenging, not only because they mimic human behavior, but also because punitive actions...

FALCON: Autonomous Cyber Threat Intelligence Mining with LLMs for IDS Rule Generation

Signature-based Intrusion Detection Systems IDS detect malicious activities by matching network or host activity against predefined rules. These rules are derived from extensive Cyber Threat Intelligence CTI, which includes attack signatures and behavioral patterns obtained through automated tool...

Collaborative Intelligence: Topic Modelling of Large Language Model Use in Live Cybersecurity Operations

Objective: This work describes the topic modelling of Security Operations Centre SOC use of a large language model LLM, during live security operations. The goal is to better understand how these specialists voluntarily use this tool. Background: Human-automation teams have been extensively...

Risk Assessment and Security Analysis of Large Language Models

As large language models LLMs expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence framework that covers their entire life cycle. This paper...

CVE-2025-48956

A flaw was found in vLLM. A denial of service DoS vulnerability can be triggered by sending a single HTTP GET request with an extremely large X-Forwarded-For header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does n...

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...

CVE-2025-48956

Technical details for CVE-2025-48956 are not publicly available in the provided documents. Monitor for updates from project advisories; no verified affected versions, exploit status, or remediation details are included here.

Stop LLM Attacks: How Security Helps AI Apps Achieve Their ROI

AI security is a business problem. Protect your LLM application investment and ROI by connecting your security team with business stakeholders...

CIA+TA Risk Assessment for AI Reasoning Vulnerabilities

As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning processes from adversarial manipulation. Our contributions...

Systematic Analysis of MCP Security

The Model Context Protocol MCP has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, significantly enhancing their functionality. However, while MCP brings notable benefits, it also introduces significant vulnerabilities, such as Tool Poisoning...

LLM Coding Integrity Breach

Here's an interesting story about a failure being introduced by LLM-written code. Specifically, the LLM was doing some code refactoring, and when it moved a chunk of code from one file to another it changed a "break" to a "continue." That turned an error logging statement into an infinite loop,...

CVE-2025-54382 Cherry Studio RCE Vulnerability Disclosure

Cherry Studio is a desktop client that supports for multiple LLM providers. In version 1.5.1, a remote code execution RCE vulnerability exists in the Cherry Studio platform when connecting to streamableHttp MCP servers. The issue arises from the server’s implicit trust in the oauth auth redirecti...

CVE-2025-45146

ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/datamanager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data...