Mitigating the OWASP Top 10 for Large Language Models Applications Using Intelligent Agents

Large Language Models LLMs have emerged as a transformative and disruptive technology, enabling a wide range of applications in natural language processing, machine translation, and beyond. However, this widespread integration of LLMs also raised several security concerns highlighted by the Open...

PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair

Continuous fuzzing platforms such as OSS-Fuzz uncover large numbers of vulnerabilities, yet the subsequent repair process remains largely manual. Unfortunately, existing Automated Vulnerability Repair AVR techniques -- including recent LLM-based systems -- are not directly applicable to continuou...

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...

From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks

Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily, making systematic analysis and reproduction highly challenging. In practice, reproducing such attacks requires manually crafting proofs-of-concept PoCs, ...

Why AI Keeps Falling for Prompt Injection Attacks

Imagine you work at a drive-through restaurant. Someone drives up and says: "I'll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer." Would you hand over the money? Of course not. Yet this is what large language models LLMs do...

EUVD-2026-3678

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

CVE-2026-22807

Vulnerability CVE-2026-22807 affects vLLM versions prior to 0.14.0, where during model resolution the engine loads Hugging Face auto_map dynamic modules without gating on trust_remote_code. This allows attacker-controlled Python code in a model repo or path to execute at server startup, before an...

CVE-2026-22807

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path ...

Malicious code in mw-proto-models (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a365899ad5e810104ab4af3dee30bf4bb6ba242dfe2bac8a8b6dce2ce4940dd8 The package mw-proto-models was found to contain malicious code. Source: ghsa-malware 1e2b22967998e78acece8a85fd589aaf543b7744c652af4973aeb8b5b67391a...

MAL-2026-368 Malicious code in mw-proto-models (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a365899ad5e810104ab4af3dee30bf4bb6ba242dfe2bac8a8b6dce2ce4940dd8 The package mw-proto-models was found to contain malicious code. Source: ghsa-malware 1e2b22967998e78acece8a85fd589aaf543b7744c652af4973aeb8b5b67391a...

EUVD-2026-3503

Malicious code in mw-proto-models npm...

Malicious Package

Overview mw-proto-models is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models LLMs convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide...

A Prompt-Based Framework for Loop Vulnerability Detection Using Local LLMs

Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources, or introduce logical errors that degrade performance and compromise security. The problem are often undetected by traditional static analyzers becau...

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...

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models LLMs. By systematically applying carefully engineered prompts, we demonstrate how latent model behaviors can be influenced in...

HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation

Large language models LLMs are being increasingly integrated into practical hardware and firmware development pipelines for code generation. Existing studies have primarily focused on evaluating the functional correctness of LLM-generated code, yet paid limited attention to its security issues...

CVE-2025-55423

A command injection vulnerability exists in the upnprelay function in multiple ipTIME router models because the controlURL value used to pass port-forwarding information to an upper router is passed to system without proper validation or sanitization, allowing OS command injection...

Constructing Multi-Label Hierarchical Classification Models for MITRE ATT&CK Text Tagging

MITRE ATT&CK is a cybersecurity knowledge base that organizes threat actor and cyber-attack information into a set of tactics describing the reasons and goals threat actors have for carrying out attacks, with each tactic having a set of techniques that describe the potential methods used in these...

CVE-2025-55423

CVE-2025-55423 is an OS command-injection vulnerability in the upnp_relay() function affecting ipTIME routers across numerous models (e.g., A2003NS-MU, N600, A604-V3, A6ns-M, V508, N704QCA, A8ns-M, A304, A3004NS-M, A5004NS-M, A9004M, N702R, A604M, A804NS-MU, N804R, A7004M, A8004T, A604G-MU, A3008...