Red Teaming Program Repair Agents: When Correct Patches Can Hide Vulnerabilities

LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair APR. APR agents automatically fetch GitHub issues and use backend LLMs to generate patches that fix the reported bugs. However, existing work primarily focuses on the functional correctness ...

MAVUL: Multi-Agent Vulnerability Detection Via Contextual Reasoning and Interactive Refinement

The widespread adoption of open-source software OSS necessitates the mitigation of vulnerability risks. Most vulnerability detection VD methods are limited by inadequate contextual understanding, restrictive single-round interactions, and coarse-grained evaluations, resulting in undesired model...

CHAI: Command Hijacking against Embodied AI

Embodied Artificial Intelligence AI promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to novel real-world situations. These capabilities, however, al...

SoK: Systematic Analysis of Adversarial Threats against Deep Learning Approaches for Autonomous Anomaly Detection Systems in SDN-IoT Networks

Integrating SDN and the IoT enhances network control and flexibility. DL-based AAD systems improve security by enabling real-time threat detection in SDN-IoT networks. However, these systems remain vulnerable to adversarial attacks that manipulate input data or exploit model weaknesses,...

CodeQL zero to hero part 5: Debugging queries

When you're first getting started with CodeQL, you may find yourself in a situation where a query doesn't return the results you expect. Debugging these queries can be tricky, because CodeQL is a Prolog-like language with an evaluation model that's quite different from mainstream languages like...

A Hybrid CAPTCHA Combining Generative AI with Keystroke Dynamics for Enhanced Bot Detection

Completely Automated Public Turing tests to tell Computers and Humans Apart CAPTCHAs are a foundational component of web security, yet traditional implementations suffer from a trade-off between usability and resilience against AI-powered bots. This paper introduces a novel hybrid CAPTCHA system...

Important: kernel-livepatch-6.1.141-167.250

Issue Overview: In the Linux kernel, the following vulnerability has been resolved: bridge: mcast: Fix use-after-free during router port configuration CVE-2025-38248 In the Linux kernel, the following vulnerability has been resolved: ACPICA: Refuse to evaluate a method if arguments are missing...

Quant Fever, Reasoning Blackholes, Schrodinger'S Compliance, and More: Probing GPT-OSS-20B

OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought CoT reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model's behavior under different adversarial conditions. Using the Jailbreak Oracle J...

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence

Large Language Models LLMs are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence CTI to support vulnerability assessment and incident response. While recent work has shown that LLMs can support a wid...

Automatic Red Teaming LLM-Based Agents with Model Context Protocol Tools

The remarkable capability of large language models LLMs has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol MCP tools have become the de facto standard and are now widely...

SoK: Potentials and Challenges of Large Language Models for Reverse Engineering

Reverse Engineering RE is central to software security, enabling tasks such as vulnerability discovery and malware analysis, but it remains labor-intensive and requires substantial expertise. Earlier advances in deep learning start to automate parts of RE, particularly for malware detection and...

CVE-2025-48868 Horilla vulnerable to authenticated RCE via eval() in project_bulk_archive

Horilla is a free and open source Human Resource Management System HRMS. An authenticated Remote Code Execution RCE vulnerability exists in Horilla 1.3.0 due to the unsafe use of Python’s eval function on a user-controlled query parameter in the projectbulkarchive view. This allows privileged use...

Horilla 安全漏洞

Horilla is a free and open source human resources software from Horilla, Inc. A security vulnerability exists in Horilla version 1.3.0 that stems from the unsafe use of the eval function for user-controlled query parameters, which could lead to remote code execution...

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation

Fine-tuning large language models LLMs with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific domains. Given the shared characteristics in data across different organizations, the idea of collaboratively fine-tuning an LLM using data from multiple...

10 Evaluation Points for Your App Platform on Kubernetes

...

CVE-2025-59528

Flowise is a drag & drop user interface to build a customized large language model flow. In version 3.0.5, Flowise is vulnerable to remote code execution. The CustomMCP node allows users to input configuration settings for connecting to an external MCP server. This node parses the user-provided...

CVE-2025-59528 Flowise has Remote Code Execution vulnerability

Flowise is a drag & drop user interface to build a customized large language model flow. In version 3.0.5, Flowise is vulnerable to remote code execution. The CustomMCP node allows users to input configuration settings for connecting to an external MCP server. This node parses the user-provided...

Evaluating LLM Generated Detection Rules in Cybersecurity

LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark metrics for evaluating LLM-generated cybersecurity rules. The...

MalEval Android Malware Evaluation Framework

This repository contains the source code of MalEval, an evaluation framework for Android malware behavior auditing, focusing on explaining and substantiating malicious behaviors. The framework provides expert-verified reports, curated metadata, and model outputs to enable reproducible evaluation ...

Prototype Pollution

Overview org.webjars.npm:expr-eval is a WebJar for expr-eval Affected versions of this package are vulnerable to Prototype Pollution via the evaluation process, which accesses global values by searching for item.value in expr.functions. An attacker can access prototype, proto, constructor, and...