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

Jun 2, 2026cs.AI

Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI

As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and dynamic scoping as executable governance primitives. Unlike access delegation standards such as OAuth 2.0, we treat delegation as a contractual term rather than merely a static token-based consent credential. This paper proposes a compositional governance framework that introduces primitives indispensable for agentic AI. We define types of delegation and their permissions and accountability implications, and we introduce a notion of resource scope attenuation to bound agentic access envelopes. These concepts are expressed as general relational definitions that can be composed into existing authorization domains (e.g., financial systems). To operationalize this composition, we define a compositional operator that overlays new agentic semantics, such as recursive delegation chains, onto existing relational policies without rewriting them. We substantiate this framework through formal proofs and empirical evaluation, showing that it provides a formal yet practical foundation for accountable authorization in agentic AI systems.

Amjad Ibrahim, Yong Li

Huawei Heisenberg Research Center Germany

AI Accountability AI Agent Security AI Agent Governance Access Control Tool Access Control for LLM Agents Agentic AI

Jun 2, 2026cs.MA

OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery

This yellow paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection and discoverable AI resource products. It specifies the role architecture, \texttt{did:oan} identity objects, registration workflow, governance-backed Root lifecycle enforcement, Root-verified package model, authorization-aware Discovery, Root-issued infrastructure authorization VCs, signed trusted invocation, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, domain-specific Agent protocols, Skills, MCP Servers, and Tool/API resources. OAN does not define the entire business conversation among Agents or the native protocol of every resource; it defines how resource identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins.

Jinliang Xu

China Academy of Information and Communications Technology, Beijing, China

AI Agent Security AI Agent Governance

Jun 2, 2026cs.MA

OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection

OpenAgenet, abbreviated as OAN, is an open infrastructure project for trusted Agent interconnection. It addresses a problem that becomes visible when Agents move from isolated applications into open, multi-operator networks: before an Agent can safely discover, select, and invoke another Agent, it needs a way to verify identity provenance, governance state, discovery authorization, freshness, and pre-connection trust evidence. OAN is designed as a protocol-neutral trust layer. It does not replace Agent interaction protocols, tool protocols, model orchestration frameworks, or application-level workflows. Instead, it provides \texttt{did:oan}-based resource identity, governance-backed admission, Registrar-assisted onboarding, Root-verified package publication, authorization-aware Discovery, Root-issued infrastructure authorization VCs, and signed trusted invocation. The architectural center of OAN is the combination of federated governance, resource identity, and trusted Discovery, rather than a single directory or naming service. This white paper explains the motivation, architecture, roles, governance model, relationship with MCP, A2A, and ANP, deployment patterns, cooperation model, on-chain governance layer, prototype status, performance profile, and roadmap of OAN.

Jinliang Xu

China Academy of Information and Communications Technology, Beijing, China

AI Agent Security AI Agent Governance

Jun 1, 2026cs.CL

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.

Yuting Ning, Zhehao Zhang, Yash Kumar Lal +8

The Ohio State University · Amazon AGI · Stanford University

AI Agent Security AI Agent Security Benchmarks

Jun 1, 2026cs.CR

Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems

Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows. Their core abstractions processes, threads, system calls, files, and permissions assume bounded behavior and predictable interaction patterns. Agentic AI systems introduce a different execution model: long-lived, goal-directed entities that reason probabilistically, invoke tools dynamically, and adapt behavior based on feedback. While agents can be implemented as user-space applications today, their execution characteristics stress OS boundaries in scheduling, memory and state management, security, observability, and governance. This paper introduces the concept of an Agent Operating System (AOS), a systems architecture that integrates an agentic control plane into existing operating systems or, in some models, subsumes selected OS responsibilities over time. We provide a precise definition of an AOS, explicit assumptions and non-goals, and a structured decomposition of AOS responsibilities into schedulers, context and memory management, tool and capability registries, policy and trust enforcement, and observability and audit. We analyze limitations of classical OS abstractions for agent workloads, propose integration models from user-space runtimes to distributed control planes, and map AOS concepts onto Linux and Windows primitives. We present security and safety implications, including agent specific threat models, and define evaluation criteria that emphasize deterministic enforcement, auditability, and operator comprehensibility. The objective is not to replace operating systems wholesale, but to establish a rigorous systems foundation for agentic computation that remains controllable, accountable, and secure at scale.

Ankur Sharma, Deep Shah

Independent Researcher San Francisco, USA

AI Agent Security AI Agent Monitoring AI Agent Governance

May 31, 2026cs.CR

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill versions. Each row pairs redacted SKILL.md content and sanitized bundled files where present with a final ClawScan registry verdict and evidence from three scanner families: VirusTotal, static heuristic analysis, and NVIDIA SkillSpector. Rather than estimating malicious-skill prevalence, we study scanner disagreement. The three scanners rarely flag the same skills: any pair overlaps on at most 10.4% of their combined positives, only 0.69% of skills are flagged by all three, and 81.9% of flagged skills are identified by a single scanner. The disagreement is structured by attack surface. SkillSpector, which raises semantic agentic-risk advisories rather than malware-reputation signals, is positive for 19,209 of 25,504 suspicious rows (75.3%) but only 14 of 206 malicious rows (6.8%). The malicious-verdict region shows the inverse profile: 150 of 206 malicious rows (72.8%) are VirusTotal-positive, consistent with bundled-code malware evidence. These results show that agent-skill security requires layered governance, not single-scanner allow/block decisions. The corpus is released as a sanitized silver-standard dataset: labels are the registry's automated verdicts, not human-annotated ground truth, and the release represents an early, versioned snapshot intended to support the community while a human-annotated subset is developed. Further research is encouraged, including models tailored for skill-security triage.

Vincent Koc, Patrick Erichsen, Jacob Tomlinson +3

OpenClaw Foundation USA · NVIDIA United Kingdom · NVIDIA USA

AI Agent Security Agent Skill Security Auditing Malware Detection

May 30, 2026cs.CR

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems

Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contributors can hide harmful behavior inside skills that appear benign under superficial inspection. However, existing defenses are hard to evaluate because there is no benchmark that measures both malicious-skill detection and runtime verification. We present SkillVetBench, a two-stage security vetting benchmark for open agentic skill ecosystems. The first stage performs semantic vetting over each skill's natural-language specification to detect hidden malicious intent. The second stage executes flagged skills in an instrumented sandbox to observe runtime behavior and collect auditable evidence. We build a benchmark from confirmed malicious skills in the live OpenClaw ecosystem, including samples from the recent ClawHavoc supplychain campaign. Unlike static-only methods, SkillVetBench verifies detected threats with execution traces. Our experiments show that: (1) semantic-only and signature-based baselines are insufficient, missing up to 89% of malicious skills whose threats arise from natural-language instructions, multicomponent logic, or cross-component interactions; (2) runtime attacks are concentrated in a small set of high-permission primitives, especially exec, write_file, install_skill, and spawn; and (3) SkillVetBench provides case studies in which sandbox execution directly supports malicious verdicts with concrete runtime evidence.

Ismail Hossain, Sai Puppala, Zhuoran Lu +2

University of Texas at El Paso, TX, USA · Southern Illinois University-Carbondale, IL, USA · Purdue University, IN, USA

AI Agent Security AI Agent Security Benchmarks Software Supply Chain Security Agent Skill Security Auditing

May 30, 2026cs.SE

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set. We study a core safety problem in agentic AI systems: whether individually safe skills can compose into unsafe installed skill sets. We present SkillReact, a compositional security measurement framework with three components: a deterministic static-composition benchmark, a two-rater LLM-assisted human-adjudication pipeline, and an action-based exploitability harness. On 1,520 ClawHub skills, 651 pass individual inspection and form 211,575 pairs; the benchmark flags 22.25% of these as structural candidates. We treat this raw rate as a recall-oriented scanner ceiling and calibrate it against human judgment: in a pattern-stratified audit, roughly one in five flagged pair-pattern hits survives as a real compositional risk (population-weighted validity 18.2%, our headline result), implying about 14K genuine risk memberships in a single registry that per-skill scanning misses by construction, since every pair is individually safe. An action-based harness then probes when these candidates become model-issued tool calls, and finds realization gated by host-model disposition: on an anchor-conditioned dropper subset, Haiku-4-5 issues the dropper-stage tool call on all 39 direct-prompt trials (36 of them the full download-then-execute chain, 3 download-only), Opus-4-7 stops at the download, and Sonnet-4-6 refuses outright. A control that holds the request fixed and varies only the installed skills finds compliance highest with no skills installed: a composition fixes which capabilities are reachable, while the host model decides whether to use them. Together these motivate install-time compositional checks and capability isolation as complements to per-skill scanning.

Su Wang, Pin Qian, Yihang Chen +6

Carnegie Mellon University · Georgia Institute of Technology · University of Glasgow +2

Software Security AI Agent Security LLM Agent Security AI Agent Security Benchmarks Agent Skill Security Auditing

May 29, 2026cs.CV

VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents

Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking external tools. We study a concrete failure mode in this setting: action-boundary propagation, where sensitive or unsafe visible text is copied from an image into downstream tool arguments. We present VisualLeakBench, a diversified 500-image benchmark spanning UI, chat, document, form, and dashboard scenes, and evaluate a stratified 100-image agent subset with four production VLM systems under two workflows: note capture and external handoff. At baseline, target strings are propagated into tool arguments in 78.8% of PII cases and 85.5% of rendered unsafe-text cases. Under a defensive system prompt, rendered unsafe-text propagation remains high at 52.6%, while PII tool propagation falls to 2.0%, largely by suppressing tool use rather than preserving utility. Rates are tool-surface dependent: search-like tools suppress PII propagation, but rendered unsafe text still crosses tool boundaries. We measure visual-to-tool propagation rather than downstream instruction execution. We additionally provide a labeled-target oracle upper-bound diagnostic that localizes most failures at the tool boundary while leaving response-side leakage as residual risk.

Youting Wang, Yuan Tang, Yitian Qian +1

Northeastern University · Carnegie Mellon University · Boston University +1

Data Leakage Tool Use in VLMs AI Agent Security Privacy Leakage in Language Models AI Agent Security Benchmarks Tool-Using Vision-Language Agents

May 29, 2026cs.CR

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity

ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, and data access. Their tool observation loop creates a direct attack surface: an adversary who controls any tool's return value can embed instructions that redirect the agent away from the user's goal, a threat known as indirect prompt injection. Existing benchmarks evaluate attack success rate (ASR) at a fixed injection position under fixed conditions, leaving three risk dimensions unexplored: where in the tool sequence the payload appears (injection depth), what rhetorical register it uses (framing), and how many turns the agent is permitted (turn cap). We conduct four controlled studies on 20 scenarios spanning five attack categories, totalling 460 trials against GPT-4o-mini and Claude Haiku at a combined API cost under 0.36 USD. Study 1 shows that ASR against GPT-4o-mini decays from 60% at depth 1 to 0% at depths 4 and 5 (Cramer's V = 0.58, p < 0.001; restricted to within-sequence depths 1-3: V = 0.47, p = 0.0013), driven by model resistance at depth 1 and task completion before payload encounter at deeper positions. Study 2 replicates the depth experiment on Claude Haiku, which achieves 0% ASR at every depth through a combination of conservative tool invocation and genuine instruction resistance. Study 3 shows that framing modulates ASR between 25% (neutral) and 75% (persona) at depth 1, a 50-percentage-point range that does not reach statistical significance at N = 20 per condition. Study 4 confirms that ASR is stable across turn caps of 3, 5, and 7, indicating the turn budget is not a risk factor in this setting. Our results establish injection depth as the dominant variable and show that sanitising only the first tool observation captures 67% of measured injection successes.

Mohammadreza Rashidi

Department of Computer Science AI and Media Analysis Lab Berlin, Germany

LLM Agent Evaluation AI Agent Security Indirect Prompt Injection Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents

May 28, 2026cs.AI

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex and OpenClaw execution scenarios. We further build a taxonomy-guided data engine with influence-function purification to train lightweight AgentDoG 1.5 variants (0.8B, 2B, 4B, and 8B parameters) using only around 1k samples, achieving comparable performance with leading closed-source models (e.g., GPT-5.4). Based on AgentDoG 1.5, we construct a highly efficient agentic safety SFT and RL training environment, which reduces deployment overhead in Docker-level environments by two orders of magnitude. Finally, we deploy AgentDoG 1.5 as a training-free online guardrail for real-time safety moderation. Extensive experimental results indicate that AgentDoG 1.5 achieves state-of-the-art performance in diverse and complex interactive agentic scenarios. All models and datasets are openly released.

Dongrui Liu, Yu Li, Zhonghao Yang +47

LLM Safety Alignment AI Agent Security AI Agent Safety LLM Agent Training

May 28, 2026cs.AI

Provably Secure Agent Guardrail

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures heavily rely on empirical semantic guardrails and probabilistic large model adjudicators, mechanisms that fail to provide deterministic security lower bounds when facing complex semantic symbol decoupling attacks. To overcome this empirical semantic guardrail dilemma, this paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning. Based on this paradigm, we further introduce an executable Proof-Constrained Action (ePCA) framework with a neural symbolic isolation architecture. This framework abandons semantic trust in natural language, forcing agents to losslessly formalize their intentions into first-order logical mathematical constraints before performing physical operations. Empirical evaluations of macroscopic and microscopic two-dimensional dynamic adversarial systems demonstrate that our formal verification mechanism achieves zero attack success rate and zero false positive rate across the evaluated scenarios, with extremely low computational latency. This research provides a conditional formal foundation under explicit system assumptions and an engineering paradigm for constructing the underlying defense foundation for future intelligent systems.

Benlong Wu, Weiming Zhang, Kejiang Chen +2

University of Science and Technology of China

LLM Guardrails AI Agent Security Formal Verification

May 27, 2026cs.AI

The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane

AI agents are increasingly expected to operate as digital employees: accessing enterprise data, making decisions, and taking actions autonomously. But agents are simultaneously less predictable than humans -- prone to hallucination, misinterpretation, and adversarial manipulation -- and more technically capable: with deep system knowledge and high-throughput interfaces cascading damage at machine speed. This combination makes it unsafe to rely on agents to faithfully interpret or propagate security-critical metadata such as access policies, data classifications, and behavioral constraints. We present the Redpanda Agentic Data Plane (ADP), an architecture built around out-of-band metadata channels: infrastructure pathways that carry security context, policy signals, and audit trails deterministically, entirely outside the agent's read and write path and across heterogeneous infrastructure. These channels enforce governance at every stage of the agent lifecycle -- scoping data access on the way in, constraining actions during execution, and capturing tamper-proof transcripts on the way out. We demonstrate ADP with a multi-agent portfolio rebalancing system in which autonomous agents monitor markets, make trade decisions, and execute orders across isolated client accounts -- with per-client data scoping, trade approval thresholds, and tamper-proof audit trails all enforced by out-of-band channels the agents can neither see nor bypass.

Tyler Akidau, Tyler Rockwood, Johannes Brüderl +1

Redpanda · USA / Germany

AI Agent Security AI Agent Safety AI Agent Monitoring Runtime Enforcement for AI Agents AI Agent Governance Multi-Agent System Security

May 27, 2026cs.CR

AIRGuard: Guarding Agent Actions with Runtime Authority Control

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful step is often not an obviously forbidden output, but an ordinary executable action that becomes unsafe because attacker-controlled context steers authorized access against the user's interest. We identify this failure mode as authority confusion: untrusted resources may inform reasoning, but they must not authorize side effects. We present AIRGuard, a runtime guard that operationalizes least privilege as action-time authorization. AIRGuard normalizes heterogeneous tool calls, derives task authority into step-level authority, tracks source and target trust, simulates sensitive side effects, audits cross-step risk, and enforces decisions before actions execute. On AgentTrap, AIRGuard reduces Sonnet 4.6 attack success from 36.3% without defense to 5.5%. On DTAP-150, AIRGuard preserves 76.0% benign utility with Haiku 4.5, compared with 52.0% for ARGUS and 42.0% for MELON. An ablation further shows that prompt-only policy helps only modestly, whereas a dedicated runtime authority-control layer gives the agent system direct control over tool-mediated side effects. Code and data are available at https://github.com/Sophie508/AIRGuard.

Suliu Qin, Haomin Zhuang, Yujun Zhou +2

University of Liverpool · University of Notre Dame · 2Inria, France

AI Agent Security Tool-Using Agents Tool Access Control for LLM Agents

May 27, 2026cs.CR

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on real-world samples, and details the attack patterns we observed. As skill marketplaces grow rapidly and AI agents gain access to sensitive credentials and systems, automated security analysis is no longer optional.

Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta +3

1Snyk

AI Agent Security Malware Analysis Agent Skill Security Auditing

May 27, 2026cs.CR

Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems

Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may also move attacks beyond the reach of visible-text inspection. In this paper, we study whether latent states can carry attack-associated information that remains effective during clean executions. To examine this question, we introduce a latent attack framework that reactivates attack-induced effects through latent interventions without reusing adversarial text. Extensive experiments show that the resulting latent-only attacks can substantially degrade task performance in clean executions, especially when applied to inter-agent KV-cache handoffs rather than local hidden states. Further control analyses indicate that this degradation cannot be reduced to arbitrary perturbations or invalid generation. Overall, our findings suggest that latent-based collaboration does not remove attack risk. It shifts part of the risk into less observable execution states, calling for safeguards beyond visible-text inspection.

Chenxi Wang, Ruiyang Huang, Jiayan Sun +2

Southeast University, Nanjing, China · Peking University, Beijing, China

Multi-Agent LLM Systems Adversarial Attacks Adversarial Attacks on LLMs AI Agent Security Multi-Agent Communication

May 27, 2026cs.CR

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents

A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and the run succeeds, yet an out-of-scope step can leak credentials or delete files. Existing benchmarks miss it: task-completion suites credit any finished run, jailbreak suites probe adversarial prompts, and the one prior overeager benchmark applies a single fixed prompt set to every agent-model pair, leaving its easiest and most resistant pairs under-measured. We present SNARE (Synthesizing Non-adversarial scenarios for Adaptive Reward-guided Elicitation), a pipeline that composes benign scenarios from reusable scope and trap fragments, scores each run with a judge-free oracle flagging trap-pattern matches and unsolicited file additions or deletions, and uses Thompson sampling to steer each pair's run budget toward the scenarios that most often trigger it. Instantiating it over 24 overeager archetypes yields OverEager, which we run across a 4x5 matrix of four coding agents and five base models. Across 10,000 benign runs, 19.51% trigger overeager behavior, with per-pair rates spanning 11.9x. This variation is driven by the agent framework, not the model: the framework accounts for 56% of it against the model's 21%, so any single-framework or single-model evaluation undercounts the matrix by about a fifth.

Yubin Qu, Yi Liu, Gelei Deng +4

1Griffith University · 2Quantstamp · 3Nanyang Technological University +2

Coding Agents AI Agent Security AI Agent Security Benchmarks Synthetic Benchmark Generation

May 27, 2026cs.CR

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent memory have received less attention, even though such memory can contain sensitive user-agent interactions, retrieved facts, and user preferences. Therefore, in this work, we focus on chat agent memory MIAs, where an adversary infers whether a candidate memory unit belongs to the chat agent's memory store. We propose Multi-Recall Memory MIA (MRMMIA), a unified attack that utilizes multiple recall probes to the agent to extract the membership signal across black-box, gray-box, and white-box settings. Our experiments demonstrate that MRMMIA consistently outperforms baselines. Our results expose the privacy risk in agents and provide an initial evaluation framework for membership leakage in chat-agent memory systems.

Kai Chen, Yan Pang, Tianhao Wang

University of Virginia

Data Leakage Membership Inference Attacks LLM Agent Memory AI Agent Security

May 26, 2026cs.AI

Agyn: An Open-Source Platform for AI Agents with Scalable On-Demand Execution, Agent Definition as a Code, and Zero-Trust Access

As organizations move toward production deployments of AI agents, which execute non-deterministic workflows, maintain stateful sessions, and often operate with privileged access to internal services, the engineering challenge shifts from building individual agents to operating them at scale with proper isolation, governance, and security. In this paper we present Agyn, an open-source platform designed around three key principles tailored for agent workloads: a signal-driven, stateful serverless runtime on Kubernetes; a Terraform provider for agent and harness definition; and a security model grounded in zero-trust and least-privilege principles. Agyn is agent-agnostic, model-agnostic, and cloud-agnostic.

Nikita Benkovich, Vitalii Valkov

Agyn, Inc. · Mila AI e-Lab

AI Agent Security AI Agent Governance

May 26, 2026cs.CR

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused by other agents and amplified into system-level harm. We introduce HARP (Harm Amplification through Role Perturbation), a trace-first methodology for studying local-to-global harm amplification in multi-agent LLM systems. HARP compares paired clean and perturbed executions and records specialist outputs, tool calls, memory reads/writes, guard events, oracle logs, latency, token cost, and decisions. We define local harm as deviation from targeted agents or corrupted channels, global harm as deviation over the full trace, and harm amplification as (H_global/H_local). This complements attack success rate with a measure of how strongly orchestration spreads harm beyond the attack point. We instantiate HARP in a finance-oriented seven-agent system with a deterministic decision gate and configurable attack harness for specialist compromise, collusion, shared-context corruption, and temporal or memory-persistent attacks. Across five defenses, prompt-only defenses preserve benign utility but leave high success and stealth; pre-tool and step-level guards reduce some failures with utility or latency costs; and IntegrityGuard, a trace-consistency defense, achieves the lowest attack success and global harm but introduces utility/cost trade-offs. Results show that single-specialist compromise produces the strongest amplification, shared-context corruption yields the highest attack success, and temporal persistence produces the largest malicious impact. HARP argues that secure multi-agent evaluation must measure not only bypass, but propagation.

Md Hafizur Rahman, Zafaryab Haider, Tanzim Mahfuz +1

Electrical and Computer Engineering University of Maine, ME, USA

Multi-Agent LLM Systems Adversarial Attacks on LLMs AI Agent Security Multi-Agent System Security

May 26, 2026cs.CR

Grimlock: Guarding High-Agency Systems with eBPF and Attested Channels

Agentic systems increasingly run user-authored orchestration code that invokes tools, spawns subtasks, and delegates work across machines and clouds. Although this high agency is productive, it creates a security problem: identity, authorization, provenance, and delegation are often pushed into application code, where they become difficult to enforce consistently and difficult to audit. We present Grimlock, an Agent Guard that restores separation of concerns by moving trust enforcement into the sandbox substrate while leaving agent code unchanged. Grimlock uses eBPF-enforced traffic interception to ensure that sandbox communication passes through a guard, and combines it with post-handshake attestation bound to standard TLS~1.3 channel bindings. After a channel is established, the guard authorizes communication and mints short-lived, channel-bound scope tokens that capture least-privilege delegation. At the receiving side, the destination guard re-validates identity, scope, and channel binding, terminates TLS, and releases plaintext to the destination sandbox only after policy checks succeed. kTLS provides an efficient dataplane for protected communication. As a result, Grimlock offers a path toward transparent, auditable, and scope-bound agent-to-agent communication across heterogeneous multi-cloud environments, using commodity Linux primitives and without requiring changes to user-layer orchestration code.

Qiancheng Wu, Wenhui Zhang, Gan Fang +5

Roblox

Agent Communication Protocols Software Security Remote Attestation AI Agent Security

May 26, 2026cs.CR

Lessons from Penetration Tests on Large-Scale Agent Systems

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes of weaknesses long observed in prior computing systems. Execution-capable AI agents are effectively unbounded, self-modifying programs that interact extensively with multiple layers of the computing stack. This broad interaction surface imposes a significant security burden on developers, who must reason about and secure complex cross-layer behaviors. Prior research has primarily focused on vulnerabilities in open-source agents and agent frameworks. In contrast, it remains unclear whether proprietary agent systems -- developed under stricter coding standards and formal review processes -- exhibit similar security weaknesses. In this paper, we present findings from two penetration tests conducted in 2025 against proprietary agent products and evaluate whether the security posture of AI agents has improved since these assessments.

Kevin Eykholt, Dhilung Kirat, Xiaokui Shu +3

IBM Research

Software Security AI Agent Security

May 25, 2026cs.DC

When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems

Multi-agent systems powered by large foundation models (LFMs) are increasingly deployed to control industrial robots through natural language, creating deployments in which security failures produce physical consequences. We analyse this threat landscape through Cobot-Claw, a deployed four-agent system for UR3e robotic arm control, and identify five attack classes specific to agentic cyber-physical systems. We propose ZTPM, a Zero Trust Policy Model comprising 25 typed primitives across five enforcement domains with Physical Impact Tiers as a runtime policy dimension. An empirical evaluation across 60 execution traces on two LFM backends provides initial evidence that actuation parameter selection is model-dependent and non-deterministic, motivating the need for policy-level enforcement at the physical actuation boundary.

Tharindu Ranathunga, Kavishka Fernando, Susan Rea

Nimbus Centre, Munster Technological University, Cork, Ireland

Robotic Control Cyber-Physical Systems Cybersecurity AI Agent Security Multi-Agent System Security Zero-Trust Security

May 25, 2026cs.AI

Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures

The rapid evolution of large language model (LLM)-driven autonomous agents has given rise to OpenClaw, a new class of open-source agent frameworks that operate as continuously running, skill-augmented systems with persistent memory, multi-channel interaction, and high degrees of autonomy. Such capabilities enable OpenClaw agents to autonomously execute complex, multi-step tasks and interact seamlessly with external applications, but simultaneously introduce a substantially enlarged attack surface. In particular, the combination of high-privilege operations and persistent memory exposes OpenClaw agents to various emerging threats, including skill poisoning, cognitive manipulation, multi-agent cascading failures, and supply-chain vulnerabilities. In this survey, we present a comprehensive study of the security landscape of OpenClaw agents. We first examine the general architecture and key characteristics that distinguish OpenClaw agents from traditional AI agent systems. We categorize existing security and privacy threats into a layered framework and analyze how vulnerabilities arise during agent reasoning, action execution, and external interaction. Representative defense mechanisms are also reviewed to draw the current defense landscape. Finally, several unresolved issues related to the reliability and trustworthiness of OpenClaw ecosystems are discussed.

Yuntao Wang, Jianle Ba, Han Liu +5

School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China

AI Agent Security LLM Agent Security Multi-Agent System Security

May 25, 2026cs.CR

KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition

KYA (Know Your Agents) is an open-source, framework-agnostic trust and governance layer for autonomous systems, composed of five primitives: (1) a four-gate inbound apply pipeline; (2) an only-tighten composition algebra over a three-channel multi-tenant hierarchy; (3) KYP (Know Your Principal), a schema-level unification of trust scoring across human users, AI agents, and service accounts; (4) auditable interaction-multiplier amplification over an AIVSS-shaped additive baseline; and (5) two-axis delegation attribution: a static premium for risky delegates and a runtime debit for actual delegate misbehavior in multi-agent fan-out. Together these span three pillars (trust, governance, and evidentiary assurance), making an autonomous system's actions authorized, policy-conforming, and post-hoc verifiable: where observability answers how long, how much, and what path, KYA answers was it authorized, did it conform, and can it be verified; it composes with observability rather than replacing it. It ships native adapters for 15+ agent frameworks. On a 4 by 9 cross-backend matrix all 36 cells pass; the pure-function scorer runs sub-millisecond at p99 and the system sustains ~ 1,800 ops/sec at 20 concurrent workers with HMAC chain integrity preserved end-to-end. KYA detects 89% of 1,200 adversarial probes from PyRIT and Garak, including the recently-published topology-guided multi-agent attack. The system is available under Apache 2.0 as the veldt-kya package on PyPI.

Kolawole Quadri

Veldt Labs USA

AI Agent Security AI Agent Governance Multi-Agent System Security

May 22, 2026cs.CR

Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a server's tools are in bounds. This work grew out of a concrete need -- letting the Enclawed agent use Google's externally-operated MCP servers (Gmail, Calendar, Drive) safely, admitting the server and bounding the tools it may drive, without changing MCP or Enclawed's own tool application-programming interface (API). The mechanism we built, mcp-attested (shipped in both the open enclawed-oss distribution and the enclaved flavor), generalizes: the gap that makes an unmediated third-party connection unsafe for one user makes a regulated deployment impossible to accredit. We close it with three additive mechanisms: (1) a small, offline-signed clearance assertion a server publishes at a well-known Uniform Resource Identifier (URI) and a host verifies against a pinned trust root before any tool dispatch; (2) a deny-by-default per-server tool allowlist, so admitting a server is not trusting its every tool; and (3) a flavor-gated enforcement mode that turns the checks from warnings into hard denials, with every decision written to a tamper-evident audit log. We give the wire format, the verification algorithm, a security analysis, and an LLM-driven adversarial evaluation; we then state the design in normative Request-for-Comments (RFC 2119) form -- schema, verification rules, error registry, well-known registration, and machine-checkable conformance vectors -- so it can be adopted as an MCP addendum rather than reinvented. An unextended host ignores the well-known document and behaves exactly as today.

Alfredo Metere

Enclawed LLC

MCP Security AI Agent Security Model Context Protocol Tool-Use Authorization Tamper-Evident Logging

May 22, 2026cs.MA

ProofAgent Harness: Open Infrastructure for Adversarial Evaluation of AI Agents

AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or static tasks, missing failures that emerge through trajectory, pressure, and adversarial interaction. We introduce ProofAgent Harness, open infrastructure for scalable, auditable, and adversarial AI agent evaluation. The harness provides evaluation infrastructure around an agent: it curates evaluation intelligence, runs adversarial multi-turn trials, captures behavioral traces, applies post-hoc multi-juror scoring, resolves disagreement, and produces evidence-linked reports. Its open design allows developers and researchers to extend domains, traps, metrics, juror personas, scoring rules, and reporting formats. At its core is Adversarial Multi-Juror Scoring with Turn-Level Audit, which evaluates completed agent behavior under pressure using calibrated juror personas, consensus checks, and turn-level evidence. Experiments across customer support, medical triage, privacy and security, and code generation agents show that strong agents fail selectively through weak metrics, fragile turns, unsafe reframing, and manipulation paths. We also find that a small quantized local Harness LLM can challenge production agents powered by best-in-class large LLMs, suggesting that evaluation capability emerges from the full harness pipeline rather than model scale alone. ProofAgent Harness turns AI agent evaluation from a static score into scalable adversarial evaluation infrastructure: repeatable, evidence-backed, extensible, and actionable before deployment.

Fouad Bousetouane

The University of Chicago, USA

AI Agent Reliability AI Agent Auditing AI Agent Evaluation Agent Evaluation AI Agent Security AI Agent Safety

May 21, 2026cs.CR

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.

Sahar Abdelnabi, Chris Hicks, Konrad Rieck +1

ELLIS Institute Tübingen & MPI-IS & Tübingen AI Center, Germany · The Alan Turing Institute, London, UK · BIFOLD & Technische Universität Berlin, Germany +1

AI Agent Evaluation AI Agent Security AI Agent Security Benchmarks Benchmark Validity AI Agent Safety Benchmarks

May 21, 2026cs.CR

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and from 100% to 55.6% on Gemini 2.0 Flash. We formalize this as the Camouflage Detection Gap (CDG), the difference in injection detection rate between static and camouflaged payloads. Across 45 tasks spanning three domains and two model families, CDG is large and statistically significant (chi^2 = 38.03, p < 0.001 for Llama; chi^2 = 17.05, p < 0.001 for Gemini), with zero reverse discordant pairs in either case. We additionally evaluate Llama Guard 3, a production safety classifier, which detects zero camouflage payloads (IDRcamouflage = 0.000), confirming that the blind spot extends beyond few-shot detectors to dedicated safety classifiers. We further show that multi-agent debate architectures amplify static injection attacks by up to 9.9x on smaller models, while stronger models show collective resistance. Targeted detector augmentation provides only partial remediation (10.2% improvement on Llama, 78.7% on Gemini), suggesting the vulnerability is architectural rather than incidental for weaker models. Our framework, task bank, and payload generator are released publicly.

Aaditya Pai

Data Science Institute Columbia University

Multi-Agent LLM Systems AI Agent Security Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Detection

May 20, 2026cs.SE

Quality and Security Signals in AI-Generated Python Refactoring Pull Requests

As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactoring edits affect maintainability, code quality, and security once merged into GitHub repositories. To address this gap, we conduct an empirical study of Python refactoring pull requests (PRs) from the AIDev dataset. We analyze agentic refactoring PRs using PyQu, an ML-based quality assessment tool for Python, to quantify changes across five quality attributes, and we complement PyQu with domain-independent static analysis (Pylint and Bandit) to measure code quality and security issues before and after each change. Our results show that, on average, agentic commits improve a quality attribute in 22.5% of the studied changes, with usability improving most frequently (36.5%). At the same time, 24.17% of modified files introduce new Pylint issues predominantly convention level violations such as long lines-while 4.7% introduce new Bandit findings. From the observed diffs, we derive a taxonomy of 24 recurring change operations and map them to the lint and security findings they most commonly affect. Despite these mixed outcomes, developer acceptance is high: 73.5% of the analyzed PRs are merged, including cases that introduce new lint or security findings, often alongside the removal of existing issues. Overall, these findings highlight both the promise and current limitations of agentic refactoring, and motivate stronger tool-in-the-loop quality and security gating for AI-driven development workflows.

Mohamed Almukhtar, Anwar Ghammam, Hua Ming

University of Michigan-Flint · USA · University of Michigan-Dearborn

AI Coding Agents AI Agent Security Automated Software Engineering Code Generation Evaluation