EUVD-2026-12454

LibreChat RAG API, version 0.7.0, contains a log-injection vulnerability that allows attackers to forge log entries...

LibreChat RAG API 安全漏洞

LibreChat RAG API is an open-source interface service for building retrieval-enhanced generation capabilities in LibreChat. Version 0.7.0 of the LibreChat RAG API contains a security vulnerability, which stems from log injection, potentially allowing attackers to forge log entries...

SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection

Large language models LLMs have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language HDL datasets. This knowledge gap constrains LLM performan...

ai-security-toolkit

...

This Week in Spring - February 24th, 2026

Hi, Spring fans! Welcome to another awesome and oh-so-agentic week in Spring! We've got a ton to look into, and I've got even more to prepare for next week's DevNexus event in Atlanta, GA, so let's dive right into it! Be sure to say "hi" if you're going to be there, though! You've heard of Agent...

EUVD-2026-6091

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

CVE-2026-2555

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

CVE-2026-2555 JeecgBoot Retrieval-Augmented Generation AiragKnowledgeController.java importDocumentFromZip deserialization

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

CVE-2026-2555

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

CVE-2026-2111

A weakness has been identified in JeecgBoot up to 3.9.0. Affected by this issue is some unknown functionality of the file /airag/knowledge/doc/edit of the component Retrieval-Augmented Generation Module. Executing a manipulation of the argument filePath can lead to path traversal. The attack can ...

CVE-2026-2111

A weakness has been identified in JeecgBoot up to 3.9.0. Affected by this issue is some unknown functionality of the file /airag/knowledge/doc/edit of the component Retrieval-Augmented Generation Module. Executing a manipulation of the argument filePath can lead to path traversal. The attack can ...

CVE-2026-2111 JeecgBoot Retrieval-Augmented Generation edit path traversal

A weakness has been identified in JeecgBoot up to 3.9.0. Affected by this issue is some unknown functionality of the file /airag/knowledge/doc/edit of the component Retrieval-Augmented Generation Module. Executing a manipulation of the argument filePath can lead to path traversal. The attack can ...

EUVD-2026-5716

A weakness has been identified in JeecgBoot up to 3.9.0. Affected by this issue is some unknown functionality of the file /airag/knowledge/doc/edit of the component Retrieval-Augmented Generation Module. Executing a manipulation of the argument filePath can lead to path traversal. The attack can ...

CVE-2026-2111

JeecgBoot

JeecgBoot 路径遍历漏洞

JeecgBoot is a Java low-code platform developed by Jeecg Corporation, designed for enterprise web applications. JeecgBoot versions 3.9.0 and earlier contained a path traversal vulnerability. This vulnerability stemmed from incorrect handling of the parameter “filePath” in the Component...

Persistent Human Feedback, LLMs, and Static Analyzers for Secure Code Generation and Vulnerability Detection

Existing literature heavily relies on static analysis tools to evaluate LLMs for secure code generation and vulnerability detection. We reviewed 1,080 LLM-generated code samples, built a human-validated ground-truth, and compared the outputs of two widely used static security tools, CodeQL and...

User-Centric Phishing Detection: A RAG and LLM-Based Approach

The escalating sophistication of phishing emails necessitates a shift beyond traditional rule-based and conventional machine-learning-based detectors. Although large language models LLMs offer strong natural language understanding, using them as standalone classifiers often yields elevated...

Lightweight LLMs for Network Attack Detection in IoT Networks

The rapid growth of Internet of Things IoT devices has increased the scale and diversity of cyberattacks, exposing limitations in traditional intrusion detection systems. Classical machine learning ML models such as Random Forest and Support Vector Machine perform well on known attacks but requir...

Rethinking On-Device LLM Reasoning: Why Analogical Mapping Outperforms Abstract Thinking for IoT DDoS Detection

The rapid expansion of IoT deployments has intensified cybersecurity threats, notably Distributed Denial of Service DDoS attacks, characterized by increasingly sophisticated patterns. Leveraging Generative AI through On-Device Large Language Models ODLLMs provides a viable solution for real-time...

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems

The rapid advancement of Large Language Models LLMs presents new opportunities for automated software vulnerability detection, a crucial task in securing modern codebases. This paper presents a comparative study on the effectiveness of LLM-based techniques for detecting software vulnerabilities...