text-generation-inference: Unbounded external image fetch in validation leads to resource-exhaustion DoS

Description Text Generation Inference Router DoS via pre-validation image fetch in VLM mode. Affected: Router workspace version 3.3.6 the latest repo, when deployed with a vision/VLM model e.g., Idefics/Mllama/Idefics2/Idefics3/Gemma3/Llama4/Paligemma/LlavaNext/Qwen2VL/Qwen25VL. Pure text LLMs do...

CVE-2025-10538

An authentication bypass vulnerability exists in LG Innotek camera models LND7210 and LNV7210R. The vulnerability allows a malicious actor to gain access to camera information including user account information...

Integer Overflow lead to DOS in API `v2/models/<model-name>/infer`

This report is not public...

MALF: A Multi-Agent LLM Framework for Intelligent Fuzzing of Industrial Control Protocols

Industrial control systems ICS are vital to modern infrastructure but increasingly vulnerable to cybersecurity threats, particularly through weaknesses in their communication protocols. This paper presents MALF Multi-Agent LLM Fuzzing Framework, an advanced fuzzing solution that integrates large...

Authentication Security of PRF GNSS Ranging

This work derives the authentication security of pseudorandom function PRF GNSS ranging under multiple GNSS spoofing models, including the Security Code Estimation and Replay SCER spoofer. When GNSS ranging codes derive from a PRF utilizing a secret known only to the broadcaster, the spoofer cann...

FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI

Fuzz testing has become a cornerstone technique for identifying software bugs and security vulnerabilities, with broad adoption in both industry and open-source communities. Directly fuzzing a function requires fuzz drivers, which translate random fuzzer inputs into valid arguments for the target...

Backdoor Attacks against Speech Language Models

Large Language Models LLMs and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to cascade domain-specific encoders with an LLM, making the resulting model inherit vulnerabilities from all of its components. In this work, we present the...

PT-2025-40062

Name of the Vulnerable Software and Affected Versions LG Innotek camera models LND7210 and LNV7210R Description An authentication bypass flaw exists in LG Innotek camera models LND7210 and LNV7210R. This allows a malicious actor to gain access to camera information, including user account...

Better Privilege Separation for Agents by Restricting Data Types

Large language models LLMs have become increasingly popular due to their ability to interact with unstructured content. As such, LLMs are now a key driver behind the automation of language processing systems, such as AI agents. Unfortunately, these advantages have come with a vulnerability to...

CHAI: Command Hijacking against Embodied AI

Embodied Artificial Intelligence AI promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to novel real-world situations. These capabilities, however, al...

Apple Security Update: tvOS 26.0.1

Apple recommends to install security update tvOS 26.0.1 on devices Apple TV HD and Apple TV 4K all models...

FuncPoison: Poisoning Function Library to Hijack Multi-Agent Autonomous Driving Systems

Autonomous driving systems increasingly rely on multi-agent architectures powered by large language models LLMs, where specialized agents collaborate to perceive, reason, and plan. A key component of these systems is the shared function library, a collection of software tools that agents use to...

Automated Vulnerability Validation and Verification: A Large Language Model Approach

Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior limits effective vulnerability assessment and mitigation. This...

Binary Diff Summarization Using Large Language Models

Security of software supply chains is necessary to ensure that software updates do not contain maliciously injected code or introduce vulnerabilities that may compromise the integrity of critical infrastructure. Verifying the integrity of software updates involves binary differential analysis...

HFuzzer: Testing Large Language Models for Package Hallucinations Via Phrase-Based Fuzzing

Large Language Models LLMs are widely used for code generation, but they face critical security risks when applied to practical production due to package hallucinations, in which LLMs recommend non-existent packages. These hallucinations can be exploited in software supply chain attacks, where...

SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the...

Benchmarking LLM-Assisted Blue Teaming Via Standardized Threat Hunting

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models LLMs offer promising capabilities for enhancing threat analysis. However, their effectiveness in real-world blue...

AutoML in Cybersecurity: An Empirical Study

Automated machine learning AutoML has emerged as a promising paradigm for automating machine learning ML pipeline design, broadening AI adoption. Yet its reliability in complex domains such as cybersecurity remains underexplored. This paper systematically evaluates eight open-source AutoML...

CVE-2025-11045 WAYOS LQ_04/LQ_05/LQ_06/LQ_07/LQ_09 usb_paswd.asp command injection

A vulnerability was identified in WAYOS LQ04, LQ05, LQ06, LQ07 and LQ09 22.03.17. This affects an unknown function of the file /usbpaswd.asp. The manipulation of the argument Name leads to command injection. The attack can be initiated remotely. The exploit is publicly available and might be used...

CVE-2025-11045

The CVE-2025-11045 entry concerns WAYOS LQ_04/LQ_05/LQ_06/LQ_07/LQ_09 (version 22.03.17) where the Name parameter in an unknown function of the /usb_paswd.asp file enables remote command injection. Affected products are WAYOS routers in the LQ series; the vulnerability’s root cause is improper ha...