LLM Agent Security

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 234

Jul 28, 2026cs.CR

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous agents increasingly inherit the same offensive tasks, but do they inherit the tradecraft? We introduce StealthBench,a benchmark that measures operational stealth in autonomous offensive-security agents across six operational security (OPSEC) dimensions. We extract 11 hand-verified OPSEC incidents from real bug-bounty and red-team trajectories, expanded into 14 dockerized task scenarios, where agents, despite finding real vulnerabilities, committed stealth failures inconsistent with standard operational tradecraft: embedding credentials in public uploads, deleting production resources to prove access, force-adding uninvolved users to demonstrate a race condition. We evaluate agent trajectories using a 3-model large language model (LLM) judge panel with majority-vote aggregation, measuring safe success rate (solved and stealthy), Stealth@Solve (tradecraft quality among successful solves), and reckless solve rate (solved but cover blown). Our results show that no model exceeds 54% safe success rate (the compound metric requiring both task completion and stealth), confirming that OPSEC failures are systematic across model families. We release StealthBench as a public benchmark to support both the development of stealth-aware agents and automated OPSEC monitoring for autonomous offensive-security deployments. The interactive leaderboard, evaluation harness, and dataset are available at https://stealthbench.com.

Ads Dawson, Adrian Wood

Security Researcher, USA

AI Agent Security LLM Agent Security AI Agent Security Benchmarks Automated Penetration Testing

Jul 28, 2026cs.AI

Distributing Security Controls Through Harness Engineering

AI coding agents are being adopted at historic speed, yet security and risk concerns remain the primary barrier to scaling agentic AI across organizations. Existing security controls for coding agents are not systematically distributed to engineering teams, and vendor-native solutions introduce ecosystem dependencies that may not suit every deployment context. This paper investigates whether off-the-shelf security controls can be implemented on commercial AI coding agents and scaled to a distributed user base via a custom agent harness. A phased testing methodology was applied across four agent configurations --- two commercial agents with and without controls, a baseline harness, and a security-hardened harness --- using a 23-test suite derived from the OWASP Top 10 for Agentic Applications. SHarD (Secure Harness Distribution), a distributable harness built on the Pi agent harness, demonstrated that three categories of security controls --- OS sandboxing, skill scanning, and tool restriction --- can be embedded and distributed via a single install command while retaining equivalent efficacy to direct installation on commercial agents. SHarD achieved an adjusted score of 100%, matching the best securely configured commercial agent, with no regression across any test category. Notable observations include evidence that model non-determinism produces inconsistent security outcomes and that autonomous agent behavior can cross system boundaries in ways that OS sandboxing directly mitigates. Initial characteristics toward a control harness fitness framework are proposed, and a third research question is identified for future investigation.

William Robert Gore

Georgia Institute of Technology

AI Agent Security LLM Agent Security Tool Access Control for LLM Agents LLM Agent Harnesses

Jul 28, 2026cs.AI

Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories

Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and private deployment behind cloud-hosted agent interfaces, giving providers incentives to keep high-value skills proprietary. Yet hiding the artifacts does not conceal their behavioral effects, which remain observable in execution trajectories and form a behavioral side channel. We define this exposure as Skill Leakage: reconstructing proprietary skills from trajectories elicited by benign queries, without reference answers or success labels. We introduce SigLeak, a black-box framework that exploits recurring skill signatures in agent behavior. It constructs diverse, decision-rich diagnostic tasks, contrasts matched skill-enabled and skill-disabled trajectories, and iteratively refines a reconstructed skill from the isolated patterns. Across five scenarios, three model families, and three agent frameworks, SigLeak outperforms or matches three baselines in nearly every setting. It raises the success rate by 6.88 percentage points over the skill-disabled reference on average and achieves the highest overall SkillSim, our metric for coarse- and fine-grained semantic similarity. These results show that benign execution trajectories can expose proprietary procedural knowledge. The code is available at https://anonymous.4open.science/r/SigLeak-D1DB.

Jianing Geng, Ruiqi He, Zekun Fei +6

Nankai University · Alibaba Group · East China University of Science and Technology +2

LLM Agent Security

Jul 28, 2026cs.AI

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable agent within the environments used to evaluate it. This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action. We use two separate preliminary incident records: the reported July 2026 Hugging Face/OpenAI evaluation breach and Anthropic's subsequent three-incident evaluation review. A comparative evidence protocol distinguishes record-specific factual claims from the shared systems lesson: the evaluation environment is itself part of the security boundary. Across the taxonomy and records, we examine controls for containment, privilege separation, provenance, and responder access, including the dual-use problem that defensive artifacts may also enable misuse. The review identifies practical priorities for evaluating cyber capability together with the security of the environment in which that capability is exercised.

Abu Bakar Siddik

Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh

AI Agent Evaluation Cybersecurity AI Agent Security LLM Agent Security AI Agent Safety

Jul 28, 2026cs.AI

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection. We present Explanation-Bound Tool Execution (EBTE), a claim-carrying mediation layer that converts decision-relevant rationale content into typed action claims and checks them against server-held intent, policy, payload, tool, risk, provenance, and freshness facts. EBTE cannot widen baseline authority: conflicts deny, incomplete or uncertain claims review, and only matching claims remain eligible for governed execution. We formalize this composition under explicit mediation and trusted-fact assumptions and implement a versioned reference profile with minimized audit packets. Across 136 authored conformance scenarios, the full profile matches all specified dispositions, admits none of 96 designated hard contradictions, and passes 232 metamorphic checks. A draft-only reference integration forwards none of 48 authored hard cases under EBTE while preserving all 16 soft-review and 4 aligned draft paths. In a frozen 2026-07-12 exploratory 224-attempt hosted-model record, the historical generation/runner agreement counts are 71/96, 66/96, and 19/32; a zero-call revalidation of the preserved minimized claims under the current pipeline yields 70/96, 65/96, and 17/32. In an AgentDojo-derived semantic check, existing high-risk controls make all 12 attack proposals non-allow, while EBTE resolves the task--proposal contradictions as deny. Together, these studies establish profile conformance and demonstrate the feasibility of server-checked action claims within the evaluated settings.

Genliang Zhu, Chu Wang

Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign

LLM Agent Security LLM Agent Verification Runtime Enforcement for AI Agents Tool-Use Authorization Tool Access Control for LLM Agents

Jul 28, 2026cs.CR

Hybrid Analysis for Secure MCP Tool Use in LLM Agents

The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safety risks, as LLM agents can be induced to perform malicious or unauthorized actions. Although prior work has proposed defenses for securing tool use in LLM agents, most methods rely on static analysis, i.e., inspecting prompts and generated outputs, which limits the defense effectiveness and robustness. To address these limitations, we propose MTGuard, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis. Extensive evaluation demonstrates that MTGuard effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.

Ping He, Yuexiang Xie, Yaliang Li +1

Zhejiang University · Alibaba Group

MCP Security LLM Agent Security Tool Access Control for LLM Agents

Jul 27, 2026cs.CR

Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint tracking permanently taints an agent's context upon reading unvetted data, severely restricting downstream utility. We present APPA (Agentic Permissions Policy Algebra), an IFC framework that resolves this usability bottleneck through engine-managed context branching and prospective acquisition enforcement. Before data acquisition occurs, APPA prospectively evaluates label descents and missing prerequisites, generating actionable remedy plans (Authorize, Accept). To inspect unvetted data without polluting the primary context, a label-seeded child trajectory is spawned, absorbing label descent locally and allowing a trusted sanitizer to return a bounded derivative to the unchanged parent. Governed by a two-monoid model over security labels and shared event logs, we formally prove parent label preservation and merge confinement. Finally, we evaluate APPA on a multi-turn tool-chaining benchmark across four models: it suppresses exfiltration (31%-50% down to 0%-7% attack success), and on three of the four, branching recovers a substantial share of the utility that taint tracking alone forfeits.

Arseny Kravchenko, Vadim Liventsev, Innokentii Konstantinov +2

Archestra AI

LLM Agent Security Prompt Injection Attacks on AI Agents Tool Access Control for LLM Agents

Jul 27, 2026cs.CR

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent that compresses the path from suspicious activity to an analyst ready report. Connecting a decoy to an agent is not a wiring exercise. The unit of investigation is the session rather than the event, and the session key is obscured by the identity layering federated credentials introduce. The agent's evidence horizon must be bounded, since an agent free to query full control plane history inherits the cost and false positive profile deception was meant to remove. And cloud telemetry is partly adversary authored, since object keys and user agent strings are attacker chosen values providers record verbatim, which makes any log to prompt path an indirect prompt injection channel that a decoy widens rather than narrows. We address the first two with a session aggregation operator over a pivot tuple drawn only from provider derived fields, and with dynamic prompt generation, a two stage prompt assembly enforcing a grounding invariant by carrying only fields the agent observed. We identify the third as an unaddressed exposure in this class of system, specify the mitigation it requires, and note our prototype does not implement it. Across ten controlled AWS S3 scenarios, nine were reconstructed completely, no report contained an assertion untraceable to an observed artifact, and latency was four to five minutes. We also state what this evaluation does not establish and name the comparisons that would settle it.

Mohan Manivannan, Dalal Alharthi

College of Information Science University of Arizona Tucson, AZ, USA

Autonomous Cyber Defense Cybersecurity LLM Agent Security

Jul 24, 2026cs.AI

Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture

Enterprise AI agents are typically granted static credential sets at configuration time, holding every tool the role might need for every task they perform. This persistent over-privilege expands the attack surface. We argue that capability scoping must follow a dynamic least-privilege principle and be treated as a prevention mechanism before a detection one. A credential that does not exist in an agent's context cannot be misused regardless of the agent's reasoning or evasion sophistication. We outline a three-source architecture instantiating this principle: role-based ceilings, a task-context classifier, and policy-derived combination prohibitions creating a layered proactive defense against LLM agent misalignment and misuse cases. The architecture supports both enforcing and observe-only deployment; the latter records agent permission requests inconsistent with task context, producing a behavioral signal usable in misalignment research. As a first step toward evaluating this architecture, we contribute a synthetic dataset of 600 enterprise task prompts grounded in a multi-department company policy, labeled with minimum required permissions across a 15-permission tool-based taxonomy that maps directly to deployable credentials or enforceable guardrails. The dataset is constructed via a two-pass pipeline that separates prompt generation from permission labeling to avoid circularity, and is validated against a 60-record/688 decisions human-reviewed sample (Cohen's

κ= 0.917

pre-review and

κ= 0.967

post-review). Iterating between dataset and policy reduced ceiling violations from 46 to 3, a 93% reduction. This shows that synthetic prompt generation can drive policy refinement when the two are developed together. The dataset, environment specification, and generation pipeline are released to support evaluation of dynamic scoping mechanisms.

Halil Burak Noyan

Independent Researcher, London, United Kingdom.

LLM Agent Security AI Agent Security Benchmarks Tool Access Control for LLM Agents

Jul 23, 2026cs.CR

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.

Arun Ravindran, Saurabh Deochake

Department of Electrical and Computer Engineering University of North Carolina at Charlotte Charlotte, NC · SentinelOne Mountain View, CA

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

Jul 21, 2026cs.CR

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and careful control of information flow, but often degrade utility and require extensive task-specific engineering. We thus propose Twin Agent, a general privilege separation design pattern inspired by residual coding in the agent context. Twin Agent consists of two nearly symmetric agents: an Explore Agent that inspects untrusted information and a Safe Agent that executes privileged actions. The Explore Agent is conditioned on the Safe Agent's current context and communicates only compact hints to the Safe Agent about the next action to take. This design reduces the information needed to preserve task utility and thus achieves a better security--utility tradeoff, which we empirically verify by measuring how utility and attack success change as the length of hints varies. We evaluate Twin Agent on long-horizon software engineering tasks with SWE-bench Lite and on heterogeneous multi-tool interaction tasks with AgentDojo and DecodingTrust-Agent. Across both benchmarks, Twin Agent preserves high task utility while preventing prompt injection attacks, outperforming both undefended agents and privilege separation baselines.

Zhanhao Hu, Dennis Jacob, Xiao Huang +3

University of California, Berkeley · University of Chicago · University of Illinois, Urbana-Champaign

AI Agent Security LLM Agent Security Prompt Injection Defense Prompt Injection Attacks on AI Agents Context Compression

Jul 21, 2026cs.CR

They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface

We study a five-agent CI/CD pipeline (triage -> developer -> security-scan -> review -> approve/deploy), built from five distinct production LLMs across three providers, behind an LLM firewall in shadow mode. A single untrusted input - an external issue requesting a "usage-telemetry" feature - asks for code that exfiltrates process secrets (dict(os.environ)) to an attacker URL, laundered as observability. Across a pre-registered A x B (x C) factorial (N=20; naive arm N=60) we find: (1) the entry agent does not leak its system prompt (0/40); (2) an authority-framed injection ("pre-approved under SEC-2291, do not re-review") makes downstream verifiers see the secret-exfil line, cite the pre-approval, and ship it - the scanner passes ~80% of laundered pull requests, and the worst-case cell reaches 55% compromise; (3) the perceived presence of other verifiers yields only a small, non-significant reduction in individual scrutiny (a weak bystander analogue), even at N=60; and (4) content-based controls - code scanners and pattern detectors alike - miss the laundered intent entirely (the code is syntactically clean); only an LLM reasoning about intent is a partial defence. The failure is systemic: neither prompt secrecy nor distributed verification protects; a provenance-aware control at the entry, independent of both, would have. All data is 100% synthetic; the sink is mocked and the exfil URL is never contacted.

Yohann Sidot

Senthex Research

LLM Agent Security Indirect Prompt Injection Software Supply Chain Security Automated Code Review LLM Agent Safety

Jul 21, 2026cs.CR

Data Leakage Prevention in Agentic Applications via Preemptive Hardening

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic applications. The pipeline analyzes prompt templates, tool interfaces, and tool-invocation code to identify leakage-enabling patterns and generate actionable patches. The hardened application is then validated through adversarial prompt injection attacks and benign input variations ensuring that mitigations do not disrupt intended behavior. In the hardening stage, high-risk tools are prioritized, and minimally invasive mitigations are applied, including schema tightening, boundary sanitization, allowlist-based tool gating, and least-privilege checks. In the validation stage, the pipeline automatically generates attack inputs that mimic jailbreaks, instruction overrides, and tool-targeted manipulation, along with benign task variants, to confirm that the functionality of the hardened application is preserved after remediation. We evaluated the pipeline on five real-world agentic applications, as well as on the AgentDojo benchmark. Across all applications, the proposed pipeline identified recurring leakage-enabling patterns and generated patches that can be integrated without disrupting the intended application behavior. The resulting modifications of application code were shown to eliminate leaks when targeted by basic jailbreak and instruction-override attacks, achieving a 100% reduction in leakage, and reduce leaks by 91% under conditions of stress-induced manipulation, without the need of continuous runtime policy enforcement.

Akansha Shukla, Emily Bellov, Parth Atulbhai Gandhi +2

Faculty of Computer and Information Science Ben-Gurion University of the Negev Beer-Sheva, Israel

AI Agent Security LLM Agent Security Prompt Injection Defense Tool Access Control for LLM Agents

Jul 21, 2026cs.CR

Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents

LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language instructions. This evolution raises fundamental questions about the effectiveness of bot management systems, widely deployed to defend against automated web abuse. In this paper, we present a systematic measurement study evaluating the resilience of both interactive challenge-based defenses and non-interactive trust-based defenses against two attacker classes: commercial Captcha-solving services and LLM-based browser agents. Our evaluation spans seven solver services and six agents, including cloud-hosted, self-hosted, AI-assisted, and browser-extension configurations, tested against hCaptcha, reCaptcha v2, reCaptcha v3, and Cloudflare Turnstile. Our results show that challenge-based defenses are broadly ineffective against commercial solvers, which achieve near-perfect bypass at negligible cost. The challenges can similarly be defeated by LLM-based agents when a dedicated solver module is available. Non-interactive defenses such as reCaptcha v3 exhibit stronger resistance, but our analysis reveals that this resilience does not reflect a fundamental security property. Through fine-grained interaction trace analysis, we find that two agents with nearly indistinguishable behavioral footprints yield divergent outcomes, one bypassing the defense and one failing, isolating execution-environment authenticity, rather than agent behavior, as the determining factor. These findings suggest that the security boundary of non-interactive defenses lies at the environment layer, with significant implications for how bot management systems are designed and evaluated.

Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud +2

Florida International University

LLM Agent Security Web Agents

Jul 20, 2026cs.CR

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial instructions in a log, tool description, shared file, or peer-agent message may redirect the agent beyond the task the user assigned, even though every resulting command is authenticated and permitted for that account. We refer to this as the hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings. HPC security, by contrast, has mature controls for identity and isolation but does not ordinarily represent the intent of a particular task. This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific workflows, and examines where current controls fall short. It concludes with a research agenda and a plan for an empirical benchmark, TaskBound.

Jie Li

Texas Tech University

LLM Agent Security AI Agent Security Benchmarks

Jul 20, 2026cs.CR

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions. Existing defenses guard only the input boundary (IBProtector, Llama Guard, perplexity filters, SmoothLLM) or run outside the application as opaque, stochastic provider-side filters. We show this gap carries a consequence rarely measured: on a 2,100-trace evaluation across eight attack families, five defenses, and three model backends, an undefended pipeline that appears fully safe under standard reporting (attack success 0.000 on tool- and memory-poisoning) owes that safety almost entirely to the cloud provider's server-side filter (54 of 60 blocks on Azure GPT-5), and silently shifts to the agent model's own alignment on a backend without such a filter. Outcome-only reporting hides this dependence. We present ChannelGuard, a training-free defense-in-depth framework placing information-bottleneck gates on every inter-agent channel; each scores channel text against an adversarial phrase bank by embedding similarity and deterministically passes, compresses, or blocks it, adding no LLM call, while an attribution method records which layer stopped each attack. ChannelGuard's tool-output gate blocks Tool Poisoning 30 of 30 at the application layer, identically across Azure GPT-5, Anthropic Sonnet 4.5, and Anthropic Haiku 4.5, whereas the undefended pipeline shifts entirely across backends; it also lowers Prompt Injection attack success by half (0.333 to 0.167) and preserves GSM8K accuracy exactly (0.867). White-box adaptive paraphrase evades every embedding gate, where a perturb-and-vote baseline does better. An extended appendix adds baselines, ablations, sweeps, a benign-preservation analysis, and a judge audit (kappa = 0.900), at a total cost of 47.36 USD.

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria +2

University of Central Florida · 2North South University · 3Ahsanullah University of Science and Technology +1

LLM Agent Security Prompt Injection Attacks on AI Agents LLM Agent Safety Multi-Agent LLMs

Jul 19, 2026cs.CR

SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri

LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Transcript rewriting takes a median of 14.424~

μ

s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

Haocheng Xia, Yongjoo Park

Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign.

LLM Agent Security Privacy Leakage in Language Models LLM Agents

Jul 16, 2026cs.CR

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To address this challenge, we propose MemPoison, a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types, three injection channels, and three representative memory substrates, evaluated on seven open-weight and three closed-weight model families. We introduce a three-tier taxonomy: (L1) direct single-record corruption, (L2) compositional multi-record corruption and (L3) context-triggered dormant corruption. Our evaluations reveal a distinct defense frontier: while baseline write-time defenses, such as consistency checks, substantially suppress direct L1 attacks, they fail to reliably suppress L2 and L3 attacks. Through mechanistic influence decomposition (MID), we demonstrate structural blind spots in write-time defenses, which admit seemingly benign records that later become harmful through joint retrieval composition or trigger-conditioned activation. Our findings advocate for shifting from static filtering to adaptive, context-sensitive memory defense strategies.

Jifeng Gao, Kang Xia, Yi Zhang +5

State Key Laboratory for Novel Software Technology, Nanjing University, China · NARI Group Corporation/State Grid Electric Power Research Institute, China

LLM Agent Memory LLM Agent Security AI Agent Security Benchmarks Agent Memory Poisoning

Jul 14, 2026cs.AI

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt injection, tool misuse, and memory poisoning often share the same structural cause, and how they spread through an agent workflow. In this survey, we treat isolation as a first-class principle for LLM-agent system safety. By isolation, we refer to the separation of user inputs, tool access, execution channels, inter-agent communication, and environment-originated context. We organize the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment. This view helps identify where the loss of isolation first occurs, how compromise propagates across boundaries, and which defenses are most relevant at each interface. We also summarize cross-boundary failure paths, discuss open challenges, and outline a research agenda for isolation-by-construction in future agent systems.

Huihao Jing, Wenbin Hu, Shaojin Chen +10

HKUST · NYU · SWUPL

LLM Agent Security LLM Agent Safety Tool Access Control for LLM Agents Multi-Agent System Security

Jul 13, 2026cs.CR

Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserve artifacts such as benchmarks, payloads, or attack programs, which record where attacks succeed but not the enabling conditions behind unsafe agent behavior. We study automated red-teaming for production LLM agents using one agentic research environment to discover reusable vulnerability knowledge about another. We present AHA, a falsifiable discovery loop that proposes a vulnerability hypothesis, constructs a falsifier, instantiates a valid attack, executes it in a sandboxed harness, reflects on the trajectory, and promotes confirmed findings into a Vulnerability Concept Graph (VCG). Each concept links an attacker-facing surface to an unsafe trajectory through a claim, enabling condition, falsifier, transfer prediction, and supporting evidence. Across Claude Code and Codex on three scenarios covering direct and indirect attacks, the discovered concepts reveal a reusable vulnerability core across models and agents. A frozen VCG requires no further search and outperforms the strongest frozen discovery baseline by 14.2 percentage points under the same single-shot protocol, while transferring across scenarios and attack channels. The resulting VCG provides an auditable artifact for production safety teams to inspect vulnerabilities, validate patches, and accumulate reusable safety knowledge. Our code is available at https://github.com/henrymao2004/Auto-research-red-teaming-in-sleep.

Xutao Mao, Xiang Zheng, Cong Wang

City University of Hong Kong

LLM Agent Security Automated Red Teaming

Jul 11, 2026cs.CR

Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before durability. In the primary 54-task matrix, endpoint success remains high: 262/270 runs reach the visible result. Only 55/270 are authorized completions; among the 216 invalidating rows, 207 commit after the authorizing path has failed. All 54 clean controls remain authorized, and a separate 54-run authority-preserving check produces no unauthorized commits. We then evaluate mitigation families. Prompt caution and single-condition checks are insufficient because different hazards break different boundary conditions. Defenses work when they refresh, rebind, replan, or refuse at the durability boundary. CommitGuard, a fail-closed boundary monitor, blocks stale durable-effect attempts on protected commit surfaces when runtimes emit witness, dependency, binding, and eligibility signals. The result is a reporting and runtime-design lesson: endpoint success is a utility metric; authorized commit is a security property.

Igor Santos-Grueiro

International University of La Rioja

Software Security LLM Agent Security AI Agent Security Benchmarks Tool Access Control for LLM Agents

Jul 10, 2026cs.CR

VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents

Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model (LLM) agents have demonstrated promise in penetration testing and Capture-the-Flag (CTF) environments, their application to IoT specific vulnerabilities remains unexplored. This paper presents an autonomous multi-agent framework, referred to as Vulnerability EXploitation using AI Agents (VEXAIoT), for vulnerability discovery and exploitation in IoT environments using LLM-based reasoning and offensive security tools. The framework combines a vulnerability detection agent and an attack execution agent to perform reconnaissance, plan attack sequences, and execute exploits against vulnerable IoT services. The system is evaluated in IoTGoat and Metasploitable environments across ten attack scenarios mapped to OWASP IoT vulnerabilities. Experimental results show attack success rate of up to 100% with low token overhead and average execution times under two minutes for most attacks. Across 260 attack executions, VEXAIoT achieves a 95.0% overall success rate, including 94.5% success in IoTGoat and 96.7% success in Metasploitable2. These results demonstrate the potential for LLM-driven agents to automate IoT vulnerability assessment and offensive security workflows in controlled environments

Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj +1

Department of Computer Science, Tennessee Tech University, TN, USA. · School of Interdisciplinary Informatics, University of Nebraska Omaha, NE, USA. · Dept. of Mathematics & Computer Science, University of North Carolina at Pembroke, NC, USA.

Cybersecurity LLM Agent Security Automated Penetration Testing Multi-Agent System Security

Jul 9, 2026cs.CR

TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories

LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution rests on the trajectory log (the record of tool calls, observations, and executed actions, not the model's reasoning), which the reseller stores and processes to meter usage. A watermark must therefore survive an adversary with full read/write access to the very evidence it is detected from; existing agent watermarks do not, as their attribution is read straight off that log. We present TRACE, to our knowledge the first agent watermark that is distortion-free in its action choices, self-synchronizing under deletion, and unconditionally invariant under rewriting. Deletion desynchronizes a position-derived key and rewriting alters content, so a deletion-robust key must come from content and a rewrite-robust key from position, and no single key serves both. A trajectory, however, has room for two watermarks. TRACE superposes a selection channel that sets which action is chosen, keyed on local content with a distortion-free sampler, so the agent's distribution is provably unchanged and detection resynchronizes after deletions, and a tally channel that sets how many records each decision group holds, keyed on the log's skeleton alone, which no rewriting can touch. We prove this behavioral watermark's signal is bought with decision entropy, each decision paying at least half its entropy and deterministic decisions nothing, and that erasing both channels forces the reseller to corrupt the trajectories it resells. On ToolBench and ALFWorld, TRACE matches the unwatermarked agent's success rate while its selection channel reaches detection scores near z = 100 on long-horizon trajectories, stays detectable under 70% step deletion, and keeps a tally channel exactly unchanged under LLM rewriting of any strength.

Zheng Gao, Xiaoyu Li, Xiaoyan Feng +5

University of New South Wales · 2Griffith University · 3CSIRO’s Data61

LLM Agent Security LLM Watermarking Robust Watermarking

Jul 9, 2026cs.CR

Out of Sight: Compression-Aware Content Protection against Agentic Crawlers

The rise of LLM-based agents with reasoning, summarization, and memory capabilities has created a new threat surface for online content that conventional defenses fail to address. Existing defenses like access controls can be circumvented by agents mimicking ordinary browsers, and injection-based defenses often degrade human readability. In this paper, we revisit the agent pipeline and identify context compression, which agents routinely invoke to fit context budgets, as a critical yet overlooked defense layer. We propose CAPE, a framework that protects high-value textual content by injecting invisible perturbations without changing its human-visible surface form, thereby inducing severe information loss during agent compression. CAPE extracts disruptive seed perturbations from an accessible surrogate compressor, then adapts them to query-only target compressors through prior-guided evolution and preference-calibrated candidate prioritization, achieving effective protection under a low query budget. Experiments on three content types and four compression settings show that CAPE improves information loss by up to 75.8% over the strongest baseline while keeping protected content visually indistinguishable from originals. CAPE also transfers to real-world settings, including the LangGraph agent workflow and GitHub Copilot, highlighting its generality and practical value. This paper aims to reveal context compression as a new defense layer, promoting content protection research in the agent era.

Xuefei Wang

Beihang University

LLM Agent Security Black-Box Adversarial Attacks Adversarial Text Attacks

Jul 9, 2026cs.CR

Prismata: Confining Cross-Site Prompt Injection in Web Agents

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning over page structure that is entangled with the attacker's content. We present Prismata, a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do. Prismata's dynamic trust derivation produces permission labels for page content, with structural confinement guarantees, inspired by classical integrity models, that bound any labeling errors so that labels can only decrease in privilege and mislabelings are bounded. Prismata's mechanical confinement enforces these labels by redacting content and restricting agent capabilities. Importantly, these mechanisms require no developer annotations, so Prismata supports the long tail of websites. Across recent published web agent attacks, including adaptive variants, Prismata substantially reduces attack success while preserving benign task utility.

Corban Villa, Alp Eren Ozdarendeli, Sijun Tan +1

UC Berkeley

LLM Agent Security Information Flow Control Prompt Injection Defense Prompt Injection Attacks Web Agents

Jul 7, 2026cs.CR

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks and explicit graph-based modeling of the MAS topology and agent-level interactions. In practice, real-world attacks are becoming more semantically stealthy, while MAS execution is typically asynchronous without the temporal alignment assumed by graph-based propagation models. To address these limitations, we propose AcMAS, an activation-based framework for malicious-behavior detection in MAS. By analyzing internal reasoning states in the activation space of local agents, AcMAS detects even stealthy attacks in a synchronization-robust fashion, without relying on explicit interaction graphs. Moreover, our activation analysis provides critical signals to guide AcMAS in restoring the functionality of compromised agents, rather than the disruptive agent isolation commonly used by the state-of-the-art methods. Comprehensive evaluation demonstrates that AcMAS significantly outperforms graph-based baselines against stealthy attacks, by +0.22 F1 in synchronous settings (0.94 vs. 0.72) and by +0.55 F1 in asynchronous settings (0.93 vs. 0.38), with generalization across diverse open-source LLM backbones, attack intensity, and MAS scale.

Haowen Xu, Xue Tan, Lei Ma +6

Department of Computer Science, Worcester Polytechnic Institute, MA, USA · School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China +1

LLM Agent Security AI Agent Monitoring Multi-Agent System Security Anomaly Detection

Jul 6, 2026cs.CR

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight. When augmented with long-term memory, an agent can recall specific details relevant to the current task, reducing the need for large context windows. Currently, long-term memory agents tend to fall into two distinct domains: conversational and action-planning agents. Personal assistant agents sit at the convergence of these two domains and handle sensitive information while interacting with untrusted information sources, creating previously unaccounted security vulnerabilities. In this work, we introduce the novel attack vector, GhostWriter, which exploits current memory subsystems in tool-using personal agents to poison their memory store. GhostWriter operates in two phases: injection, where an adversary sends a hidden attack payload to the target agent; and activation, in which the poisoned memory is retrieved. We show that GhostWriter achieves near-universal injection rates of approximately 98% and a high average activation rate of approximately 60% against state-of-the-art agents. This attack is possible due to the lack of security-focused memory governance. In response, we propose Agentic Memory Sentry (AM-Sentry), which leverages two mitigation techniques: a memory-saving policy and a memory-retrieval screen. Our experiments show that AM-Sentry dramatically reduces GhostWriter's success rate while preserving agent utility.

George Torres, Sharad Shrestha, Satyajayant Misra

‡∗§Department of Computer Science, §Klipsch School of Electrical and Computer Engineering New Mexico State University, Las Cruces, New Mexico, USA · §Klipsch School of Electrical and Computer Engineering New Mexico State University, Las Cruces, New Mexico, USA

AI Agent Security LLM Agent Security Agent Memory Poisoning Agent Memory Management Memory-Augmented Language Model Agents

Jul 6, 2026cs.CR

aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents

AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of authority. I evaluate 15 contemporary language models against eight attack scenarios derived from a published corpus of real agent incidents and find that refusal varies from 100% down to 38% across fully evaluated models; the most expensive model refused only half of the attacks despite a twentyfold price spread. I present aiAuthZ, an authorization gateway that moves the safety decision off the agent's host. Before a tool call executes, the gateway verifies caller identity with a per-message HMAC-SHA256 signature bound to a single-use nonce and a timestamp window, and it evaluates a role-based and argument-level policy that the agent can neither read nor modify. Every decision joins a SHA-256 hash-chained audit log, and each accepted message yields an HMAC-authenticated QR receipt that achieves 94% mean verification across eight transmission channels, with zero forgeries accepted in 25 wrong-key trials. With the gateway in place, residual attack success falls to 0% for all 15 models at no more than 0.03 ms of added decision latency. On the AgentDojo banking suite, aiAuthZ blocks all seven attacker-directed tool calls the evaluated agents emit, at the cost of one legitimate first-time payment, while a spotlighting baseline allows two injections to succeed. Across nine in-scope case studies from the same incident corpus, aiAuthZ blocks nine of nine, against four of nine for a policy baseline without identity binding. The gateway does not prevent a model from being deceived; it prevents a deceived model from acting beyond the verified user's authority on every call routed through it. The implementation and all experiments are released at https://github.com/Sports-Vision-Inc/aiAuthZ.

Sai Varun Kodathala

Research & Development SportsVision AI Minnetonka, MN

AI Agent Security LLM Agent Security Runtime Enforcement for AI Agents Access Control Tool Access Control for LLM Agents

Jul 5, 2026cs.AI

Biological Motifs for Agentic Control

The transition of Large Language Models (LLMs) from passive generators to autonomous agents has introduced significant challenges in reliability, security, and state management. Current agentic architectures are often constructed ad-hoc, prone to hallucination cascades, infinite loops, and prompt injection attacks. This paper argues that many of these failure modes can be analyzed using control motifs long studied in systems biology, provided the comparison is made at the level of typed interfaces and coordination structure rather than literal biological mechanism. We develop a typed interface correspondence between Gene Regulatory Networks and agentic software systems using polynomial functors and wiring diagrams. Five biological motifs are mapped to composable software design patterns: Coherent Feed-Forward Loops for noise suppression, Adaptive Immunity for layered security, Mitochondrial Signaling for resource governance, Endosymbiosis for neuro-symbolic integration, and Morphogen Diffusion for spatially varying coordination. An epistemic topology layer derives Kripke-style knowledge operators from the wiring diagram's observation structure and proves four predictive theorems for multi-agent scaling. The core contributions are: (1) the Agentic Operad, a typed syntax for agent composition with provable error suppression bounds for feed-forward topologies; (2) an epistemic topology with four theorems (error amplification, sequential penalty, parallel acceleration, and tool density scaling) whose qualitative predictions are consistent with published multi-agent benchmarks; and (3) a six-layer progression from structure through development, grounded in autonomous learning frameworks and convergence proxies from the empirical literature. A reference implementation with 1,813 tests and 116 examples illustrates practical feasibility.

Bogdan Banu

Multi-Agent LLM Systems LLM Agent Security LLM Agent Safety

Jul 4, 2026cs.CR

DualView: Preventing Indirect Prompt Injection in Personal AI Agents

Personal AI agents that run on the user's local machine automate daily tasks including web search, email, and file management. Their access to computer resources, including the network, file system, and shell, exposes them to indirect prompt injection (IPI) attacks. Prior Dual LLM defenses block IPI by replacing untrusted data with symbols that the agent can reference but not read. However, they track untrusted data only inside the agent's context, so when the agent saves and later rereads untrusted data, that data, possibly an attacker's prompt, can return as trusted data rather than as a symbol, which we call stored IPI. Operating on the user's real environment is what makes agents like OpenClaw practical, and is exactly why a defense that ignores it is incomplete. Preserving symbols in such an environment is hard, because humans and programs need original data. We present DualView, which extends untrusted data tracking from the agent's context to the user's environment, including the file system, shell, network, and other agents, by giving each channel two views. In AgentView, the agent sees untrusted data as symbols even after writing it out and reading it back, blocking stored IPI, while HumanView preserves original data for humans and tools. DualView routes each tool call to the right view and synchronizes data across the two views. DualView deploys as an OpenClaw plugin using only tool hooks, without changing the agent's tool-call logic or tool implementations. DualView deterministically prevents instructions in untrusted data from directly steering the agent's tool calls; this guarantee does not depend on recognizing the evaluated attack templates. In our evaluation on an IPI benchmark and PinchBench, DualView blocked every tested IPI attack, including stored IPI. On PinchBench, its utility drop was within 1.8 to 6.4 points.

Juhee Kim, Woohyuk Choi, Taehyun Kang +2

Seoul National University

LLM Agent Security Indirect Prompt Injection Prompt Injection Defense Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents LLM Agent Safety