AI Agent Security

Follow this topic Ask about this topic

Momentum

43 papers in the last four weeks, up 258% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 311

Apr 27, 2026cs.CR

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 Guardrails AI Agent Security AI Safety Evaluation AI Agent Safety Benchmarks Prompt Injection Detection

Apr 27, 2026cs.CR

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 Security LLM Agent Training

Apr 26, 2026cs.CR

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)

: a contract

C

, an Execution Causal Event Stream (ECES)

T

, and a replay context

R

. 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 Security Formal Verification Runtime Enforcement for AI Agents AI Agent Governance Tamper-Evident Logging Runtime Verification

Apr 26, 2026cs.AI

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 \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 Security AI Agent Safety AI Agent Governance

Apr 25, 2026cs.CR

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

\times

4 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 Security LLM Agent Security AI Agent Security Benchmarks Multi-Agent System Security

Apr 25, 2026cs.AI

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 Accountability AI Agent Security AI Agent Governance

Apr 25, 2026cs.CR

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 Evaluation Adversarial Attacks on LLMs AI Agent Security LLM Security Robot Safety LLM Agent Safety

Apr 25, 2026cs.CR

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR (Augmented Reality) glass to capture the image and vocal information of the target, using the LLM to identify the target and generate the social profile, using the LLM agents to apply social engineering strategies for conversation suggestion to win the target trust and perform phishing afterwards. Current defensive approaches, such as role-based access control or data flow tracking, are not directly applicable to the convergent AR-LLM ecosystem (considering embedded AR device and opaque LLM inference), leaving an emerging and potent social engineering threat that existing privacy paradigms are ill-equipped to address. This necessitates a shift beyond solely human-centric measures like legislation and user education toward enforceable vendor policies and platform-level restrictions. Realizing this vision, however, faces significant technical challenges: securing resource-constrained AR-embedded devices, implementing fine-grained access control within opaque LLM inferences, and governing adaptive interactive agents. To address these challenges, we present UNSEEN, a coordinated cross-stack defense that combines an AR ACL (Access Control Layer) for identity-gated sensing, F-RMU-based LLM unlearning for sensitive profile suppression, and runtime agent guardrails for adaptive interaction control. We evaluate UNSEEN in an IRB-approved user study with 60 participants and a dataset of 360 annotated conversations across realistic social scenarios.

Tianlong Yu, Yang Yang, Xiao Luo +6

Hubei University, Wuhan, China · University of Southern California, Los Angeles, USA · Huazhong University of Science and Technology, Wuhan, China

Privacy-Preserving Language Models LLM Guardrails Cybersecurity AI Agent Security

Apr 24, 2026cs.AI

Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work defined Reconstructive Authority (RAM) as a condition for valid execution: actions are permitted only if authority can be constructed from current state. This paper addresses enforcement at runtime: how to enforce this condition in a running system. We introduce a runtime execution model in which authority is evaluated at action time and execution is conditioned on its constructibility. This extends the execution state space beyond admit/deny with a third state, halt, representing cases where authority is undefined due to incomplete or uncertain observability. We define a concrete execution protocol including dynamic dependency resolution, authority reconstruction, and explicit decision semantics. We further introduce a Recovery Loop that integrates drift detection (IML) with execution control (ACP), allowing the system to suspend execution, acquire missing information, and re-attempt authority reconstruction. We show that this model guarantees safety -- no action is executed without constructible authority -- and conditional liveness: execution resumes when authority-defining variables become observable. This work operationalizes reconstructive authority as a runtime enforcement mechanism, providing the execution semantics required to apply RAM in real systems.

Marcelo Fernandez - TraslaIA

TraslaIA

AI Agent Security AI Agent Safety Runtime Verification

Apr 22, 2026cs.CR

Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make three contributions to cross-session threat detection. (1) Dataset. CSTM-Bench is 26 executable attack taxonomies classified by kill-chain stage and cross-session operation (accumulate, compose, launder, inject_on_reader), each bound to one of seven identity anchors that ground-truth "violation" as a policy predicate, plus matched Benign-pristine and Benign-hard confounders. Released on Hugging Face as intrinsec-ai/cstm-bench with two 54-scenario splits: dilution (compositional) and cross_session (12 isolation-invisible scenarios produced by a closed-loop rewriter that softens surface phrasing while preserving cross-session artefacts). (2) Measurement. Framing cross-session detection as an information bottleneck to a downstream correlator LLM, we find that a session-bound judge and a Full-Log Correlator concatenating every prompt into one long-context call both lose roughly half their attack recall moving from dilution to cross_session, well inside any frontier context window. Scope: 54 scenarios per shard, one correlator family (Anthropic Claude), no prompt optimisation; we release it to motivate larger, multi-provider datasets. (3) Algorithm and metric. A bounded-memory Coreset Memory Reader retaining highest-signal fragments at

K=50

is the only reader whose recall survives both shards. Because ranker reshuffles break KV-cache prefix reuse, we promote

\mathrm{CSR\_prefix}

(ordered prefix stability, LLM-free) to a first-class metric and fuse it with detection into

\mathrm{CSTM} = 0.7 F_1(\mathrm{CSDA@action}, \mathrm{precision}) + 0.3 \mathrm{CSR\_prefix}

, benchmarking rankers on a single Pareto of recall versus serving stability.

Ari Azarafrooz

Intrinsec AI

Cybersecurity AI Agent Security AI Agent Security Benchmarks Memory-Augmented Language Model Agents

Apr 22, 2026cs.CR

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks have been extensively explored to showcase the vulnerabilities of LLMs to user prompt manipulation. The expanded capabilities of agentic models introduce further vulnerabilities via their function calling interface. Recent work in LLM security showed that function calling can be abused, leading to data tampering and theft, causing disruptive behavior such as endless loops, or causing LLMs to produce harmful content in the style of jailbreaking attacks. This paper introduces a novel function hijacking attack (FHA) that manipulates the tool selection process of agentic models to force the invocation of an attacker-chosen function. While existing attacks focus on semantic preference of the model for function-calling tasks, we show that FHA is largely agnostic to the context semantics and remains effective across domains and function sets. We demonstrate that FHA generalizes to unseen queries and payload perturbations under a fixed target model, reaching 62.5% to 81.9% ASR on held-out queries across 4 function-calling LLMs (instructed and reasoning models), evaluated on the Berkeley Function Calling Leaderboard (BFCL). We further evaluate the cross-model transferability of FHA, showing that FHA can be transferred to other model sizes and families (11.2-27.6% ASR). Our findings further demonstrate the need for strong guardrails and modules for agentic systems.

Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis +2

IBM Research Europe · Trinity College Dublin · Imperial College London +1

Adversarial Attacks on LLMs AI Agent Security

Apr 22, 2026cs.CR

AgentSOC: A Multi-Layer Agentic AI Framework for Security Operations Automation

Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a multi-layered agentic AI framework that enhances SOC automation by integrating perception, anticipatory reasoning, and risk-based action planning. The proposed architecture consolidates several layers of abstraction to provide a single operational loop to support normalizing alerts, enriching context, generating hypotheses, validating structural feasibility, and executing policy-compliant responses. Conceptually evaluated within a large enterprise environment, AgentSOC improves triage consistency, anticipates attackers' intentions, and provides recommended containment options that are both operationally feasible and well-balanced between security efficacy and operational impact. The results suggest that hybrid agentic reasoning has the potential to serve as a foundation for developing adaptive, safer SOC automation in large enterprises. Additionally, a minimal Proof-Of-Concept (POC) demonstration using LANL authentication data demonstrated the feasibility of the proposed architecture.

Joyjit Roy, Samaresh Kumar Singh

Austin, Texas, USA · Leander, Texas, USA

Autonomous Cyber Defense Cybersecurity AI Agent Security AI Agent Safety

Apr 21, 2026cs.CR

An AI Agent Execution Environment to Safeguard User Data

AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy. Adversaries may attack the AI model (e.g., via prompt injection) to exfiltrate user data. Furthermore, sharing private data with an AI agent requires users to trust a potentially unscrupulous or compromised AI model provider with their private data. This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that guarantees confidentiality for private user data. Through dynamic and directed user prompts, GAAP collects permission specifications from users describing how their private data may be shared, and GAAP enforces that the agent's disclosures of private user data, including disclosures to the AI model and its provider, comply with these specifications. Crucially, GAAP provides this guarantee deterministically, without trusting the agent with private user data, and without requiring any AI model or the user prompt to be free of attacks. GAAP enforces the user's permission specification by tracking how the AI agent accesses and uses private user data. It augments Information Flow Control with novel persistent data stores and annotations that enable it to track the flow of private information both across execution steps within a single task, and also over multiple tasks separated in time. Our evaluation confirms that GAAP blocks all data disclosure attacks, including those that make other state-of-the-art systems disclose private user data to untrusted parties, without a significant impact on agent utility.

Robert Stanley, Avi Verma, Lillian Tsai +2

University of California, Los Angeles · Google

AI Agent Security Privacy Leakage in Language Models Information Flow Control Access Control

Apr 21, 2026cs.CV

If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality creates a fundamental challenge: agents must respond to legitimate environmental cues while remaining robust to misleading ones. We refer to this tension as trust boundary confusion. To study this behavior, we design a dual-intent dataset and evaluation framework, through which we show that current LVLM-based agents fail to reliably balance this trade-off, either ignoring useful signals or following harmful ones. We systematically evaluate 7 LVLM agents across multiple embodied settings under both structure-based and noise-based visual injections. To address these vulnerabilities, we propose a multi-agent defense framework that separates perception from decision-making to dynamically assess the reliability of visual inputs. Our approach significantly reduces misleading behaviors while preserving correct responses and provides robustness guarantees under adversarial perturbations. The code of the evaluation framework and artifacts are made available at https://anonymous.4open.science/r/Visual-Prompt-Inject.

Jiamin Chang, Minhui Xue, Ruoxi Sun +3

University of New South Wales, Sydney, NSW 2052, Australia · CSIRO’s Data61, Marsfield, NSW 2122, Australia · Macquarie University, NSW 2109, Australia

VLM Robustness Adversarial Attacks on VLMs Prompt Injection AI Agent Security AI Agent Security Benchmarks Vision-Language Agents

Apr 20, 2026cs.AI

How Adversarial Environments Mislead Agentic AI?

Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking "can the agent use tools correctly" but never "what if the tools lie". We identify this Trust Gap: agents are evaluated for performance, not for skepticism. We formalize this vulnerability as Adversarial Environmental Injection (AEI), a threat model where adversaries compromise tool outputs to deceive agents. AEI constitutes environmental deception: constructing a "fake world" of poisoned search results and fabricated reference networks around unsuspecting agents. We operationalize this via POTEMKIN, a Model Context Protocol (MCP)-compatible harness for plug-and-play robustness testing. We identify two orthogonal attack surfaces: The Illusion (breadth attacks) poison retrieval to induce epistemic drift toward false beliefs, while The Maze (depth attacks) exploit structural traps to cause policy collapse into infinite loops. Across 11,000+ runs on five frontier agents, we find a stark robustness gap: resistance to one attack often increases vulnerability to the other, demonstrating that epistemic and navigational robustness are distinct capabilities.

Zhonghao Zhan, Huichi Zhou, Zhenhao Li +3

Imperial College London

Adversarial Robustness AI Agent Evaluation AI Agent Security AI Agent Security Benchmarks

Apr 20, 2026cs.CR

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents

GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6.51 s on real OSWorld workloads) creates a Time-Of-Check, Time-Of-Use (TOCTOU) window during which an unprivileged attacker can manipulate the UI state. We formalize this as a Visual Atomicity Violation and characterize three concrete attack primitives: (A) Notification Overlay Hijack, (B) Window Focus Manipulation, and (C) Web DOM Injection. Primitive B, the closest desktop analog to Android Action Rebinding, achieves 100% action-redirection success rate with zero visual evidence at the observation time. We propose Pre-execution UI State Verification (PUSV), a lightweight three-layer defense that re-verifies the UI state immediately before each action dispatch: masked pixel SSIM at the click target (L1), global screenshot diff (L2a), and X Window snapshot diff (L2b). PUSV achieves 100% Action Interception Rate across 180 adversarial trials (135 Primitive A + 45 Primitive B) with zero false positives and < 0.1 s overhead. Against Primitive C (zero-visual-footprint DOM injection), PUSV reveals a structural blind spot (~0% AIR), motivating future OS+DOM defense-in-depth architectures. No single PUSV layer alone achieves full coverage; different primitives require different detection signals, validating the layered design.

Wenpeng Xu

University of California, San Diego

Adversarial Attacks Computer-Use Agents AI Agent Security Runtime Verification GUI Automation

Apr 20, 2026cs.CR

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose Owner-Harm, a formal threat model with eight categories of agent behavior damaging the deployer. We quantify the defense gap on two benchmarks: a compositional safety system achieves 100% TPR / 0% FPR on AgentHarm (generic criminal harm) yet only 14.8% (4/27; 95% CI: 5.9%-32.5%) on AgentDojo injection tasks (prompt-injection-mediated owner harm). A controlled generic-LLM baseline shows the gap is not inherent to owner-harm (62.7% vs. 59.3%, delta 3.4 pp) but arises from environment-bound symbolic rules that fail to generalize across tool vocabularies. On a post-hoc 300-scenario owner-harm benchmark, the gate alone achieves 75.3% TPR / 3.3% FPR; adding a deterministic post-audit verifier raises overall TPR to 85.3% (+10.0 pp) and Hijacking detection from 43.3% to 93.3%, demonstrating strong layer complementarity. We introduce the Symbolic-Semantic Defense Generalization (SSDG) framework relating information coverage to detection rate. Two SSDG experiments partially validate it: context deprivation amplifies the detection gap 3.4x (R = 3.60 vs. R = 1.06); context injection reveals structured goal-action alignment, not text concatenation, is required for effective owner-harm detection.

Dongcheng Zhang, Yiqing Jiang

BlueFocus Communication Group · Tongji University

AI Agent Security AI Agent Safety Prompt Injection Attacks on AI Agents AI Agent Safety Benchmarks

Apr 20, 2026cs.CR

From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers

The transition of agentic AI from brittle prototypes to production systems is stalled by a pervasive crisis of craft. We suggest that the prevailing orchestration paradigm-delegating the system control loop to large language models and merely patching with heuristic guardrails-is the root cause of this fragility. Instead, we propose Arbiter-K, a Governance-First execution architecture that reconceptualizes the underlying model as a Probabilistic Processing Unit encapsulated by a deterministic, neuro-symbolic kernel. Arbiter-K implements a Semantic Instruction Set Architecture (ISA) to reify probabilistic messages into discrete instructions. This allows the kernel to maintain a Security Context Registry and construct an Instruction Dependency Graph at runtime, enabling active taint propagation based on the data-flow pedigree of each reasoning node. By leveraging this mechanism, Arbiter-K precisely interdicts unsafe trajectories at deterministic sinks (e.g., high-risk tool calls or unauthorized network egress) and enables autonomous execution correction and architectural rollback when security policies are triggered. Evaluations on OpenClaw and NanoBot demonstrate that Arbiter-K enforces security as a microarchitectural property, achieving 76% to 95% unsafe interception for a 92.79% absolute gain over native policies. The code is publicly available at https://github.com/cure-lab/ArbiterOS.

Xiangyu Wen, Yuang Zhao, Xiaoyu Xu +9

CUHK · Hong Kong SAR, China · Shanghai Jiao Tong University +6

AI Agent Security AI Agent Safety Runtime Enforcement for AI Agents AI Agent Governance

Apr 19, 2026cs.AI

SafeAgent: A Runtime Protection Architecture for Agentic Systems

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning through two coordinated components: a runtime controller that mediates actions around the agent loop and a context-aware decision core that operates over persistent session state. The core is formalized as a context-aware advanced machine intelligence and instantiated through operators for risk encoding, utility-cost evaluation, consequence modeling, policy arbitration, and state synchronization. Experiments on Agent Security Bench (ASB) and InjecAgent show that SafeAgent consistently improves robustness over baseline and text-level guardrail methods while maintaining competitive benign-task performance. Ablation studies further show that recovery confidence and policy weighting determine distinct safety-utility operating points.

Hailin Liu, Eugene Ilyushin, Jie Ni +1

Lomonosov Moscow State University · Central University

Adversarial Attacks on LLMs AI Agent Security LLM Agent Security Prompt Injection Attacks on LLMs

Apr 18, 2026cs.CR

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning

The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it introduces a vulnerability: reliance on Long-term Memory (LTM). In this paper, we uncover a threat termed "Visual Inception." Unlike traditional adversarial attacks that seek immediate misclassification, Visual Inception injects triggers into user-uploaded images (e.g., lifestyle photos) that act as "sleeper agents" within the system's memory. When retrieved during future planning, these poisoned memories hijack the agent's reasoning chain, steering it toward adversary-defined goals (e.g., promoting high-margin products) without prompt injection. To mitigate this, we propose CognitiveGuard, a dual-process defense framework inspired by human cognition. It consists of a System 1 Perceptual Sanitizer (diffusion-based purification) to cleanse sensory inputs and a System 2 Reasoning Verifier (counterfactual consistency checks) to detect anomalies in memory-driven planning. Extensive experiments on a mock e-commerce agent environment demonstrate that Visual Inception achieves about 85% Goal-Hit Rate (GHR), while CognitiveGuard reduces this risk to around 10% with configurable latency trade-offs (about 1.5s in lite mode to about 6.5s for full sequential verification), without quality degradation under our setup.

Jiachen Qian

City University of Hong Kong

AI Agent Security Agent Memory Poisoning Recommender Systems

Apr 18, 2026cs.CR

Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives

AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls: privileged operations with side effects on shared state, yet today's safety enforcement lives entirely in userspace, where a 10-line script can bypass it. I propose Governed MCP, a kernel-resident tool governance gateway built on a logit-based safety primitive (ProbeLogits). The gateway interposes on every MCP tool call in a 6-layer pipeline: schema validation, trust tier, rate limit, adversarial pre-filter, a ProbeLogits semantic gate (the load-bearing check), and constitutional policy match, with a Blake3-hashed audit chain. I implement Governed MCP in Anima OS, a bare-metal x86-64 kernel in ~286,000 lines of Rust. The five non-inference layers plus the audit append cost a measured 11.3 us per call; the ProbeLogits gate (one probe-prompt prefill plus a single logit read) costs 332-556 ms per classification across Qwen2.5-7B, Llama-3-8B, and Mistral-7B, 2.4-3.4x faster than a Llama Guard 3 pass on the same hardware. A silicon-measured ablation shows that removing the ProbeLogits layer collapses F1 from 0.789 to 0.357 (delta-F1 = -0.432): hand-rule firewalling alone is insufficient. Every WASM-to-system host function and every registered MCP tool is mediated by the kernel gateway, so the 10-line userspace bypass that defeats existing guardrail libraries is structurally impossible; a disclosed set of ring-3 syscall paths remains ungated pending future work. Multi-model validation across three architectures (HarmBench 98-99% non-copyright block, XSTest 98.5-100% unsafe recall, ToxicChat parity with Llama Guard 3) shows the underlying primitive is architecture-agnostic. Governed MCP demonstrates that tool-call governance is feasible as an OS primitive, not just an application-layer concern.

Daeyeon Son

Independent Researcher · Republic of Korea

MCP Security AI Agent Security Safety Filtering Runtime Enforcement for AI Agents AI Agent Governance Access Control+1

Apr 18, 2026cs.CR

enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways

We present enclawed, a hard-fork hardening framework built on the OpenClaw AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a tamper-evident audit trail -- typically regulated industries (financial services, healthcare, defense, government). The framework ships in two flavors: an open flavor preserving OpenClaw compatibility while emitting audit, classification, and data-loss-prevention (DLP) signals, and an enclaved flavor activating strict allowlists, FIPS cryptographic-module assertion, mandatory manifest signature verification, and high-assurance peer attestation for the Model Context Protocol. The classification ladder is data-driven: deployers pick from five built-in presets or supply their own JSON. We ship a 356-case test suite (261 unit + 95 adversarial pen-tests) covering tamper detection, signature forgery, egress bypass, audit-log truncation, trust-root mutation, DLP evasion, prompt injection, code injection, and biconditional admission for net-capable extensions; real-time human-in-the-loop control; a memory-bounded transaction buffer with rollback; strict-mode TypeScript typecheck; and a CI workflow. The biconditional extension-admission gate extends the skill trust schema to non-skill extensions. The four-level verification lattice is now closed at the top: four skill-formal-* primitives plus a CLI produce a signed proof-carrying bundle the runtime re-checks at load, raising a skill from tested to formal via static effect-containment, refinement-typed dispatch, and bounded model checking. enclawed is a hardening framework, not an accredited certification; hardware, validated crypto, facilities, and assessor sign-off remain the deployer's responsibility.

Alfredo Metere

Metere Consulting, LLC.

AI Assurance AI Agent Security LLM Agent Security

Apr 18, 2026cs.CR

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution

Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding sockets. This design fails against prompt injection, tool misuse, and model-controlled exfiltration because the agent can both use and reveal the same bearer credential. We present CapSeal, a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker. CapSeal combines capability issuance, schema-constrained HTTP execution, broker-executed SSH actions, anti-replay session binding, policy evaluation, and tamper-evident audit trails. We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability, and define an evaluation plan spanning prompt injection, tool misuse, and SSH abuse. The resulting system reframes secret handling for agentic systems from handing the model a key to granting the model a narrowly scoped, non-exportable action capability.

Shutong Jin, Ruiyi Guo, Ray C. C. Cheung

City University of Hong Kong, Hong Kong · Beijing Foreign Studies University

AI Agent Security LLM Agent Security Capability-Based Security

Apr 16, 2026cs.SE

Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents. This has drawn growing research attention, and many agent security and safety benchmarks have emerged. They implicitly shape how the community approaches security and safety. Yet existing work exhibits a blind spot: it emphasizes training-based methods and neural guardrails, which reduce the likelihood of insecure or unsafe actions but cannot guarantee their prevention. It generally overlooks opportunities for deductive, symbolic guardrails grounded in standard software engineering practices, which can provide guarantees for some security and safety requirements. Our study has three parts: (1) a systematic review of 80 agent security and safety benchmarks finding that that 85% of benchmarks do not state verifiable requirements (61% provide none, and 24% give only high-level goals); (2) an applicability analysis of which security and safety requirements symbolic guardrails can and cannot enforce on

τ^2

-Bench, CAR-bench, and MedAgentBench, finding that 74% of requirements are symbolically enforceable and 95% of these need only simple, low-cost checks; and (3) an empirical evaluation of symbolic guardrails on the same three benchmarks, finding that symbolic guardrails improve security and safety without sacrificing utility, and often improve it. Our work draws attention to the potential for symbolic guardrails for AI agents, suggesting them as an overlooked but practical path toward deploying domain-specific AI agents in risk-averse commercial software. We release all codes and artifacts at https://github.com/hyn0027/agent-symbolic-guardrails.

Yining Hong, Yining She, Eunsuk Kang +2

Carnegie Mellon University

LLM Guardrails AI Agent Security AI Agent Safety AI Agent Security Benchmarks AI Agent Safety Benchmarks

Apr 16, 2026cs.SE

Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution

Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests, cross-workspace execution, and other costly failures. We argue this is primarily an execution architecture problem. We present a bounded-autonomy architecture in which language models may interpret intent and propose actions, but all executable behavior is constrained by typed action contracts, permission-aware capability exposure, scoped context, validation before side effects, consumer-side execution boundaries, and optional human approval. The enterprise application remains the source of truth for business logic and authorization, while the orchestration engine operates over an explicit published actions manifest. We evaluate the architecture in a deployed multi-tenant enterprise application across three conditions: manual operation, unconstrained AI with safety layers disabled, and full bounded autonomy. Across 25 scenario trials spanning seven failure families, the bounded-autonomy system completed 23 of 25 tasks with zero unsafe executions, while the unconstrained configuration completed only 17 of 25. Two wrong-entity mutations escaped all consumer-contributed layers; only disambiguation and confirmation mechanisms intercept this class. Both AI conditions delivered 13-18x speedup over manual operation. Critically, removing safety layers made the system less useful: structured validation feedback guided the model to correct outcomes in fewer turns, while the unconstrained system hallucinated success. Several safety properties are structurally enforced by code and intercepted all targeted violations regardless of model output. The result is a practical, deployed architecture for making imperfect language models operationally useful in enterprise systems.

Sarmad Sohail, Ghufran Haider

LLM Guardrails AI Agent Security AI Agent Safety LLM Safety

Apr 16, 2026cs.CR

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments

We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks representing legitimate software engineering work, and 184 side tasks representing safety failures such as data exfiltration and backdooring, making it the largest and most diverse control setting for software engineering to date. We validate LinuxArena is useful for control research by running sabotage evaluations, which measure whether attackers can complete side tasks while working on main tasks, and monitor evaluations, which measure a monitor model's ability to detect sabotage attempts. Against a GPT-5-nano trusted monitor at a 1% step-wise false positive rate, Claude Opus 4.6 achieves roughly a 23% undetected sabotage success rate. We additionally release LaStraj, a dataset of human-crafted attack trajectories that evade monitors at substantially higher rates than any model-generated attacks we elicited, showing that current attack policies do not saturate LinuxArena. These results suggest that LinuxArena has meaningful headroom for both attackers and defenders, making it a strong testbed for developing and evaluating future control protocols.

Tyler Tracy, Ram Potham, Nick Kuhn +31

Redwood Research · EquiStamp

Software Engineering Agents AI Agent Security AI Agent Security Benchmarks AI Agent Monitoring AI Control

Apr 13, 2026cs.CR

Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering

AI agents that pay for resources via the x402 protocol embed payment metadata - resource URLs, descriptions, and reason strings - in every HTTP payment request. This metadata is transmitted to the payment server and to the centralised facilitator API before any on-chain settlement occurs; neither party is typically bound by a data processing agreement. We present presidio-hardened-x402, the first open-source middleware that intercepts x402 payment requests before transmission to detect and redact personally identifiable information (PII), enforce declarative spending policies, and block duplicate replay attempts. To evaluate the PII filter, we construct a labeled synthetic corpus of 2,000 x402 metadata triples spanning seven use-case categories, and run a 42-configuration precision/recall sweep across two detection modes (regex, NLP) and five confidence thresholds. The recommended configuration (mode=nlp, min_score=0.4, all entity types) achieves micro-F1 = 0.894 with precision 0.972, at a p99 latency of 5.73ms - well within the 50ms overhead budget. The middleware, corpus, and all experiment code are publicly available at https://github.com/presidio-v/presidio-hardened-x402.

Vladimir Stantchev

SRH University Heidelberg, Germany · PRESIDIO Group, Sofia, Bulgaria

AI Agent Security Safety Filtering PII Detection

Apr 9, 2026cs.CR

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

Existing red-teaming studies on GUI agents face two fundamental limitations: adversarial perturbations require white-box access unavailable in commercial deployments, while prompt injection is increasingly neutralized by stronger safety alignment. To study robustness under a more practical threat model, we propose Semantic-level UI Element Injection, a black-box red-teaming paradigm that overlays safety-aligned and harmless UI elements onto screenshots to misdirect the agent's visual grounding. Our method couples a modular Editor--Overlapper--Victim pipeline with iterative search that samples multiple candidate edits, keeps the best cumulative overlay, and adapts future prompt strategies based on previous failures. Experiments across 19 victim models spanning 8 model families show that strategic optimization substantially outperforms random injection (3.5-6.9x on the most robust victims) and transfers near-perfectly across architectures, confirming model-agnostic visual-semantic vulnerabilities. After the first successful attack, the victim still clicks the attacker-controlled icon in over 15% of subsequent independent trials versus below 1% for random injection, establishing that strategically placed icons act as persistent attractors that causally redirect grounding rather than introducing incidental clutter.

Wenkui Yang, Chao Jin, Haisu Zhu +7

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · 2MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences · 4ShanghaiTech University +2

GUI Agents AI Agent Security Black-Box Adversarial Attacks Automated Red Teaming

Apr 7, 2026cs.AI

Auditable Agents

LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions remain answerable after deployment. We distinguish accountability (the ability to determine compliance and assign responsibility), auditability (the system property that makes accountability possible), and auditing (the process of reconstructing behavior from trustworthy evidence). Our claim is direct: no agent system can be accountable without auditability. To make this operational, we define five dimensions of agent auditability, i.e., action recoverability, lifecycle coverage, policy checkability, responsibility attribution, and evidence integrity, and identify three mechanism classes (detect, enforce, recover) whose temporal information-and-intervention constraints explain why, in practice, no single approach suffices. We support the position with layered evidence rather than a single benchmark: lower-bound ecosystem measurements suggest that even basic security prerequisites for auditability are widely unmet (617 security findings across six prominent open-source projects); runtime feasibility results show that pre-execution mediation with tamper-evident records adds only 8.3 ms median overhead; and controlled recovery experiments show that responsibility-relevant information can be partially recovered even when conventional logs are missing. We propose an Auditability Card for agent systems and identify six open research problems organized by mechanism class.

Yi Nian, Aojie Yuan, Haiyue Zhang +7

University of Southern California · Arizona State University · University of Tennessee, Knoxville +1

AI Accountability AI Agent Auditing LLM Auditing AI Agent Security

Mar 21, 2026cs.CR

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which leverages execution trajectories to guide the discovery of adversarial prompts. Our approach enables the automatic generation of attacks that not only bypass safety guardrails but also reliably realize harmful objectives through actual tool interactions. Empirical evaluations across diverse MCP environments demonstrate that T-MAP substantially outperforms baselines in attack realization rate (ARR) and remains effective against frontier models, including GPT-5.2, Gemini-3-Pro, Qwen3.5, and GLM-5, thereby revealing previously underexplored vulnerabilities in autonomous LLM agents. Code is available at https://github.com/pwnhyo/T-MAP.

Hyomin Lee, Sangwoo Park, Yumin Choi +3

KAIST · University of California, Los Angeles

Adversarial Prompt Generation LLM Red Teaming AI Agent Security LLM Agent Security