Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.5

Updated Red Hat Enterprise Linux AI 3.3.5 container images are now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications. This update provides the latest Red Hat Enterprise...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.5

Updated Red Hat Enterprise Linux AI 3.3.5 container images are now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications. This update provides the latest Red Hat Enterprise...

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

Cyber Threat Intelligence CTI reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for automated attack-path reasoning. Existing CTI extraction methods focus on indicators, entities, or TTP labels without modeling the execution conditions...

EUVD-2026-41914

vLLM: Speech-to-text upload size limit is enforced after full UploadFile read...

CVE-2026-55574

A flaw was found in vLLM, a high-throughput and memory-efficient inference and serving engine for large language models LLMs. A remote attacker could exploit this vulnerability by providing a specially crafted regular expression to the structuredoutputs.regex API parameter. This adversarial regex...

PYSEC-2026-1624 Mesop Class Pollution vulnerability leads to DoS and Jailbreak attacks

From @jackfromeast and @superboy-zjc: We have identified a class pollution vulnerability in Mesop = 0.14.0 application that allows attackers to overwrite global variables and class attributes in certain Mesop modules during runtime. This vulnerability could directly lead to a denial of service Do...

CVE-2026-55646

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

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...

CVE-2026-53923

Summary of CVE-2026-53923 : The vulnerability affects vLLM (GGUF dequantize kernels) where integer truncation of tensor dimensions causes partially filled output tensors. From 0.5.5 up to 0.23.1rc0, the code allocates the full output tensor (torch::empty) but the CUDA kernel processes only a trun...

PT-2026-51418

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.22.1 Description vLLM is an inference and serving engine for large language models. The Dockerfile is susceptible to a dependency confusion attack involving the flashinfer-jit-cache package. This occurs because the...

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash ...

Only 10% of SOCs Say They’re Getting Excellent Value From AI. Here’s What the Second Wave Has to Deliver

Eighteen months ago, the AI SOC was a marketing line. Today it's a budget item. The category has crossed over from interesting to inevitable, with billions of dollars now flowing into AI-powered security operations platforms, agentic SOC tools, and AI co-pilots built into every layer of the...

Steering LLM Viewpoints through Fabricated Evidence Injection

As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated...

SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation

Security misconfigurations remain a leading cause of OS-level compromise, and manually keeping systems compliant with standards like Defense Information Systems Agency DISA Security Technical Implementation Guides STIGs is a tedious and expensive process. Existing compliance automation tools can...

Backdoor Unlearning Generalization: A Path toward the Removal of Unknown Triggers in LLMs

Backdoor attacks in Large Language Models LLMs are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown...

Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning

The rapid proliferation of multi-cloud and SaaS platforms has transformed Identity Security Posture Management ISPM into a fundamentally cross-vendor challenge: critical misconfigurations and privilege escalation paths increasingly span multiple identity providers, infrastructure layers, and...

New Russia-Linked GREYVIBE Targets Ukraine with AI-Powered Cyberattacks

A previously undocumented threat actor dubbed GREYVIBE has been attributed to ongoing and persistent attacks targeting Ukraine and Ukraine-related entities since at least August 2025. GREYVIBE, per WithSecure, is assessed to be a Russian-speaking group operating broadly in the Russian time zone,...