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...

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...

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...

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...

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...

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...

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

When prompts become shells: RCE vulnerabilities in AI agent frameworks

In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...

When prompts become shells: RCE vulnerabilities in AI agent frameworks

In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...

Cryptographic and Information-Theoretic Security Capacities for General Arbitrarily Varying Wiretap Channels

We compare the strong secrecy capacities of Arbitrarily Varying Wiretap Channels AVWCs and General Arbitrary Varying Wiretap Channels GAVWCs with their capacities under semantic secrecy constraint and other equivalent cryptographic secrecy constraints. It turns out that the average error and stro...

Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers Using TRUSTEE

Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the...

AFL-ICP: Enhancing Industrial Control Protocol Reliability Via Specification-Guided Fuzzing

Industrial Control Protocols ICPs are critical to the reliability and stability of industrial infrastructure, yet their security is fundamentally compromised by a specification-blindness bottleneck. Modern fuzzers, constrained by observation-driven inference, struggle to penetrate deep protocol...

Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis

Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled cybersecurity professionals exacerbates this challenge. While...

The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code

Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based detection. Integrating generative AI into offensive toolchains enables attackers to synthesize structurally diverse payloads with identical behavior,...

CodeQL 2.25.3

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...

WOOTdroid: Whole-System Online On-Device Tracing for Android

System auditing on Android faces two problems. First, existing syscall tracers lose events under load, silently overwriting entries faster than a user space reader can drain them. Second, security-relevant application behavior is mediated through Binder, Android's kernel IPC mechanism, and is...

From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension: probabilistic LLMs weaken classical mechanisms for validation,...