PYSEC-2026-406 mamba language model framework vulnerable to insecure deserialization when loading pre-trained models from HuggingFace Hub

The mamba language model framework thru 2.2.6 is vulnerable to insecure deserialization CWE-502 when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.frompretrained method uses torch.load to load the pytorchmodel.bin weight file without enabling the security-restrictive...

MLFlow Path Traversal Vulnerability

A malicious user could use this issue to get command execution on the vulnerable machine and get access to data & models information...

PYSEC-2026-422 MLFlow Path Traversal Vulnerability

A malicious user could use this issue to get command execution on the vulnerable machine and get access to data & models information...

PYSEC-2026-417 Remote Code Execution due to Full Controled File Write in mlflow

The mlflow web server includes tools for tracking experiments, packaging code into reproducible runs, and sharing and deploying models. As this vulnerability allows to write / overwrite any file on the file system, it gives a lot of ways to archive code execution like overwriting /home//.bashrc. ...

PYSEC-2026-514 Rasa Allows Remote Code Execution via Remote Model Loading

Vulnerability A vulnerability has been identified in Rasa Pro and Rasa Open Source that enables an attacker who has the ability to load a maliciously crafted model remotely into a Rasa instance to achieve Remote Code Execution. The prerequisites for this are: - The HTTP API must be enabled on the...

CVE-2025-7386

Information exposure vulnerability in Hitachi Storage Navigator. This issue affects Hitachi Virtual Storage Platform 5100, 5200, 5500, 5600, 5100H, 5200H, 5500H, 5600H, VX8: before DKCMAIN Ver. 90-09-24-00/00, SVP Ver. 90-09-24/00, before DKCMAIN Ver. 90-08-86-00/00, SVP Ver. 90-08-86/00; Hitachi...

CVE-2025-2902 Improper Authorization Vulnerability of Maintenance Utility in Hitachi Virtual Storage Platform

Improper Authorization Vulnerability of Maintenance Utility in Hitachi Virtual Storage Platform. This issue affects Hitachi Virtual Storage Platform E390, E590, E790, E990, E1090, E390H, E590H, E790H, E1090H: before DKCMAIN Ver. 93-07-26-xx/00, GUM Ver. 93-07-26/00; Hitachi Virtual Storage Platfo...

CVE-2025-0824

Lack of validation for firmware update in Hitachi Hitachi Virtual Storage Platform One Block 23, 24, 26, 28. This issue affects Hitachi Virtual Storage Platform One Block 23, 24, 26, 28: before DKCMAIN A3-04-21-40/00, ESM A3-04-21/00...

CVE-2026-47155

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The revision pinning controls in vLLM do not consistently apply to all artifacts loaded for a model. This allows a deployment configured with specific revisions to still load dynamic code or other...

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which corrupts tasks that must preserve it, such as translation and document editing. Attack-success metrics cannot see this,...

AI-Generated PowerShell Malware: An Experimental Framework and Dataset

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive...

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems MAS are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize...

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

Researchers and practitioners increasingly apply Large Language Models LLMs for automated vulnerability detection. Recent work has shown that LLMs are susceptible to the same cognitive heuristics that bias human judgment. Yet, no work has investigated whether these heuristics affect a model's...

Forensic Trajectory Signatures for Agent Memory Poisoning Detection

We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through observable memory-tool invocations, successful attacks require calling memoryrecallfact before emailsendemail, a transition that non-exfiltrating...

Understanding and Evaluating Claw-Like Agent Security through a Computer-Systems Lens

Claw-like AI agents e.g., OpenClaw are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more...

Top Cyber Range Providers: A Comparison of 15 Leading Platforms

Compare 15 cyber range platforms across live-fire exercises, AI testing, SOC training, OT realism, deployment options, pricing models, and data residency needs...

An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models across Multilingual and Obfuscated Attack Scenarios

Large Language Models LLMs have rapidly evolved, transforming industries by automating complex tasks and generating human-like content. However, as their adoption accelerates, prompt injection vulnerabilities have become increasingly apparent. Malicious actors exploit these weaknesses to generate...

Missing Authentication For Critical Function

Backpropagate is vulnerable to Missing Authentication for Critical Function. The vulnerability is due to the Reflex web UI failing to enforce the --auth authentication mechanism despite indicating it is enabled, which allows an attacker who can access the exposed UI port to perform unauthorized...

Cybersecurity Is the True Frontier for Generative AI Success or Failure

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models LLMs to automate processes as "agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various...

FlipGuard: Defending Large Language Models against Quantization-Conditioned Backdoor Attacks

Model quantization is essential for the efficient deployment of Large Language Models LLMs, but introduces a critical vulnerability: Quantization-Conditioned Backdoor QCB attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific...