Tanium Benchmark 安全漏洞

Tanium Benchmark is a security and operations status assessment module developed by the American company Tanium. Tanium Benchmark has security vulnerabilities, which stem from improper default permission settings...

Bypassing AI Control Protocols Via Agent-As-A-Proxy Attacks

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection IPI attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought CoT and tool-use actions to ensure alignment with user intent. We demonstrate that these...

Benchmarking Large Language Models for Zero-Shot and Few-Shot Phishing URL Detection

The Uniform Resource Locator URL, introduced in a connectivity-first era to define access and locate resources, remains historically limited, lacking future-proof mechanisms for security, trust, or resilience against fraud and abuse, despite the introduction of reactive protections like HTTPS...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

Static Application Security Testing SAST tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives FPs, imposing a substantial manual triage burden on developers. Recent advances in Large Language Model LLM agents offer a promising...

Introducing the WIN Partner Index: The Integrations That Powered Modern Cloud Security in 2025

A data-driven industry benchmark showing how integrations are adopted, gain traction, and deliver value across modern cloud security programs...

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs

LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to unsafe webpages, which can cause severe damage to service...

Explainability Methods for Hardware Trojan Detection: A Systematic Comparison

Hardware trojan detection requires accurate identification and interpretable explanations for security engineers to validate and act on results. This work compares three explainability categories for gate-level trojan detection on the Trust-Hub benchmark: 1 domain-aware property-based analysis of...

TrojanGYM: A Detector-In-The-Loop LLM for Adaptive RTL Hardware Trojan Insertion

Hardware Trojans HTs remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce TrojanGYM, an agentic, LLM-driven framework that automatically curates HT insertions to expose detector blind spots while...

FirmReBugger: A Benchmark Framework for Monolithic Firmware Fuzzers

Monolithic Firmware is widespread. Unsurprisingly, fuzz testing firmware is an active research field with new advances addressing the unique challenges in the domain. However, understanding and evaluating improvements by deriving metrics such as code coverage and unique crashes are problematic,...

GHSA-QP59-X883-77QV ImageMagick has a Memory Leak in LoadOpenCLDeviceBenchmark() when parsing malformed XML

Summary A memory leak vulnerability exists in the LoadOpenCLDeviceBenchmark function in MagickCore/opencl.c. When parsing a malformed OpenCL device profile XML file that contains closing tags, the function fails to release allocated memory for string members platformname, vendorname, name, versio...

EUVD-2026-3700

ImageMagick has a Memory Leak in LoadOpenCLDeviceBenchmark when parsing malformed XML...

Release of Invalid Pointer or Reference

Overview Magick.NET-Q16-arm64 is a Magick.NET allows you can use ImageMagick without having to install ImageMagick on your server or desktop. More information about specific builds see the official docs https://github.com/dlemstra/Magick.NET/tree/main/docs Affected versions of this package are...

ImageMagick has a Memory Leak in LoadOpenCLDeviceBenchmark() when parsing malformed XML

Summary A memory leak vulnerability exists in the LoadOpenCLDeviceBenchmark function in MagickCore/opencl.c. When parsing a malformed OpenCL device profile XML file that contains closing tags, the function fails to release allocated memory for string members platformname, vendorname, name, versio...

Release of Invalid Pointer or Reference

Overview Affected versions of this package are vulnerable to Release of Invalid Pointer or Reference in the LoadOpenCLDeviceBenchmark function when parsing malformed XML files. An attacker can cause memory exhaustion and potential denial of service by placing specially crafted XML files with...

A Risk-Stratified Benchmark Dataset for Bad Randomness (SWC-120) Vulnerabilities in Ethereum Smart Contracts

Many Ethereum smart contracts rely on block attributes such as block.timestamp or blockhash to generate random numbers for applications like lotteries and games. However, these values are predictable and miner-manipulable, creating the Bad Randomness vulnerability SWC-120 that has led to real-wor...

HogVul: Black-Box Adversarial Code Generation Framework against LM-Based Vulnerability Detectors

Recent advances in software vulnerability detection have been driven by Language Model LM-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on...

Knowledge-To-Data: LLM-Driven Synthesis of Structured Network Traffic for Testbed-Free IDS Evaluation

Realistic, large-scale, and well-labeled cybersecurity datasets are essential for training and evaluating Intrusion Detection Systems IDS. However, they remain difficult to obtain due to privacy constraints, data sensitivity, and the cost of building controlled collection environments such as...

PT-2026-20455

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description A flaw exists in the Linux kernel's virtio crypto component related to spinlock protection when handling virtqueue notifications. Specifically, when a virtual machine boots with a single...

SoK: Understanding (New) Security Issues across AI4Code Use Cases

AI-for-Code AI4Code systems are reshaping software engineering, with tools like GitHub Copilot accelerating code generation, translation, and vulnerability detection. Alongside these advances, however, security risks remain pervasive: insecure outputs, biased benchmarks, and susceptibility to...