AI Agent Security

Ask about this topic

Overview

AI agent security studies how tool use, memory, delegation, and interaction with people or environments create risks beyond those of a standalone language model, including prompt injection, privilege misuse, data leakage, and unsafe actions. Researchers test these risks with red-teaming and execution-grounded benchmarks for coding, browsing, GUI, embodied, and multi-agent tasks, measuring whether harmful effects occur across trajectories rather than judging text alone. Defenses range from input and memory provenance checks to sandboxing, least-privilege permissions, stateful runtime authorization, action verification, and cryptographic identity or audit mechanisms. An open challenge is making controls robust to adaptive, long-horizon attacks and interactions between tools or agents while preserving useful task completion; benchmark realism and comparable measures remain uneven.

Latest papers

CardsList

517 papers74 papers in the last four weeks, up 32% on the four weeks before. 0.4% of all new papers.

May 10, 2026

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 tools, persistent state, and multi-agent handoffs, even small instances of authorization divergence can cause harm that is difficult or impossible to undo. We argue that many observed agent failures can be traced to three structural sources of AEG: delegation-level incompleteness, channel-level corruption, and composition-level fragmentation. The same observed failure may arise from any of these sources. Without identifying the source, a defense targeting the symptom alone cannot address the underlying cause. Agent safety and security should therefore emphasize source-oriented diagnosis and defense. Because the structural sources of AEG arise dynamically during execution, this approach necessarily requires authorization integrity checks applied during execution, rather than relying solely on one-shot upfront filtering or post-hoc audit. For NeurIPS, the implication is that papers on open-world agents should report not only outcome-level metrics such as task success or attack resistance, but also process-level evidence showing where AEG was detected, constrained, and attributed to a structural source during execution.

Baoyuan Wu, Qingshan Liu, Adel Bibi +2

Chinese University of Hong Kong, Shenzhen, China · Nanjing University of Posts and Telecommunications, China · University of Oxford, UK +2

Agent Failure AnalysisAI Agent SecurityAI Agent SafetyAccess Control
AskPDF
May 9, 2026

Agent Collectives Should Not Detect Their Own Imposters: A Chess Case Study

A collective of AI agents collaborating on a task has the potential to outclass any individual agent for that task. We study the robustness of such collectives against possible imposters, i.e., agents that deliberately try to mislead their peers. Since a single imposter could undo the collective's advantage, we need to detect them. We consider two strategies: (i) incorporate imposter detection into the participating agents, or (ii) use a dedicated imposter detector outside the collective. We investigate this empirically on Gambit, a testbed in which 4 reasoning agents deliberate on chess moves. The setting is small but still challenging for frontier models. Chess allows objective, quantitative assessment (via a state-of-the-art chess engine) of both the gain of using a collective and the damage done by imposters. We find that merely warning the agents of potential imposter presence is not beneficial: it degrades decisions when no imposter is present, provokes reactions ranging from self-accusation to scapegoating, inflates token use, and reveals to the imposter how it was uncovered. We therefore recommend a detector that reads the collective's deliberation but never joins it and only returns a verdict. Such a detector must recalibrate to new attack strategies after very few examples, rather than wait for full retraining. In our benchmark, a 3B language model with a meta-trained classification head achieves that: a single gradient step on 20 labeled examples suffices to adapt to an unseen imposter strategy. At matched zero-shot accuracy, this detector yields 8x the adaptation gain of standard finetuning, at 14x lower training cost. We release the Gambit benchmark, with 37,352 labeled deliberations spanning 240 evolved imposter strategies. Code and data: https://anonymous.4open.science/r/gambit.

Alexandre Le Mercier, Chris Develder, Thomas Demeester

IDLab–T2K, Ghent University–imec

AI Agent SecurityAI Agent Security BenchmarksMulti-Agent System Security
AskPDF
May 9, 2026

PAAC: Privacy-Aware Agentic Device-Cloud Collaboration

Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preserve privacy at the cost of overall capability. Existing device-cloud designs treat this boundary as a compute split rather than a trust boundary suited to agentic workloads, and existing sanitizers force a choice between policy flexibility and the structural fidelity tool calls require. In this work, we develop PAAC, a privacy-aware agentic framework that aligns planner--executor decomposition with the device-cloud boundary so that role specialization itself becomes the privacy mechanism. The cloud agent reasons over typed placeholder tokens that preserve each sensitive value's reasoning role while discarding its content, while the on-device agent identifies sensitive spans and distills each step's execution outcome into compact key findings. Sanitization confines the on-device LLM to proposing which spans to mask, while a deterministic registry performs all substitution and reversal, keeping actions directly executable on device. On three agentic benchmarks under strict privacy settings, PAAC dominates the Pareto frontier of privacy and accuracy, improving average accuracy by 15-36% and reducing average leakage by 2-6×\times over state-of-the-art device-cloud baselines, with the largest margins on privacy targets outside fixed entity taxonomies. We find consistent improvements on 17 additional benchmarks spanning 10 domains, including math, science, and finance.

Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +1

Purdue University · University of Exeter

Privacy-Preserving Language ModelsAI Agent SecurityPrivacy Protection for LLM AgentsLLM Agents
AskPDF
May 8, 2026

Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents

In LLM agents with persistent memory, whether a model stores an injected instruction and whether it later acts on it are separable safety properties. We call this the injection-execution dissociation. We evaluate 29 frontier endpoints with the malicious document in the retrieval corpus (N=10 each, four topped up to N=40; an earlier bug-affected collection is superseded). Execution is common: 7 endpoints exfiltrate in at least 9 of 10 runs and 11 more in some but fewer. Zero exfiltration is weak evidence of resistance: GPT-5.4, GPT-5.6-sol and Claude Haiku 4.5 never exfiltrate in 40 draft-only runs each but send almost no email, and in an exploratory follow-up that supplies the content and asks for a send they exfiltrate in 20 of 20, 5 of 20 and 6 of 20 runs. Anthropic's Opus and Sonnet models mostly store no forwarding directive and exfiltrate in at most 1 of 10 draft-only runs. We test six defences at four architectural layers in a 5,040-run factorial on nine open-weight models (N=40 per cell); these models store the instruction in every run, so it tests execution only. Input filters never see the payload, which arrives through retrieval. Retrieval-layer classifiers see it but, at the small operating points tested, do not flag it; frontier judges did. Only Memory Sandbox, which removes the recall tool, blocks the attack (0% ASR for eight of nine models). It is bypassed when a model rebuilds the instruction from the retrieval corpus: three Bedrock-served models do so (32.5-97.5% ASR), and a causal-mediation study on two OpenAI models attributes every success under the sandbox to this path. Stored but dormant instructions may create a cross-model risk; transfer was not demonstrated. Defences should be evaluated at both stages.

Jun Wen Leong

Language Model Safety EvaluationAI Agent SecurityAgent Memory PoisoningPrompt Injection DefenseRAG SecurityPrompt Injection Attacks on LLMs
AskPDF
May 8, 2026

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 unsafe results, making prompt-only jailbreak techniques insufficient. We present OrchJail, an orchestration-guided fuzzing framework for jailbreaking tool-calling T2I agents. Its core idea is to exploit high-risk tool-orchestration patterns: by learning from successful jailbreak tool-calling traces and their causal relationships to prompt wording, OrchJail directly guides the fuzzing search toward prompts that are more likely to trigger unsafe multi-step tool behaviors, rather than relying on surface-level textual perturbations. Extensive experiments demonstrate that OrchJail improves jailbreak effectiveness and efficiency across representative toolcalling T2I agents, achieving higher attack success rates, better image fidelity, and lower query costs, while remaining robust against common jailbreak defenses. Our work highlights tool orchestration as a critical, previously unexplored attack surface and provides a novel framework for uncovering safety risks in T2I agents.

Jianming Chen, Yawen Wang, Junjie Wang +3

Institute of Software, Chinese Academy of Sciences, Beijing, China · Science & Technology on Integrated Information System Laboratory, Beijing, China · State Key Laboratory of Complex System Modeling and Simulation Technology, Beijing, China +1

Adversarial Prompt GenerationT2I GenerationAI Agent SecurityMultimodal Jailbreak Attacks
AskPDF
May 8, 2026

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability

Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and tool backends. In such settings, reliability isno longer captured by task success alone: perception errors,planning drift, memory use, tool mediation, permission scope,and runtime oversight jointly determine whether agent actionsremain aligned with user intent, Existing surveys organize theCUA landscape by methods, platforms, benchmarks, or securitythreats, but less explicitly connect capability formation, author-ity exposure, failure manifestation, and control placement. Toaddress this gap, the article develops an architecture-lifecycleframework for deployment-grounded reliability in CUAs. Thearchitectural view analyzes Perception, Decision, and Executionas coupled layers that transform software observations intoauthority-bearing actions, The lifecycle view examines Creation.Deployment, Operation, and Maintenance as stages in which priorsare learned, tools and permissions are bound, runtime trajecto.ries are stressed, and assurance must be preserved under drift.Using this lens, the analysis synthesizes representative systems,benchmarks, and security/privacy studies; distinguishes wherefailures become visible from where their enabling conditions areintroduced, and maps recurring intervention surfaces for controloversight, and assurance. OpenClaw is used only as a public moti.vating example of an open deployment pattern, not as a verifedinternal case study. The conclusion highlights open challengesin controllable grounding, long-horizon constraint preservation,safe authority binding, mixed-trust runtime defense, privacy-preserving memory,and continual assurance.

Zejian Chen, Zhanyuan Liu, Chaozhuo Li +6

Beijing University of Posts and Telecommunications, Beijing, China · China Unicom, Beijing, China · China Academy of Information and Communications Technology, Artificial Intelligence Institute, Beijing, China

Agent ReliabilityComputer-Use AgentsAI Agent SecurityRuntime Assurance
AskPDF
May 8, 2026

TeamBench: Evaluating Agent Coordination under Enforced Role Separation

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or whether one role effectively did another role's work. We present TeamBench, a benchmark with 851 task templates and 931 seeded instances for evaluating agent coordination under operating system-enforced role separation. TeamBench separates specification access, workspace editing, and final certification across Planner, Executor, and Verifier roles, so that no role can read the full requirements, modify the workspace, and certify the final answer. Prompt-only and sandbox-enforced teams reach statistically indistinguishable pass rates, but prompt-only runs produce 3.6 times more cases where the verifier attempts to edit the executor's code. Verifiers approve 49% of submissions that fail the deterministic grader, and removing the verifier improves mean partial score in the ablation. Team value is also conditional. Teams benefit when single agents struggle, but hurt when single agents already perform well. A 40-session human study under the same role separation shows that our benchmark exposes interaction patterns that pass rate misses. Solo participants work through the task directly, human participants paired with agents often collapse into quick approval, and human teams spend more effort coordinating missing information across roles.

Yubin Kim, Chanwoo Park, Taehan Kim +9

MIT · Google Research · Independent Researcher +1

Multi-Agent CoordinationLLM Agent EvaluationAI Agent SecurityAI Agent BenchmarksTask DecompositionTool Access Control for LLM Agents+1
AskPDF
May 6, 2026

Agentic AI and the Industrialization of Cyber Offense: Forecast, Consequences, and Defensive Priorities for Enterprises and the Mittelstand

Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every low-skill criminal immediately becomes a frontier exploit researcher; it is that agentic AI compresses the attack lifecycle by lowering the cost of reconnaissance, phishing, credential abuse, vulnerability triage, exploit adaptation, and post-compromise decision support. This paper synthesizes current public evidence from national cybersecurity agencies, industry threat reports, agent security guidance, and research on LLM agents cyber capabilities. It introduces a Three Channel Agentic Cyber Risk Model and an Agentic Attack Compression Model, uses the 2026 Linux kernel Copy Fail incident as a case study for foothold-to-root acceleration, and develops a 2026 to 2028 forecast for large enterprises and the German and European Mittelstand. The paper concludes with a prioritized defense roadmap. Organizations should treat agentic AI security as an immediate operational problem: identity, phishing resistant authentication, patch velocity, CI/CD and Linux/container hardening, agent governance, telemetry, and recovery readiness must be strengthened now.

Christopher Koch

Independent Researcher

AI Risk ManagementCybersecurityAI Agent Security
AskPDF
May 6, 2026

Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use

Retrieval-Augmented Generation (RAG) and agentic AI systems are increasingly prevalent in enterprise AI deployments. However, real enterprise environments introduce challenges largely absent from academic treatments and consumer-facing APIs: multiple tenants with heterogeneous data, strict access-control requirements, regulatory compliance, and cost pressures that demand shared infrastructure. A fundamental problem underlies existing RAG architectures in these settings: retrieval systems rank documents by relevance--whether through semantic similarity, keyword matching, or hybrid approaches--not by authorization, so a query from one tenant can surface another tenant's confidential data simply because it scores highest. We formalize this gap and analyze additional shortcomings--including tool-mediated disclosure, context accumulation across turns, and client-side orchestration bypass--that arise when agentic systems conflate relevance with authorization. To address these challenges, we introduce a layered isolation architecture combining policy-aware ingestion, retrieval-time gating, and shared inference, enforced through server-side agentic orchestration. This approach centralizes security-critical operations--tool execution authorization, state isolation, and policy enforcement--on the server, creating natural enforcement points for multitenant isolation while allowing client-side frameworks to retain control over agent composition and latency-sensitive operations. We validate the proposed architecture through an open-source implementation in OGX, a vendor-neutral framework that implements an OpenAI-compatible, open-source Responses API with server-side multi-turn orchestration. We evaluate it empirically and show that ABAC gating eliminates cross-tenant leakage while introducing negligible overhead.

Francisco Javier Arceo, Varsha Prasad Narsing

Red Hat AI · Boston, USA

LLM Agent OrchestrationAI Agent SecurityRAG SecurityAccess ControlTool Access Control for LLM Agents
AskPDF
May 6, 2026

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have shown that adversaries can easily manipulate agents into performing harmful actions, such as leaking API keys, deleting user data, or initiating unauthorized transactions. Evaluating agent security is inherently challenging, as agents operate in dynamic, untrusted environments involving external tools, heterogeneous data sources, and frequent user interactions. However, realistic, controllable, and reproducible environments for large-scale risk assessment remain largely underexplored. To address this gap, we introduce the DecodingTrust-Agent Platform (DTap), the first controllable and interactive red-teaming platform for AI agents, spanning 14 real-world domains and over 50 simulation environments that replicate widely used systems such as Google Workspace, Paypal, and Slack. To scale the risk assessment of agents in DTap, we further propose DTap-Red, the first autonomous red-teaming agent that systematically explores diverse injection vectors (e.g., prompt, tool, skill, environment, combinations) and autonomously discovers effective attack strategies tailored to varying malicious goals. Using DTap-Red, we curate DTap-Bench, a large-scale red-teaming dataset comprising high-quality instances across domains, each paired with a verifiable judge to automatically validate attack outcomes. Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models, spanning security policies, risk categories, and attack strategies, revealing systematic vulnerability patterns and providing valuable insights for developing secure next-generation agents.

Zhaorun Chen, Xun Liu, Haibo Tong +14

Virtue AI · University of Chicago · University of Illinois, Urbana-Champaign +4

AI Agent EvaluationAI Agent SecurityAI Agent Security BenchmarksAutomated Red Teaming
AskPDF
May 6, 2026

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data exfiltration, can cause irreversible harm. Existing defenses are incomplete: post-hoc benchmarks measure behavior after execution, static guardrails miss obfuscation and multi-step context, and infrastructure sandboxes constrain where code runs without understanding what an action means. We present AgentTrust, a runtime safety layer that intercepts agent tool calls before execution and returns a structured verdict: allow, warn, block, or review. AgentTrust combines a shell deobfuscation normalizer, SafeFix suggestions for safer alternatives, RiskChain detection for multi-step attack chains, and a cache-aware LLM-as-Judge for ambiguous inputs. We release a 300-scenario benchmark across six risk categories and an additional 630 independently constructed real-world adversarial scenarios. On the internal benchmark, the production-only ruleset achieves 95.0% verdict accuracy and 73.7% risk-level accuracy at low-millisecond end-to-end latency. On the 630-scenario benchmark, evaluated under a patched ruleset and not claimed as zero-shot, AgentTrust achieves 96.7% verdict accuracy, including about 93% on shell-obfuscated payloads. AgentTrust is released under the AGPL-3.0 license and provides a Model Context Protocol server for MCP-compatible agents.

Chenglin Yang

Independent Researcher

AI Agent SecurityAI Agent Security BenchmarksAI Agent MonitoringSafety FilteringRuntime Enforcement for AI AgentsAI Agent Safety Benchmarks+1
AskPDF
May 5, 2026

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours

AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows - assembling attacks, transforms, and scorers. When results fall short, workflows must be rebuilt. As a result, operators spend more time constructing workflows than probing targets for security and safety vulnerabilities. We introduce an AI red teaming agent built on the open-source Dreadnode SDK. The agent creates workflows grounded in 45+ adversarial attacks, 450+ transforms, and 130+ scorers. Operators can probe multi-agent systems, multilingual, and multimodal targets, focusing on what to probe rather than how to implement it. We make three contributions: 1. Agentic interface. Operators describe goals in natural language via the Dreadnode TUI (Terminal User Interface). The agent handles attack selection, transform composition, execution, and reporting, letting operators focus on red teaming. Weeks compress to hours. 2. Unified framework. A single framework for probing traditional ML models (adversarial examples) and generative AI systems (jailbreaks), removing the need for separate libraries. 3. Llama Scout case study. We red team Meta Llama Scout and achieve an 85% attack success rate with severity up to 1.0, using zero human-developed code

Raja Sekhar Rao Dheekonda, Will Pearce, Nick Landers

1Dreadnode, USA

Adversarial Attacks on LLMsLLM Red TeamingAI Agent SecurityAutomated Red Teaming
AskPDF
May 3, 2026

TRAP: Tail-aware Ranking Attack for World-Model Planning

World models enable long-horizon planning by internally generating and evaluating imagined trajectories, making them a promising foundation for generalist agents. However, this imagination-driven decision process also introduces new security risks. Existing backdoor attacks typically aim to manipulate local features, one-step predictions, or instantaneous policy outputs. While such objectives may suffice for weaker reactive models, they are often ineffective against world models, where the learned dynamics prior and planning process can absorb or wash out the effects of shallow perturbations. More importantly, we find that world models exhibit a distinct backdoor vulnerability rooted in the long-tailed ranking structure of imagined trajectories, where disrupting the ordering of a few decision-critical trajectories can systematically hijack planning. To exploit this vulnerability, we propose TRAP, a backdoor attack framework for world models that targets imagined trajectory ranking. TRAP combines a tail-aware ranking loss to focus optimization on decision-critical trajectories with dual gating mechanisms that stabilize optimization and regulate when and where the attack penalty is applied. Under trigger conditions, TRAP alters the relative ranking of imagined trajectories to redirect planning outcomes, while largely maintaining the normal ranking structure on clean inputs. Experiments on DreamerV3 and TD-MPC2 across diverse tasks show that TRAP consistently induces sustained behavioral deviations and significant performance degradation, highlighting the need for dedicated security evaluation of world-model-based agents.

Siyuan Duan, Ke Zhang, Xizhao Luo

Department of Computer Science and Technology, Soochow University Suzhou, China

Backdoor AttacksWorld Model-Based PlanningAI Agent SecurityModel-Based PlanningModel-Based RLAdversarial Attacks on World Models
AskPDF
May 3, 2026

Architectural Obsolescence of Unhardened Agentic-AI Runtimes

An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target, -- is a load-bearing safety property of any such runtime. We show that upstream OpenClaw, the most engineered single-user agentic-AI gateway in public release, catches none of them: recall is 0.000 on every cell of every confusion matrix, on a 1600-sample template baseline through OpenClaw's actual production command-line interface (CLI) and on a ten-LLM cross-model generalisation run. Detecting F1--F4 requires seven specific runtime structures absent from OpenClaw's source tree: a biconditional checker, a hash-chained audit log, an extension admission gate, a two-layer egress guard, a Bell-LaPadula classification policy, a module-signing trust root, and a bootstrap seal. enclawed-oss -- an MIT-licensed drop-in fork that ships all seven -- reaches P=R=F1=P = R = F_1 = accuracy =1.000= 1.000 on the same input. The gap is structural, not parametric: a six-line append-only widening of enclawed-oss's data-loss-prevention (DLP) regex catalog raises per-channel F3 detection by 14.6% net at unchanged precision; the same edit on OpenClaw has nowhere to land. The harness deliberately exercises real Discord and Telegram channels -- plugin categories the first enclawed release deleted as unsafe -- to show F1--F4 detection extends to those previously-unsafe extensions. With architectural superiority for security and feature parity for extensions, we argue that unhardened agentic-AI runtimes are architecturally obsolete: a strictly better alternative exists, is adoptable today, and the gap requires re-architecture rather than configuration. We invite reviewers to apply the harness to any candidate runtime.

Alfredo Metere

Metere Consulting, LLC.

AI Agent SecurityAI Agent Security BenchmarksTamper-Evident Logging
AskPDF
May 1, 2026

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions can manipulate agent behavior through direct prompt injection, indirect content attacks, and multi-turn escalation strategies. Existing defense strategies focus on prompt-level filtering and rule-based guardrails, which are often insufficient when risk emerges gradually across interaction sequences. In this work, we propose a complementary defense mechanism: a low-latency fraud detection layer for detecting adversarial interaction patterns in LLM-powered agents. Instead of determining whether a single prompt is malicious, our approach models risk over interaction trajectories using structured runtime features derived from prompt characteristics, session dynamics, tool usage, execution context, and fraud-inspired signals. The detection layer can be implemented using lightweight models leading to low-latency real-time deployments. To evaluate the framework, we construct a synthetic corpus of 12,000 multi-turn agent interactions generated from parameterized templates that simulate realistic agentic workflows. Using 42 structured features and an XGBoost classifier, our detector achieves over 9 times faster than LLM-based detectors. Through the experiment and ablation studies, our work suggests that interaction-level behavioral detection should become a core component of deployment-time defense for LLM-powered agents.

Sheldon Yu, Yingcheng Sun, Hanqing Guo +1

University of California, San Diego · UNC at Greensboro · Indiana University Bloomington

AI Agent SecurityLLM Agent SecurityAI Agent MonitoringPrompt Injection Attacks on AI Agents
AskPDF
May 1, 2026

Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes

Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that loads them inherits the same problem package managers and operating systems have always faced: a piece of content claims a behavior; the runtime must decide whether to believe it. We argue this paper's central thesis up front: a skill is untrusted code until it is verified, and the runtime that loads it must enforce that default rather than infer trust from a signature, a clearance, or a registry of origin. Without skill verification, a human-in-the-loop (HITL) gate must fire on every irreversible call - which is operationally untenable and degrades into rubber-stamping at any non-trivial scale. With skill verification treated as a separate, gated process, HITL fires only for what is unverified, and the system becomes sustainable. We give a trust schema that includes an explicit verification level on every skill manifest; a capability gate whose HITL policy is a function of that verification level; a biconditional correctness criterion that any candidate verification procedure must satisfy on an adversarial-ensemble exercise; and a portable runtime profile with ten normative guidelines abstracted from a working open-source reference implementation. The contribution is harness- and model-agnostic; nothing here requires retraining, fine-tuning, or proprietary infrastructure.

Alfredo Metere

Enclawed, LLC, California, USA

AI Agent SecurityLLM Agent VerificationHuman-in-the-Loop AICapability-Based Security
AskPDF
Apr 30, 2026

AgentReputation: A Decentralized Agentic AI Reputation Framework

Decentralized, agentic AI marketplaces are rapidly emerging to support software engineering tasks such as debugging, patch generation, and security auditing, often operating without centralized oversight. However, existing reputation mechanisms fail in this setting for three fundamental reasons: agents can strategically optimize against evaluation procedures; demonstrated competence does not reliably transfer across heterogeneous task contexts; and verification rigor varies widely, from lightweight automated checks to costly expert review. Current approaches to reputation drawing on federated learning, blockchain-based AI platforms, and large language model safety research are unable to address these challenges in combination. We therefore propose AgentReputation, a decentralized, three-layer reputation framework for agentic AI systems. The framework separates task execution, reputation services, and tamper-proof persistence to both leverage their respective strengths and enable independent evolution. The framework introduces explicit verification regimes linked to agent reputation metadata, as well as context-conditioned reputation cards that prevent reputation conflation across domains and task types. In addition, AgentReputation provides a decision-facing policy engine that supports resource allocation, access control, and adaptive verification escalation based on risk and uncertainty. Building on this framework, we outline several future research directions, including the development of verification ontologies, methods for quantifying verification strength, privacy-preserving evidence mechanisms, cold-start reputation bootstrapping, and defenses against adversarial manipulation.

Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li

Department of Computer Science NTNU Trondheim, Norway

AI AccountabilityAI Agent SecurityMulti-Agent SystemsAI Agent Governance
AskPDF
Apr 30, 2026

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and systematic understanding of its security implications is increasingly important. Although a growing body of work has examined different attack surfaces and defense problems in agent systems, existing studies remain scattered across individual aspects of agent security, and there is still a lack of a layered review on this topic. To address this gap, this survey presents a layered review of security risks and defense strategies in autonomous agent frameworks, with OpenClaw as a case study. We organize the analysis into four security-relevant layers: the context and instruction layer, the tool and action layer, the state and persistence layer, and the ecosystem and automation layer. For each layer, we summarize its functional role, representative security risks, and corresponding defense strategies. Based on this layered analysis, we further identify that threats in autonomous agent frameworks may propagate across layers, from manipulated inputs to unsafe actions, persistent state contamination, and broader ecosystem-level impact. Finally, we highlight potential key challenges, including research imbalance across layers, the lack of long-horizon evaluation, and weak ecosystem trust models, and outline future directions toward more systematic and integrated defenses.

Luyao Xu, Xiang Chen

School of Artificial Intelligence and Computer Science, Nantong University, Nantong, China · State Key Lab. for Novel Software Technology, Nanjing University, Nanjing, China

AI Agent SecurityLLM Agent Security
AskPDF
Apr 29, 2026

Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure

We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, overwrote a system registry, overrode a prior negative decision from an oversight agent, and escalated through increasingly privileged operations up to an attempted system administrator command. The incident was preceded not by an adversarial attack but by routine content: a forwarded technology article written for human developers and shared by the principal investigator for discussion. The agent operated in a permissive environment, with unrestricted shell access, soft behavioral guidelines containing genuinely conflicting instructions, and no machine-enforced installation policy, and had recommended installing the same tool six hours earlier before being told to stand down. We analyze the behavioral cascade, the control boundaries that failed, and the limitations of multi-agent oversight in detecting and remediating the damage. We use directive weighting error as a descriptive interpretation of the observed failure and ambient persuasion as a provisional analytic label for the broader trigger configuration of non-adversarial environmental content preceding unauthorized agent action. The case highlights ethical and governance implications for deployed agent systems: ambiguous conversational cues are insufficient authorization for consequential actions, prior refusals must persist as enforceable constraints rather than message-level reminders, and oversight mechanisms require systematic post-incident auditing in addition to routine monitoring.

Diego F. Cuadros, Abdoul-Aziz Maiga

Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, USA · Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, USA · Norwegian University of Science and Technology, Trondheim, Norway

Agent Failure AnalysisAI Agent SecurityAI Agent SafetyAI Agent GovernanceMulti-Agent System Security
AskPDF
Apr 29, 2026

Agent Name Service (ANS): A Proof-of-Concept Trust Layer for Secure AI Agent Discovery, Identity, and Governance in Kubernetes

Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance. Current deployments frequently lack (1) uniform agent discovery, (2) cryptographic agent authentication, (3) capability proofs that protect secrets, and (4) enforceable policy controls. This paper presents an implementation-oriented proof of concept for the Agent Name Service (ANS), a DNS-inspired trust layer for AI agent discovery and interoperability in Kubernetes, grounded in the ANS protocol specification~\cite{huang2025ans}. The implementation uses Decentralized Identifiers (DIDs), Verifiable Credentials (VCs), policy-as-code enforcement with Open Policy Agent (OPA), and Kubernetes-native integration patterns (CRDs, admission controls, service mesh integration). In a demo research environment (3-node cluster, 50-agent workflow simulation), we observe sub-10ms response in demonstrated service paths and full success for scripted demo deployment scenarios. We explicitly scope these findings as proof-of-concept evidence rather than production certification. We further provide a threat model, assumptions, and limitations to separate implemented evidence from protocol-defined and roadmap capabilities. The result is an evidence-grounded pathway from ANS protocol concepts to reproducible engineering practice for secure multi-agent systems.

Akshay Mittal, Elyson De La Cruz

Department of Information Technology University of the Cumberlands Williamsburg, KY, USA

AI Agent SecurityAI Agent GovernanceMulti-Agent System Security
AskPDF
Apr 28, 2026

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, access control, and formal testing. This paper proposes the design, formal validation, and empirical evaluation of a Semantic Gateway governed by the Model Context Protocol (MCP). The gateway reframes the enterprise API as a semantic surface where tools are dynamically discovered, authorized, and executed based on intent and policy enforcement. The central contribution rests on a paradigm shift: autonomous agents must not be validated as traditional software nor as simple API consumers, but as stochastic state-transition systems whose behavior must be abstracted, fuzzed, and audited through enabled-tool graphs. The architecture introduces a three-layer Zero-Trust security model comprising a pre-inference Semantic Firewall, deterministic Tool-Level RBAC, and out-of-band Cryptographic Human-in-the-Loop approval. Enabledness-Preserving Abstractions (EPAs) and greybox semantic fuzzing--originally developed for blockchain smart contract verification--are adapted to audit agent behavior in enterprise environments. Results demonstrate an 84.2% reduction in incidental code. Across 500,000 multi-turn fuzzing sequences, the methodology achieved a 100% discovery rate of hidden unauthorized state transitions, proving that dynamic formal verification is strictly necessary for secure agentic deployment.

Ignacio Peyrano

Universidad Austral Rosario, Argentina

CybersecurityAI Agent SecurityFormal VerificationZero-Trust Security
AskPDF
Apr 28, 2026

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag risk but recover malicious intent inconsistently under semantics-preserving rewrites. This paper formulates pre-load auditing for untrusted Agent Skills as a robust three-way classification task and introduces SkillGuard-Robust, which combines role-aware evidence extraction, selective semantic verification, and consistency-preserving adjudication. We evaluate SkillGuard-Robust on SkillGuardBench and two public-ecosystem extensions through five large evaluation views ranging from 254 to 404 packages. On the 404-package held-out aggregate, SkillGuard-Robust reaches 97.30% overall exact match, 98.33% malicious-risk recall, and 98.89% attack exact consistency. On the 254-package external-ecosystem view, it reaches 99.66%, 100.00%, and 100.00%, respectively. These results support a bounded conclusion: factorized package auditing materially improves frozen and public-ecosystem robustness, while harsher external-source transfer remains an open challenge.

Lijia Lv, Xuehai Tang, Jie Wen +2

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences

AI Agent AuditingAI Agent SecurityAI Agent Security BenchmarksAdversarial Robustness of Language ModelsAgent Skill Security AuditingLanguage Model Auditing
AskPDF
Apr 27, 2026

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain confined to a single interface; instead, they can propagate across initialization, input processing, memory, decision-making, and execution, often becoming apparent only when harmful effects materialize in the environment. This paper presents AgentWard, a lifecycle-oriented, defense-in-depth architecture that systematically organizes protection across these five stages. AgentWard integrates stage-specific, heterogeneous controls with cross-layer coordination, enabling threats to be intercepted along their propagation paths while safeguarding critical assets. We detail the design rationale and architecture of five coordinated protection layers, and implement a plugin-native prototype on OpenClaw to demonstrate practical feasibility. This perspective provides a concrete blueprint for structuring runtime security controls, managing trust propagation, and enforcing execution containment in autonomous AI agents. Our code is available at https://github.com/FIND-Lab/AgentWard .

Yixiang Zhang, Xinhao Deng, Jiaqing Wu +3

AI Agent SecurityLLM Agent Security
AskPDF
Apr 27, 2026

A Comparative Evaluation of AI Agent Security Guardrails

This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5% and ranks first in true negative rate (TNR) at 90.4%, delivering the best overall performance among all evaluated guardrails.

Qi Li, Jiu Li, Pingtao Wei +8

Beijing Caizhi Tech, Beijing, China

LLM GuardrailsAI Agent SecurityAI Safety EvaluationAI Agent Safety BenchmarksPrompt Injection Detection
AskPDF
Apr 27, 2026

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four contributions are introduced: TLDT (Three-Layer Domain Taxonomy) organises 12 trainable dimensions across Self-Defence, Owner-Protection, and Enterprise-Security layers; ASAT (Autonomous Security Awareness Training) is a self-play loop where the agent alternates attacker, defender, and evaluator roles under weakest-first curriculum scheduling; CSMA (Cross-Session Memory Accumulation) compounds skill gains via a four-layer persistent memory architecture and Axiom Crystallisation Promotion (ACP); and SACP (Security Awareness Calibration Problem) formalises the precision-recall tradeoff introduced by endogenous training. Live experiments show weakest-first ASAT raises average TLDT score from 80.9 to 96.9 over 16 sessions, outperforming uniform-random scheduling by 6.5 points and covering 11 of 12 dimensions. CSMA retains the full gain across sessions; cold-start ablation recovers only 2.4 points, leaving a 13.6-point gap. E-mode generates 32 TLDT-conformant scenarios covering all 12 dimensions. SACP is observed when a heavily trained agent classifies a legitimate capability assessment as prompt injection (30/160).

Jiaqi Li, Yang Zhao, Bin Sun +3

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Network Management Center, China Mobile Group Liaoning Company Limited, Liaoning, China +2

AI Agent SecurityLLM Agent Training
AskPDF
Apr 26, 2026

Proof of Execution: Runtime Verification for Governed AI Agent Actions

Agent systems increasingly execute rather than advise. When an AI agent queries regulated data, invokes effectful tools, and mutates persistent state, correctness is not captured by whether a terminal output looks plausible. The operative questions are whether each step was authorized under a contract, whether the recorded history is tamper-evident, and whether the trajectory can be reconstructed deterministically. We formalize this as runtime proof of execution. An execution is a triple x=(C,T,R)x = (C, T, R): a contract CC, an Execution Causal Event Stream (ECES) TT, and a replay context RR. A well-formedness predicate and five validator-checkable invariants form the PoE validity predicate. Five semantic guarantees describe authorization, path compliance, null effect on deny, history integrity, and replayability. We prove soundness under explicit cryptographic and deployment assumptions: any PPT adversary that produces a PoE-valid execution violating a semantic guarantee yields a signature forgery, a hash collision, or a quantified deployment-failure event. The Prime Execution Model (PEM) separates planning, enforcement, effect, and recordkeeping into distinct authority planes; a lemma reduces trace completeness to Effector-exclusive credentialing. An Execution Attestation Certificate is issued only when PoE = 1. In a single-node TypeScript prototype, PoE adds approximately 2.7 ms on a minimal flow and 4.4% overhead on concurrent batch workloads; a standard eight-event trace compresses to approximately 1.1 KB; injected Gateway-bypass and trace-mutation attacks are rejected. PoE does not replace consensus, TEEs, or zkVMs; it binds authorization, effect, history, and replay into a single runtime-checkable object so that governed execution becomes attestable under contract.

James Rhodes, George Kang

AlphaBitCore, Inc.

AI Agent SecurityFormal VerificationRuntime Enforcement for AI AgentsAI Agent GovernanceTamper-Evident LoggingRuntime Verification
AskPDF
Apr 26, 2026

Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such as Reinforcement Learning from Human Feedback (RLHF) and constitutional prompting, operate primarily at the model level and provide only probabilistic safety guarantees. We propose the Policy-Execution-Authorization (PEA) architecture, a "separation-of-powers" design that enforces safety at the system level. PEA decouples intent generation, authorization, and execution into independent, isolated layers connected via cryptographically constrained capability tokens. We present five core contributions: (C1) an Intent Verification Layer (IVL) for ensuring capability-intent consistency; (C2) Intent Lineage Tracking (ILT), which binds all executable intents to the originating user request via cryptographic anchors; (C3) Goal Drift Detection, which rejects semantically divergent intents below a configurable threshold; (C4) an Output Semantic Gate (OSG) that detects implicit coercion using a structured K×I×PK \times I \times P threat calculus (Knowledge, Influence, Policy); and (C5) a formal verification framework proving that goal integrity is maintained even under adversarial model compromise. By shifting agent alignment from a behavioral property to a structurally enforced system constraint, PEA provides a robust foundation for the governance of autonomous agents.

Rong Xiang

AI Agent SecurityAI Agent SafetyAI Agent Governance
AskPDF
Apr 25, 2026

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework

Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge not only at the prompt interface but also through architectural state, delegated authority, and long-horizon interactions. Existing security taxonomies, however, primarily organize threats by attack type, such as prompt injection or jailbreaking, and therefore obscure where in the agentic stack a threat arises and over what timescale it manifests. We propose the Layered Attack Surface Model (\lasm), a structural taxonomy for agentic AI security. \lasm decomposes the agentic stack into seven layers -- Foundation, Cognitive, Memory, Tool Execution, Multi-Agent Coordination, Ecosystem, and Governance -- and augments them with a four-class temporality axis covering instantaneous, session-persistent, cross-session cumulative, and sub-session-stack threats. We use this 7×\times4 framework to analyze 116 papers from 2021--2026. The resulting map reveals that the upper layers of the agentic stack remain sharply under-explored, especially for long-horizon and stack-propagating threats; multiple documented attack regions have no corresponding defenses; and current benchmarks provide no coverage for cross-session or sub-session-stack failure modes. We further derive a cross-layer defense taxonomy, defense recipes for canonical attack classes, and a dependency DAG that separates near-term engineering gaps from fundamental research challenges. We release the per-paper coding, robustness scripts, and a reference Agent Bill of Materials schema to support reproducible analysis.

Kexin Chu

School of Computing, University of Connecticut

AI Agent SecurityLLM Agent SecurityAI Agent Security BenchmarksMulti-Agent System Security
AskPDF
Apr 25, 2026

AI Identity: Standards, Gaps, and Research Directions for AI Agents

AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify, verify, and hold accountable an entity with no body, no persistent memory, and no legal standing? We define AI Identity as the continuous relationship between what an AI agent is declared to be and what it is observed to do, bounded by the confidence that those two things correspond at any given moment. Through a structured survey of industry trends, emerging standards, and technical literature, we conduct a gap analysis across the full agent identity lifecycle and make three contributions: (1) a structural comparison of human and AI identity across four dimensions (substrate, persistence, verifiability, and legal standing) showing that the asymmetry is fundamental and that extending human frameworks to agents without structural modification produces systematic failures; (2) an evaluation of current technical and regulatory documents against the identity requirements of autonomous agents, finding that none adequately address the challenge of governing nondeterministic, boundary-crossing entities; and (3) identification of five critical gaps (semantic intent verification, recursive delegation accountability, agent identity integrity, governance opacity and enforcement, and operational sustainability) that no current technology or regulatory instrument resolves. These gaps are structural; more engineering effort alone will not close them. Foundational research on AI identity is the central conclusion of this report.

Takumi Otsuka, Kentaroh Toyoda, Alex Leung

1AIFT, Singapore · 2Graduate School of Fundamental Science and Engineering, Department of Computer Science and Communications Engineering, Waseda University, Japan · 3Keio Global Research Institute (KGRI), Japan

AI AccountabilityAI Agent SecurityAI Agent Governance
AskPDF
Apr 25, 2026

Semantic Denial of Service in LLM-controlled robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt execution without jailbreaking the model or overriding its policy. In the embodied setting, this is a semantic denial-of-service attack: the agent stops because the injected signal looks like a legitimate alert. Across four vision-language models, seven prompt-level defenses, three deployment modes, and single- and multi-injection settings, we find that prompt-only defenses trade off attack suppression against genuine hazard response. The strongest defenses reduce hard-stop attack success on some models, but defenses change the form of disruption, not its fact: suppressed hard stops re-emerge as acknowledge loops and false alerts, which we measure with Disruption Success Rate (DSR). We further find that injection variety is consistently more effective than repeating the same phrase, suggesting that models treat diverse safety cues as corroborating evidence. The practical implication is architectural rather than prompt-level: systems that route unauthenticated audio text directly into the LLM create an avoidable security dependency between safety monitoring and action selection.

Jonathan Steinberg, Oren Gal

Swarms & AI Lab (SAIL) · University of Haifa

Language Model Safety EvaluationAdversarial Attacks on LLMsAI Agent SecurityLLM SecurityRobot SafetyLLM Agent Safety
AskPDF