Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...

Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs

Phishing websites pose a major cybersecurity threat, exploiting unsuspecting users and causing significant financial and organisational harm. Traditional machine learning approaches for phishing detection often require extensive feature engineering, continuous retraining, and costly infrastructur...

Towards Classifying Benign and Malicious Packages Using Machine Learning

Recently, the number of malicious open-source packages in package repositories has been increasing dramatically. While major security scanners focus on identifying known Common Vulnerabilities and Exposures CVEs in open-source packages, there are very few studies on detecting malicious packages...

EUVD-2025-198042

A command injection vulnerability exists in the MCP Data Science Server's reading-plus-ai/mcp-server-data-exploration 0.1.6 in the safeeval function src/mcpserverds/server.py:108. The function uses Python's exec to execute user-supplied scripts but fails to restrict the builtins dictionary in the...

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security

As the use of large language models LLMs continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a tangible threat across industries, driving the need for...

GHSA-8GW3-RXH4-V6JX expr-eval vulnerable to Prototype Pollution

npm package expr-eval is vulnerable to Prototype Pollution. An attacker with access to express eval interface can use JavaScript prototype-based inheritance model to achieve arbitrary code execution. The npm expr-eval-fork package resolves this issue...

CVE-2025-13204

The expr-eval and expr-eval-fork npm packages are vulnerable to Prototype Pollution due to improper handling of JavaScript prototype-based inheritance in the eval interface . An attacker with access to the express eval interface can exploit this flaw to achieve arbitrary code execution . This vul...

NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due to their inherent dependence on specific contexts. To...

SoK: Security Evaluation of Wi-Fi CSI Biometrics: Attacks, Metrics, and Systemic Weaknesses

Wi-Fi Channel State Information CSI has been repeatedly proposed as a biometric modality, often with reports of high accuracy and operational feasibility. However, the field lacks a consolidated understanding of its security properties, adversarial resilience, and methodological consistency. This...

Unity Linux 20.1070e Security Update: libxslt (UTSA-2025-990908)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-990908 advisory. Uncontrolled recursion inXPath evaluationin libxml2 up to and including version 2.9.14 allows a local attacker to cause a stack overflow via crafted expressions. XPa...

General Industrial Controls Lynx+ Gateway

RISK EVALUATION Successful exploitation of these vulnerabilities could result in obtaining sensitive device information, unauthorized access, or create a denial-of-service condition. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of...

Rockwell Automation Verve Asset Manager

RISK EVALUATION Successful exploitation of this vulnerability could result in an attacker accessing or altering user data. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability, such as: Minimize network exposure for all...

Brightpick Mission Control / Internal Logic Control (Update A)

RISK EVALUATION Successful exploitation of these vulnerabilities could result in the exposure of sensitive information and the manipulation of critical functions by an attacker. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these...

Can AI Models Be Jailbroken to Phish Elderly Victims? an End-To-End Evaluation

We present an end-to-end demonstration of how attackers can exploit AI safety failures to harm vulnerable populations: from jailbreaking LLMs to generate phishing content, to deploying those messages against real targets, to successfully compromising elderly victims. We systematically evaluated...

Siemens SIMATIC S7-1500 NULL Pointer Dereference (CVE-2018-14404)

A NULL pointer dereference vulnerability exists in the xpath.c:xmlXPathCompOpEval function of libxml2 through 2.9.8 when parsing an invalid XPath expression in the XPATHOPAND or XPATHOPOR case. Applications processing untrusted XSL format inputs with the use of the libxml2 library may be vulnerab...

EUVD-2025-117008

Malicious code in varying-harlequin-pig npm...

Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code

AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of these generated code snippets remains essential. A key...

Unity Linux 20.1070e Security Update: kernel (UTSA-2025-990883)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-990883 advisory. In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: prevent NULL pointer dereference if ATIF is not supported acpievaluateobject may retu...

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-Based Agents in Security Patch Detection

The widespread adoption of open-source software OSS has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models LLMs and LLM-based agents have demonstrated remarkable...

QLCoder: A Query Synthesizer for Static Analysis of Security Vulnerabilities

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder...