LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing...

Comment and Control: Hijacking Agentic Workflows Via Context-Grounded Evolution

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model LLM agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An...

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models can keep prompted information out of their writing. We giv...

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study

LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners across different sectors lack systematic methods to assess how known threat classes translate into concrete risks within a specific agentic deployment. We present MATRA, a...

LangChain Core 1.3.2 / 0.3.84 Tracer Deserialization / Credential Disclosure

LangChain Core has a tracer deserialization vulnerability that could allow unauthenticated remote credential exfiltration in affected deployments. Versions 1.3.2 and 0.3.84 are affected...

Agentic Fuzzing: Opportunities and Challenges

Fuzzers and static analyzers find many bugs but struggle with logic bugs in mature codebases. Triggering such a bug often requires multi-step reasoning that produces no distinctive execution feedback, and variants can appear across implementations too different for a single pattern to match. Rece...

Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support

Engineering managers increasingly must decide how to introduce generative artificial intelligence AI, retrieval-augmented generation, and coding agents into high-risk operational functions without weakening accountability, privacy, cost discipline, or auditability. The central message of this stu...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous...

Trust Me, Import This: Dependency Steering Attacks Via Malicious Agent Skills

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which attackers may register as malicious packages. In this...

Position: AI Security Policy Should Target Systems, Not Models

We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...

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...

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning

We address a fundamental challenge in cybersecurity operations of translating governance frameworks into actionable mitigation decisions under realistic resource constraints. Frameworks such as the NIST Cybersecurity Framework CSF provide widely adopted measures of organizational maturity, but do...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

Strategic Commitments Shape Collective Cybersecurity under AI Inequality

The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence tools is uneven, resource-limited defenders may be unable to adopt effective protection, creating persistent system vulnerabilities. We study the...

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents

This position paper argues that the Authorization-Execution Gap AEG is a major safety and security problem in open-world agents. The AEG is the divergence between what a principal intends to authorize and what an open-world agent ultimately executes. Because such agents act autonomously across...

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security beyond Binary Scoring

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating, categorizing, and evaluating them systematically. This paper...

AI Native Asset Intelligence

Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI-native security assistants improve access to this data, they remain largely reactive: users must ask the right questions and interpret...

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-Wise Adaptive Regularization Approach

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust...

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...

AI-Accelerated Brute Force Cryptanalysis

Modern cryptography is hinged on "not learning from mistakes": trying numerous wrong keys, should not help one identify the right key. Indeed, it worked -- until recently when the surprising power of AI to see pattern in apparent randomness has turned the 'wrong plaintexts' generated by the 'wron...

Smart Contract Security beyond Detection

Smart contract security has progressed from vulnerability detection toward a broader research agenda that includes semantic reasoning, automated repair, adversarial robustness, and real-time exploit detection. This paper develops a capstone-oriented research narrative around four directions:...

An Automated Framework for Cybersecurity Policy Compliance Assessment against Security Control Standards

Organizational cybersecurity policies are often examined to determine whether they adequately comply standard security controls. This task is difficult because control statements are abstract, whereas policy documents describe governance practices in varied natural language. As a result,...

Apache mod_http2 Double-Free Detector

This is a python script that assist with detecting whether or not a server is vulnerable to the Apache modhttp2 double-free vulnerability...

Can I Check What I Designed? Mapping Security Design DSLs to Code Analyzers

When assessing the potential impact of code-level vulnerabilities, e.g., discovered by automated analyzers, it is essential to consider them in the context of the system's security design. However, this is a challenging task due to the abstraction gap between security design, often specified usin...

On the Security of Research Artifacts

Research artifacts are widely shared to support reproducibility, and artifact evaluation AE has become common at many leading conferences. However, AE mainly checks whether artifacts work as claimed and can be reproduced. It largely overlooks potential security risks. Since these artifacts are...

TOR Virtual Network Tunneling Tool 0.4.9.8

Tor is a network of virtual tunnels that allows people and groups to improve their privacy and security on the Internet. It also enables software developers to create new communication tools with built-in privacy features. It provides the foundation for a range of applications that allow...

Maestro 0.15.4

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

Dash-Uploader 0.7.0a2 Denial of Service

dash-uploader versions 0.1.0 through 0.7.0a2 suffer from multiple denial of service vulnerabilities...

CodeQL 2.25.4

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...

Securing the Dark Matter: A Semantic-Enhanced Neuro-Symbolic Framework for Supply Chain Analysis of Opaque Industrial Software

Automated vulnerability detection in critical-infrastructure software confronts a fundamental barrier: industrial software is routinely deployed as stripped, symbol-free binaries that deprive conventional Software Composition Analysis of the source-level transparency it requires. Existing binary...

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment

Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we identify a critical vulnerability inherent to this paradigm: lowering image resolution inadvertently catalyzes jailbreaking. Our experiments reveal...

When the Ruler Is Broken: Parsing-Induced Suppression in LLM-Based Security Log Evaluation

LLM-based SOC log classifiers are commonly evaluated using regular-expression pipelines that extract structured fields from free-form model output. We demonstrate that this practice introduces a class of silent, systematic evaluation errors, which we term parsing-induced suppression that can caus...

Forensic Analysis of Video Data Deletion and Recovery in Honeywell Surveillance File System

Real-time video surveillance systems store recorded video using digital video recorders DVRs and network video recorders NVRs. To support continuous high-volume video storage, these devices employ specialized, nonstandard file systems that are often proprietary and undocumented. This lack of...

Spying across Chiplets: Side-Channel Attacks in 2.5/3D Integrated Systems

Advanced packaging and chiplet-based integration are increasingly adopted to build complex heterogeneous systems beyond the limits of monolithic scaling. While these architectures offer major benefits in terms of modularity, yield, and performance, they also introduce new physical attack surfaces...

Quantifiable Uncertainty: A Stochastic Consensus Multi-Agent RAG Framework for Robust Malware Detection

While contemporary deep learning malware detectors define a dominant defense paradigm, their sophistication also exposes them to novel structural evasion attacks, a limitation we attribute to their inherent inability to express epistemic uncertainty. To address this challenge, we present MAGMA, a...

From Conceptual Scaffold to Prototype: A Standardized Zonal Architecture for Wi-Fi Security Training

Wi-Fi is the dominant wireless access technology, but its widespread use also exposes systems to threats such as rogue access points, deauthentication attacks, and other IEEE 802.11-specific vulnerabilities. Although Cyber Ranges CRs have become valuable platforms for cybersecurity training and...

ingress-nginx Configuration Injection

A security issue was discovered in ingress-nginx where the nginx.ingress.kubernetes.io/rewrite-target Ingress annotation can be used to inject configuration into nginx. This can lead to arbitrary code execution in the context of the ingress-nginx controller, and disclosure of Secrets accessible t...

DarkMoon - the Open-Source AI-Powered Autonomous Penetration Testing Platform

DarkMoon is an automated penetration testing tool that orchestrates complete security assessments using artificial intelligence security agents. Built as an open-source cybersecurity tool, it enables organizations to run professional-grade vulnerability assessments without manual intervention...

AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey

Security alert screening is the downstream task of filtering, prioritizing, correlating, and contextualizing alerts for analyst attention in Security Operations Centers. This survey reviews artificial-intelligence-driven alert screening and alert-fatigue mitigation from 2015 to 2026. We synthesiz...

OrchJail: Jailbreaking Tool-Calling Text-To-Image Agents by Orchestration-Guided Fuzzing

Tool-calling text-to-image T2I agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into...

Longitudinal Analyses of SAST Tools: A CodeQL Case Study

Open-source software OSS pipelines rely on automated static analysis tools to prevent the introduction of vulnerabilities in code. However, there is limited understanding of the efficacy of these tools across the OSS ecosystem over time. In this paper, we introduce a novel method to evaluate stat...

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code Via Prompt Optimization

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we...

Joern 4.0.536

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

VIM Plugin Persistence

This Metasploit module creates a VIM Plugin which executes a payload on VIM startup...

SL5 Standard for AI Security

Security Level 5 SL5 is a security posture for AI systems that could plausibly thwart top-priority operations by the world's most cyber-capable institutions: those with extensive resources, state-level infrastructure, and expertise years ahead of the public state of the art. The SL5 terminology...

Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses

Image steganography is widely used to protect user privacy and enable covert communication. However, it can also be abused by the adversary as a covert channel to bypass content moderation, disseminate harmful semantics, and even hide malicious instructions in images to elicit dangerous outputs...

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills

Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. However, this growing Skill ecosystem introduces a new compliance risk: a Skill may perform high-impact actions that excee...

LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution

LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and insufficient code-level grounding for identifying malicious and vulnerable code segments. To address these limitations, this research introduces LCC-LL...