CVE-2025-10354

Cross-Site Scripting XSS vulnerability reflected in Semantic MediaWiki. This vulnerability allows an attacker to execute JavaScript code in the victim's browser by sending them a malicious URL using the '/index.php/Speciaal:GefacetteerdZoeken' endpoint parameter. This vulnerability can be exploit...

CodeQL 2.25.6

Discover vulnerabilities across a codebase with CodeQL, an industry-leading semantic code analysis engine. CodeQL lets you query code as though it were data. Write a query to find all variants of a vulnerability, eradicating it forever. Then share your query to help others do the same...

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems

Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contributors can hide harmful behavior inside skills that appear benign under superficial inspection. However, existing...

CVE-2026-44905

Vanetza (ETSI C-ITS) contains a denial-of-service condition in 26.02 and earlier due to a logic flaw in the cryptographic verification path. An incoming V2X certificate with a Psid subtype violation can be parsed syntactically, but semantic checks are not enforced until re-encoding during Straigh...

CVE-2026-44905

Vanetza is an open-source implementation of the ETSI C-ITS protocol suite. In 26.02 and earlier, a denial-of-service vulnerability was identified in the cryptographic verification pipeline of Vanetza. When processing incoming V2X messages, the ASN.1 decoder accepts the structure as syntactically...

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models LLMs are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and...

Vanetza 安全漏洞

Vanetza is an open-source implementation of a vehicle communication protocol suite developed by Raphael Riebl. Versions of Vanetza prior to 26.02 contained security vulnerabilities. These vulnerabilities stemmed from the ASN.1 decoder accepting V2X messages that are syntactically valid but...

CodeQL 2.25.5

Discover vulnerabilities across a codebase with CodeQL, an industry-leading semantic code analysis engine. CodeQL lets you query code as though it were data. Write a query to find all variants of a vulnerability, eradicating it forever. Then share your query to help others do the same...

MAL-2026-4760 Malicious code in nvidia-nat-semantic-kernel (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fd31ef3bb7acb152519e55b43037368e8dfc21d444050bec7739778c4ce73381 The wheel's METADATA declares a hard dependency Requires-Dist: ruamel-yaml-clibz==0.3.5. The legitimate upstream is ruamel.yaml.clib with dots...

Malicious code in nvidia-nat-semantic-kernel (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fd31ef3bb7acb152519e55b43037368e8dfc21d444050bec7739778c4ce73381 The wheel's METADATA declares a hard dependency Requires-Dist: ruamel-yaml-clibz==0.3.5. The legitimate upstream is ruamel.yaml.clib with dots...

Not What You Asked For: Typographic Attacks in Household Robot Manipulation

Open-vocabulary embodied AI agents increasingly rely on vision-language models such as CLIP for object perception and task grounding. However, the shared embedding space that enables this flexibility introduces a structural vulnerability to typographic attacks, where printed text in a physical...

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents

Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented, typically assuming predefined target events and a fixed set o...

Exploiting LLM Agent Supply Chains Via Payload-Less Skills

Autonomous agents powered by Large Language Models LLMs acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms a...

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these specification violations: benign inputs cause a skill to breach...

VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics required for accurate detection. Recent Large Language...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

Can a Single Message Paralyze the AI Infrastructure? the Rise of AbO-DDoS Attacks through Targeted Mobius Injection

Large Language Model LLM agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of...

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models LLMs that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usabili...

Under the Hood of SKILL.Md: Semantic Supply-Chain Attacks on AI Agent Skill Registry

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability expansion, it also introduces a semantic supply-chain risk in...

OverrideFuzz: Semantic-Aware Grammar Fuzzing for Script-Runtime Vulnerabilities

Script-language runtimes such as Python, Lua, and JavaScript are widely deployed in security sensitive contexts, yet they remain difficult to test because valid inputs must satisfy syntax, dynamic type constraints, and object-level semantics. Existing grammar and reflection-based fuzzers improve...