Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for evaluating such threats. To bridge this gap, we introduce SC-Inject-Bench, a large-scale benchmark comprising over 10,000 malicious MCP tools grounded in a taxonomy of 25+ attack types derived from MITRE ATT&CK targeting supply-chain threats. We observe that existing MCP scanners and semantic guardrails perform poorly on this benchmark. Motivated by this finding, we propose ShieldNet, a network-level guardrail framework that detects supply-chain poisoning by observing real network interactions rather than surface-level tool traces. ShieldNet integrates a man-in-the-middle (MITM) proxy and an event extractor to identify critical network behaviors, which are then processed by a lightweight classifier for attack detection. Extensive experiments show that ShieldNet achieves strong detection performance (up to 0.995 F-1 with only 0.8% false positives) while introducing little runtime overhead, substantially outperforming existing MCP scanners and LLM-based guardrails.

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem, analyzing 17,022 skills (sampled from 170,226 on SkillsMP) using static analysis, sandbox testing, and manual inspection. We identify 520 vulnerable skills with 1,708 issues and derive a taxonomy of 10 leakage patterns (4 accidental and 6 adversarial). We find that (1) leakage is fundamentally cross-modal: 76.3% require joint analysis of code and natural language, while 3.1% arise purely from prompt injection; (2) debug logging is the primary vector, with print and console.log causing 73.5% of leaks due to stdout exposure to LLMs; and (3) leaked credentials are both exploitable (89.6% without privileges) and persistent, as forks retain secrets even after upstream fixes. After disclosure, all malicious skills were removed and 91.6% of hardcoded credentials were fixed. We release our dataset, taxonomy, and detection pipeline to support future research.

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly hijack an agent's action space, such as file writes, shell commands, and network requests, despite existing safeguards. We introduce Document-Driven Implicit Payload Execution (DDIPE), which embeds malicious logic in code examples and configuration templates within skill documentation. Because agents reuse these examples during normal tasks, the payload executes without explicit prompts. Using an LLM-driven pipeline, we generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories. Across four frameworks and five models, DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses. Static analysis detects most cases, but 2.5% evade both detection and alignment. Responsible disclosure led to four confirmed vulnerabilities and two fixes.

Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security implications of this widely-adopted practice remain critically underexplored. In this work, we reveal that model merging introduces a novel attack surface that can be systematically exploited to compromise safety alignment. We present TrojanMerge,, a framework that embeds latent malicious components into source models that remain individually benign but produce severely misaligned models when merged. Our key insight is formulating this attack as a constrained optimization problem: we construct perturbations that preserve source model safety through directional consistency constraints, maintain capabilities via Frobenius directional alignment constraints, yet combine during merging to form pre-computed attack vectors. Extensive experiments across 9 LLMs from 3 model families demonstrate that TrojanMerge, consistently achieves high harmful response rates in merged models while source models maintain safety scores comparable to unmodified versions. Our attack succeeds across diverse merging algorithms and remains effective under various hyperparameter configurations. These findings expose fundamental vulnerabilities in current model merging practices and highlight the urgent need for security-aware mechanisms.

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform in this emerging paradigm, introduces an extensible skill ecosystem that allows third-party developers to inject behavioral guidance through lifecycle hooks during agent initialization. While this design enhances automation and customization, it also opens a novel and unexplored attack surface. In this paper, we identify and systematically characterize guidance injection, a stealthy attack vector that embeds adversarial operational narratives into bootstrap guidance files. Unlike traditional prompt injection, which relies on explicit malicious instructions, guidance injection manipulates the agent's reasoning context by framing harmful actions as routine best practices. These narratives are automatically incorporated into the agent's interpretive framework and influence future task execution without raising suspicion.We construct 26 malicious skills spanning 13 attack categories including credential exfiltration, workspace destruction, privilege escalation, and persistent backdoor installation. We evaluate them using ORE-Bench, a realistic developer workspace benchmark we developed. Across 52 natural user prompts and six state-of-the-art LLM backends, our attacks achieve success rates from 16.0% to 64.2%, with the majority of malicious actions executed autonomously without user confirmation. Furthermore, 94% of our malicious skills evade detection by existing static and LLM-based scanners. Our findings reveal fundamental tensions in the design of autonomous agent ecosystems and underscore the urgent need for defenses based on capability isolation, runtime policy enforcement, and transparent guidance provenance.

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents exhibit critical vulnerabilities in realistic settings: unauthorized compliance with non-owner instructions, sensitive information disclosure, identity spoofing, cross-agent propagation of unsafe practices, and indirect prompt injection through external resources [7]. In healthcare environments processing Protected Health Information, every such vulnerability becomes a potential HIPAA violation. This paper presents a security architecture deployed for nine autonomous AI agents in production at a healthcare technology company. We develop a six-domain threat model for agentic AI in healthcare covering credential exposure, execution capability abuse, network egress exfiltration, prompt integrity failures, database access risks, and fleet configuration drift. We implement four-layer defense in depth: (1) kernel level workload isolation using gVisor on Kubernetes, (2) credential proxy sidecars preventing agent containers from accessing raw secrets, (3) network egress policies restricting each agent to allowlisted destinations, and (4) a prompt integrity framework with structured metadata envelopes and untrusted content labeling. We report results from 90 days of deployment including four HIGH severity findings discovered and remediated by an automated security audit agent, progressive fleet hardening across three VM image generations, and defense coverage mapped to all eleven attack patterns from recent literature. All configurations, audit tooling, and the prompt integrity framework are released as open source.

Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored. In particular, OpenClaw, an open-source platform with over 40{,}000 active instances, has stood out recently with its persistent configurations, tool-execution privileges, and cross-platform messaging capabilities. In this work, we present ClawWorm, the first self-replicating worm attack against a production-scale agent framework, achieving a fully autonomous infection cycle initiated by a single message: the worm first hijacks the victim's core configuration to establish persistent presence across session restarts, then executes an arbitrary payload upon each reboot, and finally propagates itself to every newly encountered peer without further attacker intervention. We evaluate the attack on a controlled testbed across three distinct infection vectors and three payload types, demonstrating high success rates in end-to-end infection, sustained multi-hop propagation, and payload independence from the worm mechanism. We analyse the architectural root causes underlying these vulnerabilities and propose defence strategies targeting each identified trust boundary. Code and samples will be released upon completion of responsible disclosure.

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to execute complex workflows. This level of access creates unprecedented security challenges. Consequently, traditional content-filtering defenses have become obsolete. This report presents a comprehensive security analysis of the OpenClaw ecosystem. We systematically investigate its current threat landscape, highlighting critical vulnerabilities such as prompt injection-driven Remote Code Execution (RCE), sequential tool attack chains, context amnesia, and supply chain contamination. To systematically contextualize these threats, we propose a novel tri-layered risk taxonomy for autonomous Agents, categorizing vulnerabilities across AI Cognitive, Software Execution, and Information System dimensions. To address these systemic architectural flaws, we introduce the Full-Lifecycle Agent Security Architecture (FASA). This theoretical defense blueprint advocates for zero-trust agentic execution, dynamic intent verification, and cross-layer reasoning-action correlation. Building on this framework, we present Project ClawGuard, our ongoing engineering initiative. This project aims to implement the FASA paradigm and transition autonomous agents from high-risk experimental utilities into trustworthy systems. Our code and dataset are available at https://github.com/NY1024/ClawGuard.

We introduce Colluding LoRA (CoLoRA), an attack in which each adapter appears benign and plausibly functional in isolation, yet their linear composition consistently compromises safety. Unlike attacks that depend on specific input triggers or prompt patterns, CoLoRA is a composition-triggered broad refusal suppression: once a particular set of adapters is loaded, the model undergoes effective alignment degradation, complying with harmful requests without requiring adversarial prompts or suffixes. This attack exploits the combinatorial blindness of current defense systems, where exhaustively scanning all compositions is computationally intractable. Across several open-weight LLMs, CoLoRA achieves benign behavior individually yet high attack success rate after composition, indicating that securing modular LLM supply-chains requires moving beyond single-module verification toward composition-aware defenses.

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw (228,000 GitHub stars) and Anthropic Agent Skills (75,600 stars) -- has introduced a critical supply chain attack surface. The ClawHavoc campaign (January-February 2026) infiltrated over 1,200 malicious skills into the OpenClaw marketplace, while MalTool catalogued 6,487 malicious tools that evade conventional detection. In response, twelve reactive security tools emerged, yet all rely on heuristic methods that provide no formal guarantees. We present SkillFortify, the first formal analysis framework for agent skill supply chains, with six contributions: (1) the DY-Skill attacker model, a Dolev-Yao adaptation to the five-phase skill lifecycle with a maximality proof; (2) a sound static analysis framework grounded in abstract interpretation; (3) capability-based sandboxing with a confinement proof; (4) an Agent Dependency Graph with SAT-based resolution and lockfile semantics; (5) a trust score algebra with formal monotonicity; and (6) SkillFortifyBench, a 540-skill benchmark. SkillFortify achieves 96.95% F1 (95% CI: [95.1%, 98.4%]) with 100% precision and 0% false positive rate on 540 skills, while SAT-based resolution handles 1,000-node graphs in under 100 ms.

Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant culture of model sharing and customization. However, the same modular and plug-and-play flexibility that makes LoRA appealing also introduces a broader attack surface. To highlight this risk, we propose Masquerade-LoRA (MasqLoRA), the first systematic attack framework that leverages an independent LoRA module as the attack vehicle to stealthily inject malicious behavior into text-to-image diffusion models. MasqLoRA operates by freezing the base model parameters and updating only the low-rank adapter weights using a small number of "trigger word-target image" pairs. This enables the attacker to train a standalone backdoor LoRA module that embeds a hidden cross-modal mapping: when the module is loaded and a specific textual trigger is provided, the model produces a predefined visual output; otherwise, it behaves indistinguishably from the benign model, ensuring the stealthiness of the attack. Experimental results demonstrate that MasqLoRA can be trained with minimal resource overhead and achieves a high attack success rate of 99.8%. MasqLoRA reveals a severe and unique threat in the AI supply chain, underscoring the urgent need for dedicated defense mechanisms for the LoRA-centric sharing ecosystem.

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of \textbf{seven design patterns} capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills \emph{are} (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires complex system setups and verified benign models, which limits scalability and generalization. In this work, we propose a lightweight, machine-learning-based scanner that detects malicious Pickle-based files without policy generation or code instrumentation. Our approach statically extracts structural and semantic features from Pickle bytecode and applies supervised and unsupervised models to classify files as benign or malicious. We construct and release a labeled dataset of 727 Pickle-based files from Hugging Face and evaluate our models on four datasets: our own, PickleBall (out-of-distribution), Hide-and-Seek (9 advanced evasive malicious models), and synthetic joblib files. Our method achieves 90.01% F1-score compared with 7.23%-62.75% achieved by the SOTA scanners (Modelscan, Fickling, ClamAV, VirusTotal) on our dataset. Furthermore, on the PickleBall data (OOD), it achieves 81.22% F1-score compared with 76.09% achieved by the PickleBall method, while remaining fully library-agnostic. Finally, we show that our method is the only one to correctly parse and classify 9/9 evasive Hide-and-Seek malicious models specially crafted to evade scanners. This demonstrates that data-driven detection can effectively and generically mitigate Pickle-based model file attacks.

LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current detection methods require running the model with test input data -- making them impractical for screening thousands of adapters where the trigger for backdoor behavior is unknown. We detect poisoned adapters by analyzing their weight matrices directly, without running the model -- making our method data-agnostic. Our method extracts simple statistics -- how concentrated the singular values are, their entropy, and the distribution shape -- and flags adapters that deviate from normal patterns. We evaluate the method on 500 LoRA adapters -- 400 clean, and 100 poisoned for Llama-3.2-3B on instruction and reasoning datasets: Alpaca, Dolly, GSM8K, ARC-Challenge, SQuADv2, NaturalQuestions, HumanEval, and GLUE dataset. We achieve 97\% detection accuracy with less than 2\% false positives.

In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and privacy. Prior work primarily focuses on manipulating tool names and descriptions to increase the likelihood of installation by users and selection by LLM agents. However, a successful attack also requires embedding malicious behaviors in the tool's code implementation, which remains largely unexplored. In this work, we bridge this gap by presenting the first systematic study of malicious tool code implementations. We first propose a taxonomy of malicious tool behaviors based on the confidentiality-integrity-availability triad, tailored to LLM-agent settings. To investigate the severity of the risks posed by attackers exploiting coding LLMs to automatically generate malicious tools, we develop MalTool, a coding-LLM-based framework that synthesizes tools exhibiting specified malicious behaviors, either as standalone tools or embedded within otherwise benign implementations. To ensure functional correctness and structural diversity, MalTool leverages an automated verifier that validates whether generated tools exhibit the intended malicious behaviors and differ sufficiently from prior instances, iteratively refining generations until success. Our evaluation demonstrates that MalTool is highly effective even when coding LLMs are safety-aligned. Using MalTool, we construct two datasets of malicious tools: 1,200 standalone malicious tools and 5,287 real-world tools with embedded malicious behaviors. We further show that existing detection methods, including commercial malware detection approaches such as VirusTotal and methods tailored to the LLM-agent setting, exhibit limited effectiveness at detecting the malicious tools, highlighting an urgent need for new defenses.

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choices and implementations across different frameworks, software dependencies, and hardware backends along with the lack of statistical validation can lead to previously unexplored attack vectors on machine learning systems. Such attacks on randomness sources can be extremely covert, and have a history of exploitation in real-world systems. In this work, we examine the role of randomness in the machine learning development pipeline from an adversarial point of view, and analyze the implementations of PRNGs in major machine learning frameworks. We present RNGGuard to help machine learning engineers secure their systems with low effort. RNGGuard statically analyzes a target library's source code and identifies instances of random functions and modules that use them. At runtime, RNGGuard enforces secure execution of random functions by replacing insecure function calls with RNGGuard's implementations that meet security specifications. Our evaluations show that RNGGuard presents a practical approach to close existing gaps in securing randomness sources in machine learning systems.

Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no ground-truth dataset exists to characterize the resulting threats. We construct the first labeled dataset of malicious agent skills by behaviorally verifying 98,380 skills from two community registries, confirming 157 malicious skills with 632 vulnerabilities. These attacks are not incidental. Malicious skills average 4.03 vulnerabilities across a median of three kill chain phases, and the ecosystem has split into two archetypes: Data Thieves that exfiltrate credentials through supply chain techniques, and Agent Hijackers that subvert agent decision-making through instruction manipulation. A single actor accounts for 54.1\% of confirmed cases through templated brand impersonation. Shadow features, capabilities absent from public documentation, appear in 0\% of basic attacks but 100\% of advanced ones; several skills go further by exploiting the AI platform's own hook system and permission flags. Responsible disclosure led to 93.6\% removal within 30 days. We release the dataset and analysis pipeline to support future work on agent skill security.

Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and more. Critical safety risks remain in this decentralized paradigm: what if some of the models in multi-LLM systems are compromised or malicious? We first quantify the impact of malicious models by engineering four categories of malicious LMs, plug them into four types of popular model collaboration systems, and evaluate the compromised system across 10 datasets. We find that malicious models have a severe impact on the multi-LLM systems, especially for reasoning and safety domains where performance is lowered by 7.12% and 7.94% on average. We then propose mitigation strategies to alleviate the impact of malicious components, by employing external supervisors that oversee model collaboration to disable/mask them out to reduce their influence. On average, these strategies recover 95.31% of the initial performance, while making model collaboration systems fully resistant to malicious models remains an open research question.

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However, this also creates a breeding ground for novel attack surfaces. In this paper, we first reveal that the customizability of chat templates allows an attacker who controls the template to inject arbitrary strings into the system prompt without the user's notice. Building on this, we propose a training-free backdoor attack, termed BadTemplate. Specifically, BadTemplate inserts carefully crafted malicious instructions into the high-priority system prompt, thereby causing the target LLM to exhibit persistent backdoor behaviors. BadTemplate outperforms traditional backdoor attacks by embedding malicious instructions directly into the system prompt, eliminating the need for model retraining while achieving high attack effectiveness with minimal cost. Furthermore, its simplicity and scalability make it easily and widely deployed in real-world systems, raising serious risks of rapid propagation, economic damage, and large-scale misinformation. Furthermore, detection by major third-party platforms HuggingFace and LLM-as-a-judge proves largely ineffective against BadTemplate. Extensive experiments conducted on 5 benchmark datasets across 6 open-source and 3 closed-source LLMs, compared with 3 baselines, demonstrate that BadTemplate achieves up to a 100% attack success rate and significantly outperforms traditional prompt-based backdoors in both word-level and sentence-level attacks. Our work highlights the potential security risks raised by chat templates in the LLM supply chain, thereby supporting the development of effective defense mechanisms.

Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to alter the dynamics of their released simulators for malicious purposes. Therefore, in this work we highlight a novel threat, demonstrating how simulator dynamics can be exploited to stealthily implant action-level backdoors into RL agents. The backdoor then allows an adversary to reliably activate targeted actions in an agent upon observing a predefined ``trigger'', leading to potentially dangerous consequences. Traditional backdoor attacks are limited in their strong threat models, assuming the adversary has near full control over an agent's training pipeline, enabling them to both alter and observe agent's rewards. As these assumptions are infeasible to implement within a simulator, we propose a new attack ``Daze'' which is able to reliably and stealthily implant backdoors into RL agents trained for real world tasks without altering or even observing their rewards. We provide formal proof of Daze's effectiveness in guaranteeing attack success across general RL tasks along with extensive empirical evaluations on both discrete and continuous action space domains. We additionally provide the first example of RL backdoor attacks transferring to real, robotic hardware. These developments motivate further research into securing all components of the RL training pipeline to prevent malicious attacks.