Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection,...

Debian Security Advisory 6445-1

Debian Linux Security Advisory 6445-1 - Multiple security vulnerabilities were discovered in Ironic, the OpenStack component to management and provision of baremetal servers, which could result in bypass of administrative access/API restrictions, information disclosure or the execution of arbitra...

Microsoft SharePoint Server SecurityContextToken Deserialization Remote Code Execution

Microsoft SharePoint Server contains an unauthenticated deserialization vulnerability in the /trust/default.aspx WS-Federation endpoint that can allow remote code execution through a crafted SecurityContextToken cookie. This proof of concept uses a BinaryFormatter TypeConfuseDelegate payload...

openSUSE Security Advisory - openSUSE-SU-2026:11528-1

openSUSE Security Advisory - These are all security issues fixed in the wasm-bindgen-0.2.100-2.1 package on the GA media of openSUSE Tumbleweed...

Metabase Authentication Bypass / SQL Injection

Metabase versions x.58.0 through x.63.4 contain an unauthenticated SQL injection vulnerability in the password reset functionality that can allow a remote attacker to manipulate database queries and obtain administrator access. This proof of concept exploits the vulnerable password reset endpoint...

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

Large Language Models LLMs are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs...

Python StateMachine 3.1.2 Remote Code Execution

Python StateMachine 3.1.2 contains a code injection vulnerability in its SCXML processing functionality. The included proof of concept demonstrates code execution by writing a harmless marker file when the malicious SCXML datamodel expression is evaluated...

uproot 5.7.4 TStreamerInfo Code Injection

uproot version 5.7.4 and prior contain a code injection vulnerability in the handling of ROOT TStreamerInfo metadata where attacker-controlled streamer fields are incorporated into dynamically generated Python source without sufficient quoting. A malicious ROOT file can therefore cause arbitrary...

7-Zip 26.01 XZ Decoder Heap Buffer Overflow

7-Zip 26.01 contains a heap buffer overflow vulnerability in the XZ decoder that can be triggered while processing a specially crafted XZ archive. This proof of concept generates a malformed XZ file designed to reproduce the crash condition in the vulnerable multi-threaded XZ decompression path...

Securing AI-Generated Code: A Just-In-Time Vulnerability Detection and Remediation Pipeline

AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify security issues at development velocity, particularly ones that ground remediation in real-world threat context. This paper presents an automated...

MindsDB Minds Platform Cowork Unauthenticated Remote Code Execution

MindsDB Minds Platform Cowork contains an unauthenticated remote code execution vulnerability in the Cowork server API where unauthenticated settings modification can be combined with the Anton agent scratchpad functionality to execute arbitrary Python code without sandboxing. This proof of conce...

Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots

Large language models LLMs are increasingly used to generate textual robot design specifications, interaction policies, and risk assessments during early-stage robot development. Such outputs may influence how surveillance and security robots are conceptualized, documented, and ultimately...

Breaking and Defending LLM-Powered Social Media Bot Detection Systems

The rise of social media bots poses a persistent threat, enabling misinformation, opinion manipulation, and the erosion of trust in online platforms. To combat this, machine learning systems have been developed to detect and limit bot activity, but attackers continuously adapt through techniques...

Bounded Agents: Delegation Security for Multi-Agent AI Systems

LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static, and each request is evaluated independently, without considering prior actions. Within its permissions, an agent may act contra...

Assessing Attack Surfaces in Generative Search Engines through Publisher Attributes: A Case Study in Political Domains

We characterize the attack surface of generative search engines GSEs against poisoning attacks in the political domain, from the perspectives of citation selection and personalization. GSEs integrate web search and answer generation with user preferences and backgrounds using large language model...

When Time Meets Space: Entropy Integration and Dynamic Threshold for Adaptive DDoS Detection in SDN

Entropy-based Distributed Denial of Service DDoS detection in Software-Defined Networking SDN commonly relies on spatial traffic distributions and static or loosely adaptive thresholds, making it vulnerable to legitimate traffic fluctuations in Internet of Things IoT environments. This paper...

Proof-Of-Execution Memory: Defending LLM Agents against Forged-Reasoning Attacks by Verifying What Actually Happened

LLM agents are stateless and rely on external memory to carry context between steps. Because agents treat that memory as trustworthy, an adversary who can write to it can steer their behavior. The FARMA attack does this with no malicious command: it inserts fabricated entries into the agent's...

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands. Decision-theoretic planners provide principled optimization but typically rely on abstract states and...

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

Quantized Vision-Language-Action VLA models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to $0%$, while hundreds of random flips are harmless. Across...

Beyond Direct Access: Resource Hijacking in LLM Agents

Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions...

WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing

In this work, we introduce WeSCE, a benchmark for quantifying security drift in code editing under weak-security constraints, where tasks specify only functional objectives without explicit security requirements. WeSCE consists of 400 executable programs derived from real-world code, covering...

Beyond Single-Vulnerability Evaluation: Closing the Engineering Decision Gap between C Retrofits and Native Safety

While decades of research have produced numerous retrofitted memory-safety protections for C, these mechanisms are almost exclusively evaluated in isolation, targeting specific vulnerability classes. This siloed evaluation paradigm leaves practitioners without a clear understanding of the...

Pre-Model Representation Failures in GNN-Based Smart Contract Vulnerability Detection

This paper is a failure analysis of the representation layer underlying GNN-based smart contract vulnerability detectors. These systems convert source code into graphs before any learning takes place; if the graph fails to capture the code's semantics, no model improvement can compensate. We...

SAEFUZZ: Smart Contract Vulnerability Detection through Statically Guided Evolutionary Fuzzing

The effectiveness of smart contract fuzzing depends strongly on whether generated transactions reach deep, state-dependent execution paths. Existing fuzzers often generate highly random call sequences, wasting executions on semantically invalid or low-value states and leaving vulnerabilities that...

Apple Security Advisory 08-06-2026-2

Apple Security Advisory 08-06-2026-2 - macOS Sequoia 15.7.9 addresses addresses an authentication bypass issue on Screen Sharing...

Trust without Boundaries: An Architectural Analysis of Satellite Flight Software

As spacecraft become more software-driven and interconnected, onboard flight software is an increasingly important security boundary. Popular flight software architectures often treat onboard components as trusted peers, simplifying integration while limiting internal isolation and access control...

Workspace Topology As an Attack Vector in Agentic Coding Assistants

Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this...

MazeRunner: Nonlinear Task and Clue Orchestration for LLM-Driven Black-Box Automated Penetration Testing

Penetration testing is essential yet resource-intensive. Although large language models LLMs show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph...

Finding Vulnerabilities Via LLM-Augmented Semantics-Aware Type-Checking

Vulnerability detection via static analysis traditionally relies on security experts encoding insecure coding patterns into algorithmic rules. However, this approach often focuses on syntactic patterns and overlooks deeper semantic information in the code, such as the meanings of variable and...

BGA: A Noise-Immune Neural Distillation Framework for Malicious Signature Extraction in High-Entropy Encrypted Flows

To mitigate attention dilution in high-entropy TLS 1.3 flows, we propose BGA, a noise-immune neural distillation framework for encrypted threat intelligence.The methodology first employs Analysis of Variance ANOVA to decouple high-discriminatory control-plane features - specifically industrial...

A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models

The modelling and analysis of secure business processes require the incorporation of security annotations into process models. Although BPMN extensions, including SecBPMN2, exist for this purpose, the derivation of accurate and complete security annotations from natural-language specifications...

Apple Security Advisory 08-06-2026-3

Apple Security Advisory 08-06-2026-3 - macOS Sonoma 14.8.9 addresses an authentication bypass issue on Screen Sharing...

Extracting and Verifying Illicit Bitcoin Addresses from Underground Forum Discussions

Existing labeled Bitcoin datasets are largely derived from community-reported abuse, blockchain heuristics, incident-specific collections, or proprietary labeling processes. Their construction methods are rarely publicly reproducible and often provide limited evidence that an address was directly...

Structural Leakage in Graph Encryption: Attacks and Defenses

Graph encryption schemes GES enable secure outsourcing of graph data while supporting efficient queries. This report provides a comprehensive analysis of structural leakage in GES for single-pair shortest path SPSP queries, integrating findings from two recent works. First, we analyze PathGES, a...

STINER: Automated Extraction of Strategic Cyber Threat Intelligence from X

Strategic Cyber Threat Intelligence CTI focuses on high-level insights, such as identifying targeted industries, attributing attacks to specific ransomware groups, and assessing the scale of data loss. Today, X formerly Twitter has become the fastest source for this intelligence, often hosting...

Operationalizing Cyber Threat Intelligence with GraphRAG

When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules. In practice, most automated attempts at this only extract the simplest clues from the report --- bad IP addresses, domain names, and file hashes --- and turn...

The Ack3 H1 2026 DeFi Incident Dataset: Audit Scope across 135 Security Incidents

Smart-contract audits cover defined artifacts at a specific time, but the label audited is often treated as project-wide assurance. We analyze audit history and incident-path scope across 135 DeFi security incidents using the H1 2026 DeFi Incident Dataset published by cybersecurity company ack3...

ROLoad-PMP: Securing Sensitive Operations for Kernels and Bare-Metal Firmware

A common way for attackers to compromise victim systems is hijacking sensitive operations e.g., control-flow transfers with attacker-controlled inputs. Existing solutions in general only protect parts of these targets and have high performance overheads, which are impractical and hard to deploy o...

Characterizing the Variance Envelope: A Multi-Dimensional Analysis of Spectre Telemetry across Architectures and Workloads

Hardware attacks like Spectre exploit built-in processor vulnerabilities, leaving anomalous footprints in Hardware Performance Counter HPC metrics. While machine learning can detect these footprints in controlled settings, static models fail in the real world when confronted with background syste...

Microsoft Windows ICC File Parsing Remote Code Execution

Microsoft Windows contains a heap-based buffer overflow vulnerability related to the parsing of ICC color profiles that can allow an attacker to execute arbitrary code in the context of the current process. Insufficient validation of attacker-controlled data during ICC profile processing can resu...

Wireshark Analyzer 4.6.8

Wireshark is a GTK+-based network protocol analyzer that lets you capture and interactively browse the contents of network frames. The goal of the project is to create a commercial-quality analyzer for Unix and Win32 and to give Wireshark features that are missing from closed-source sniffers. Thi...

Does Fixing Break Security? an Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-As-Code Repair

Background: Iterative feedback loops are the dominant paradigm for improving LLM-generated Infrastructure-as-Code IaC: validators such as Checkov and terraform validate feed error signals back for successive repair attempts. Prior work reports cumulative-best metrics, which are non-decreasing by...

Sovereign by Necessity? Frontier AI Export Controls, Cyber Security, and the Limits of National AI Capability

A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political will to decide which other countries may use these systems. In June 2026 the United States required a leading developer to...

LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles

Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking, or other control decisions. Static analysis can identify candidate sites, but dynamically confirming exploitability requires executable test...

ATOBench: Tracing How Autonomous Penetration-Testing Agents Verify Vulnerabilities When Target Evidence Lies

Autonomous penetration-testing agents rely on target responses. These responses guide both subsequent actions and the final report. A deceptive response can therefore redirect both the attack trajectory and the agent's verification process. However, final reports reveal little about how an agent...

TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topologies

Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and access-control policies. Existing NetOps automation tools mainly operate after this design is fixed, providing limited suppor...

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

The expanding operational capabilities of large language model LLM agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses...

Vaulted Passkeys: A Device-Bound Proposal for Authenticated Credential Export and Import

Hardware authenticators deliberately resist private-key extraction, yet replacement, disaster recovery, and controlled migration create a legitimate need for portability. Existing guidance for device-bound credentials commonly reduces recovery risk by registering an additional authenticator befor...

Weird Machines in Transport Layer Security

Weird machines are latent computational capabilities that emerge from the composition of architectural components. Prior work has studied this phenomenon extensively in software systems, including x86 instructions, ELF metadata, and page tables, and more recently in cyber-physical systems such as...

Botan C++ Crypto Algorithms Library 3.13.0

Botan is a C++ library of cryptographic algorithms, including AES, DES, SHA-1, RSA, DSA, Diffie-Hellman, and many others. It also supports X.509 certificates and CRLs, and PKCS 10 certificate requests, and has a high level filter/pipe message processing system. The library is easily portable to...