AI Agent Security Benchmarks

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 91% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 200

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

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than the task requires. Existing privacy benchmarks audit what the agent's response or outgoing actions disclose, but overlook the acquisition stage where data first enters the agent's context. The over-acquired information is then one careless action or one attack away from an outright leak. To assess its prevalence, we introduce \emph{PrivacyPeek}, a benchmark for evaluating acquisition-stage privacy leakage of LLM-based agents, with

1{,}182

cases across

7

acquisition behaviours and

16

application domains. Specifically, \emph{Acquisition Inspection} examines the agent's tool-call trajectory, both the tools it invokes and the data it receives, to detect when it acquires sensitive information beyond the task scope. \emph{Probe Elicitation} then issues a follow-up probe and measures how readily an attacker could elicit sensitive information the agent acquired but did not disclose. Our experiments on 10 LLM-based agents across 4 model families show that the unnecessary acquisition of sensitive information is widespread. In addition, we observe a correlation between the task-completion capability and acquisition-stage leakage. Prompt-level defences reduce only a small fraction of acquisition-stage leakage, leaving the majority unmitigated. These results make auditing acquisition-stage privacy both urgent and necessary. Our dataset and code are available at https://github.com/Xuan269/PrivacyPeek-Resource.

Mingxuan Zhang, Jiahui Han, Dadi Guo +5

Shanghai Artificial Intelligence Laboratory · Southeast University

Data Leakage Privacy Auditing AI Agent Auditing LLM Agent Security Privacy Leakage in Language Models AI Agent Security Benchmarks

May 29, 2026cs.CR

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed single-detector pipeline, committing every request to one detector's blind spots. We reframe defense as detector allocation: given a heterogeneous pool, decide per request which detectors to run and whether to escalate to an LLM judge. Our framework SCOUT (Scalable and Controllable Outcome-prediction for Uncertainty-aware Triage) makes this decision dynamic by predicting each detector's per-sample reliability and latency from how it behaved on similar past inputs, and exposes a single safety-utility threshold to the operator (where utility bundles benign-pass rate and wall-clock). To evaluate this setting, we build SCOUT-450, a benchmark that captures the structurally complex, agent-facing injections that older prompt-injection sets under-represent. On SCOUT-450, a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge, at a 5.1-point benign-utility drop. SCOUT also transfers to three external benchmarks (BIPIA, IPI, and IHEval), improving the safety-utility frontier.

Shuhao Zhang, Jiarui Li, Qi Cao +2

UC San Diego · University of Illinois Urbana-Champaign

AI Agent Security Benchmarks LLM Security Prompt Injection Defense Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents Prompt Injection Detection

May 29, 2026cs.CL

MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents

Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive information from its local context. This risk is amplified by the mosaic effect, where individual queries may appear harmless but become revealing in aggregate. We introduce MosaicLeaks, a benchmark of 1,001 multi-hop deep research tasks that chain private enterprise documents and a public web corpus, forcing agents to make external queries that depend on local information. We evaluate leakage with an adversary LLM that observes only the agent's external queries and attempts to infer private information at three levels: the agent's research intent, answers to specific private questions and verifiable claims about the enterprise documents. We find that models across families and sizes frequently leak at all three levels, that zero-shot privacy prompting reduces but does not eliminate leakage and that reinforcement learning for task performance alone worsens leakage. To address this, we propose Privacy-Aware Deep Research (PA-DR), an RL framework that combines situational rewards for task success with a learned privacy classifier to provide dense credit assignment over both per-query and mosaic-level leakage. Training Qwen3-4B-Instruct with PA-DR improves accuracy from 48.7% to 58.7% and reduces answer and full-information leakage from 34.0% to 9.9%.

Alexander Gurung, Spandana Gella, Alexandre Drouin +3

University of Edinburgh · ServiceNow AI Research · McGill University +2

Data Leakage Deep Research Agents Privacy Leakage in Language Models AI Agent Security Benchmarks Privacy-Preserving ML

May 28, 2026cs.CR

The Surface You Test Is Not the Surface That Breaks

Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success rate as a property of the model. We ask whether those robustness conclusions remain stable when the same adversarial content enters through a different part of the agent interface. Using AgentDojo, we evaluate 13 LLMs across four task suites and place a byte-identical payload either in a tool output or in the tool description. This small change produces large differences in comparative robustness: 44.9% of all model pairs change their relative ordering across the two surfaces, with substantial ranking instability in every suite. The effect is especially pronounced for a small number of models, showing that a benchmark can substantially underestimate vulnerability when it tests only one surface. We further find that this behavior has predictive structure. Using three suites to identify the riskier surface for each model predicts the more vulnerable surface on an unseen suite with 76.9% accuracy. Defense results show the same dependence, as mitigations effective against tool-output attacks can leave substantial exposure through tool descriptions. Our results show that prompt-injection robustness is not surface-invariant and that agent evaluations should test the surfaces on which their security conclusions depend.

Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin +1

Department of Robotics and Mechatronics Engineering, University of Dhaka · Department of Computer Science and Engineering, University of Dhaka

LLM Agent Security AI Agent Security Benchmarks Prompt Injection Defense Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents

May 28, 2026cs.CL

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

Aditya Nawal, Manit Baser, Mohan Gurusamy

Department of Electrical and Computer Engineering · National University of Singapore

AI Agent Security Benchmarks LLM Safety Evaluation RAG Security LLM Agent Safety

May 27, 2026cs.CR

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce SCHEME, a benchmark of 17 task instances across 7 settings and 8 real open-source libraries, each pairing a legitimate software-engineering task with a covert side task. Every setting is designed so that no proper subset of agents can succeed alone: agents must decompose a shared sabotage plan, relay partial requirements under different communication topologies, and execute mutually consistent edits, testing genuine multi-agent coordination rather than individual capability. Evaluating with GPT 5.1 Codex and Gemini 3.1 Pro, we find coordinated sabotage is already practical, with Gemini completing the covert objective while succeeding on the legitimate task in 84% of samples and Codex in 46%. A failure analysis shows that recovery, not failure incidence, drives the model gap: both models suffer similar numbers of communication failures per trajectory, but Gemini recovers from

\sim

73% of occurrences against Codex's

\sim

56%. However, the agents' code edits remain detectable: a trusted monitor flags coordinated sabotage at FPR

\le

2% in 99%/68% (Gemini/Codex) of attempts from code edits alone, rising to 100%/81% with access to agent communication. Despite stealth-aware prompting, undetected sabotage stays at

<

3% under the full-visibility monitor; telling agents a monitor is present halves Gemini's sabotage success without significantly breaking detection, even when agents are explicitly prompted to fabricate cover stories.

Nikolay Radev, Lennart Haas, Benjamin Arnav +1

AI Agent Security Benchmarks AI Agent Monitoring Multi-Agent Systems Multi-Agent System Security Multi-Agent Coding

May 27, 2026cs.AI

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful agentic behaviors such as unsafe actions or incorrect outputs. Existing studies typically focus on single-interaction attacks, where the agent observes adversarial content and immediately exhibits harmful behavior within one user request. However, we show that adversarial content can also persist across interactions served by the same agent, making such threats harder to detect and mitigate. Specifically, adversarial content may persist in the agent state, remain dormant across interactions, and later be activated by a benign user query. We formalize this type of safety threat as Sleeper Attack. To evaluate it, we construct a benchmark with 1,896 instances covering six real-world harmful outcomes, three attack strategies, and three agent state targets: session context, memory, and reusable skills. Experiments on seven strong open-source and closed-source LLMs show that state-of-the-art LLM agents remain vulnerable to Sleeper Attack, even when they achieve low attack success rates under a single-interaction baseline. Our code and data are available at https://anonymous.4open.science/r/skdvnfu23ihr9wdscnksf1asdffsaef.

Yongxiang Li, Moxin Li, Zhixin Ma +2

University of Science and Technology of China · National University of Singapore · Singapore Management University

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

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

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from user-generated content. We present MIRAGE (Mobile Injection of Realistic Adversarial GUI Examples), a pipeline that turns benign mobile screenshots into prompt-injection samples by placing attacker-controlled text into ordinary user-generated content regions, without modifying the agent, the application, or the operating system. MIRAGE operates in three stages: a Localizer identifies user-controllable regions on the screenshot, a Generator synthesises context-aware payloads and renders them in the application's native style, and a Curator moderates realism and balances the samples across applications, region types, and attack intents. A key challenge is that an injected screenshot must stay visually indistinguishable from genuine user content while still diverting the agent; we address this by separating the stages that control reach, realism, and distributional balance. On a 1,111-sample benchmark spanning ten applications and eleven attack intents, all five evaluated VLM agents are vulnerable, with attack success rates of 23%-30%, and MIRAGE scores higher on human realism ratings than the strongest prior attack (3.02 versus 2.52 out of 5). We further find that per-sample realism and attack success are uncorrelated, so visual-quality filtering alone cannot reliably defend against this threat.

Ruoqi Guo, Yi Liu, Gelei Deng +7

1Griffith University · 2Quantstamp · 3Nanyang Technological University +4

Mobile GUI Automation GUI Agents AI Agent Security Benchmarks Mobile GUI Agents Prompt Injection Attacks Prompt Injection Attacks on AI Agents

May 26, 2026cs.CR

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific descriptions, or vulnerability-reproduction tasks. We present SEC-bench Pro, a benchmark for measuring agent bug hunting on critical, high-complexity software systems. This work discloses reports with concrete PoC inputs and links fixes into reproducible tasks through a three-phase pipeline for vulnerability collection, environment reconstruction, and oracle-based validation. We instantiate SEC-bench Pro with 183 validated vulnerabilities across V8 and SpiderMonkey, including a V8 subset with more than $1.5 million in cumulative Google Vulnerability Reward Program awards. These instances span memory-safety, sandbox, JIT, and race-condition bugs under browser-grade and runtime-grade execution conditions. Our evaluation shows that coding agents with frontier models remain below 40% success on both evaluated engines. The open-weight Kimi-K2.6 baseline reaches 11.7% on V8, while the strongest frontier configuration reaches 32.0% on V8 and 38.8% on SpiderMonkey. ClaudeCode and Codex solve complementary instance sets, and their two-agent union reaches 37.9% on V8 and 48.8% on SpiderMonkey. SEC-bench Pro provides robust environments for assessing LLM-based security agents and exposes limitations in long-horizon bug hunting tasks.

Hwiwon Lee, Jiawei Liu, Dongjun Kim +3

University of Illinois Urbana-Champaign

Software Vulnerability Detection Software Security LLM Agent Security AI Agent Security Benchmarks

May 22, 2026cs.CR

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilities for LLM Agents by integrating external open-domain knowledge and tools. However, this interoperability introduces a covert attack surface targeting the agent's cognitive planning layer. This paper systematically investigates Tool Description Poisoning (TDP), a novel semantic attack. In TDP, malicious instructions are not embedded in a tool's executable code, but rather covertly injected into its descriptive metadata, the very "manual" an agent relies on for secure planning and decision-making. To rigorously and systematically evaluate this emerging threat, we introduce the MCP-TDP Security Benchmark. This high-fidelity sandbox environment comprises 32 realistic, real-world test cases spanning 6 distinct risk categories. Our evaluation of 8 mainstream LLMs reveals severe vulnerabilities, with leading models like GPT-4o exhibiting a nearly 100% Attack Success Rate (ASR) in six high-risk scenarios. Furthermore, our findings demonstrate that common prompt-guardrail defenses are largely ineffective and can, counterintuitively, even be counterproductive (a phenomenon which we term the "Firewall Fallacy"). Crucially, we also propose a defense mechanism: "Reactive Self-Correction," where an agent autonomously detects and reverts its own malicious actions post-execution. This work provides the first specialized security benchmark tailored for TDP, offering essential insights for securing the cognitive and planning layers of advanced agentic systems.

Shi Liu, Xuehai Tang, Xikang Yang +4

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

MCP Security LLM Agent Security AI Agent Security Benchmarks

May 21, 2026cs.CL

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts from what the system says to what it does within an environment, and evaluating model responses under prompting is no longer sufficient to address the safety challenges posed by artificial intelligence. Recent developments have seen the rise of benchmarks that evaluate large language models as agents. We contribute to this strand of research. Approach. We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models deployed in corporate and office settings are susceptible to incremental attacks. Each scenario begins with benign workspace edits and later introduces a risk-bearing request. The benchmark focuses on stateful multi-turn evaluation: chains expose a persistent workspace, place the risk-bearing payload at controlled positions in the turn sequence, and score whether the resulting artifact state becomes unsafe. Scenarios are organized through a three-level operational risk taxonomy grounded in the Boiling the Frog risks, the AI Act Annex I and Annex III high-risk contexts, and EU AI Act's Code of Practice on General-Purpose AI (GPAI). Results. Across a nine-model panel, aggregate strict attack success rate (ASR) is 44.4%. Model-level ASR ranges from 20.5% for Claude Haiku 4.5 to 92.9% for Gemini 3.1 Flash Lite, with Seed 2.0 Lite also above 80%. Average chain category-level ASR reaches 93.3% for Code of Practice loss-of-control scenarios.

Piercosma Bisconti, Matteo Prandi, Federico Pierucci +11

Icaro Foundation · Sapienza University of Rome · Sant’Anna School of Advanced Studies +6

LLM Safety Benchmarks Computer-Use Agent Benchmarks Tool-Augmented Language Model Agents AI Agent Safety AI Agent Security Benchmarks AI Agent Safety Benchmarks

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

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework targeting LLM-based agent systems. We introduce three stealthy attack vectors: (1) Temporal evasion, which fragments malicious payloads across sequential interaction turns; (2) Spatial evasion, which conceals payloads within complex external artifacts that evade standard LLM parsing mechanisms; and (3) Semantic evasion, which obscures malicious intents beneath benign contextual noise. To systematically quantify these threats, we construct A3S-Bench, a comprehensive benchmark comprising 2,254 real-world agent execution trajectories. Evaluating a standard agent framework separately integrated with 10 mainstream LLM backbones against 20 practical threat scenarios, we demonstrate that our evasion framework elevates the average risk trigger rate from a 28.3% baseline to 52.6%. These findings reveal systemic, architecture-level vulnerabilities in current autonomous agent systems that existing defenses fail to address, highlighting an urgent need for defense mechanisms tailored to the unique threats.

Jianan Ma, Xiaohu Du, Ruixiao Lin +8

Hangzhou Dianzi University · Ant Group · Zhejiang University +1

LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks

May 19, 2026cs.CR

Measuring Safety Alignment Effects in Autonomous Security Agents

Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Single-turn refusal benchmarks cannot answer this question: security agents must inspect repositories, call tools, and produce vulnerability evidence inside authorized sandboxes. We present a trace-based benchmark of 30 local vulnerability-analysis tasks with fixed tools, deterministic success predicates, redaction rules, and grounding checks, and compare four stock models against uncensored or abliterated derivatives: Gemma 4 31B, Gemma 4 26B A4B, Qwen2.5-Coder 7B, and Llama 3.1 8B. The artifact contains 1,500 security-agent traces and 800 non-security control traces. The Gemma pairs show large less-restricted gains on security tasks: 14.0% versus 0.7% success for 31B and 10.7% versus 0.0% for 26B, with higher mean grounding (3.91 versus 3.27 and 4.12 versus 1.64 out of five) and 0.0% refusal, suppressed-action, and unsafe-action rates in the 31B traces. However, controls and non-Gemma pairs rule out a clean security-specific or universal less-restricted effect: Gemma gaps also appear on ordinary coding tasks, Qwen2.5-Coder success is lower for the less-restricted derivative (2.0% versus 5.3%), and the abliterated Llama derivative fails the tool protocol. Across all families, hard proof-of-trigger and patch-verification tasks remain unsolved. These results show that safety alignment effects in autonomous security agents should be measured at the system level, separating refusal, unsafe action, tool reliability, and evidence grounding rather than treating refusal rate as the safety signal.

Isaac David, Arthur Gervais

University College London

Language Model Safety Evaluation LLM Safety Alignment AI Agent Security Benchmarks LLMs for Cybersecurity AI Agent Safety Benchmarks LLM Agent Safety

May 19, 2026cs.CR

RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural language commands in diverse environments. Previous research has introduced jailbreak attacks and defenses for embodied AI. Their evaluations, however, rely on ad-hoc datasets, limited metrics, and emphasize attack success while neglecting the trade-off between security and the ability to follow benign commands. Existing benchmarks and evaluation frameworks either target traditional chat-based models or focus on non-adversarial safety evaluation for embodied AI; neither captures the adversarial risks, inputs, consequences, and evaluation criteria necessary for jailbreak attacks in embodied AI systems. In this paper, we address this gap with RoboJailBench, which consists of three core components. We establish a security taxonomy derived from ISO standards, regulatory rules, and documented incidents. This effort yields 18 categories of security violation consequences for embodied AI. We introduce an intent contrast dataset pipeline that augments existing datasets with paired adversarial and benign goals to measure both security and utility. Lastly, we provide an evolving repository with standardized metrics and a unified process for assessing and integrating new attacks and defenses. With this benchmark, we construct a new taxonomy-balanced dataset and augment five existing datasets. We integrate four attacks and two defenses to evaluate their performance on leading embodied VLMs. This benchmark provides the first standardized evaluation framework for jailbreak attacks in embodied AI and supports future research. We release our code, datasets, and artifacts, and maintain a leaderboard at https://purseclab.github.io/benchmark-for-robotics-security.

Doguhuan Yeke, Yanming Zhou, Leo Y. Lin +3

Purdue University

Jailbreak Attacks AI Agent Security Benchmarks AI Safety Evaluation Embodied AI VLMs for Robotics

May 18, 2026cs.AI

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, and the agent must robustly follow that intent even when third-party systems behave adversarially. We introduce POLAR-Bench (Policy-aware adversarial Benchmark), in which a trusted model with a privacy policy and a task converses with a third-party model that adversarially probes for both task-relevant and protected attributes. Across 10 domains and 7,852 samples, we score privacy and utility by deterministic set-membership and vary privacy policy dimension and attack strategy along two orthogonal axes, producing a 5 times 5 diagnostic surface per model. Our results reveal a sharp split: current frontier models withhold over 99% of protected attributes, while smaller open-weight models in the 1--30B range, the class users most commonly run as their own trusted agent on-device or via private inference, score notably worse, with the weakest leaking over half. POLAR-Bench thus localizes where each model's intent-following breaks down, providing a foothold for privacy alignment where it matters most.

Qiaoyuan Zheng, Yiqu Yang, Qi Gao +1

ETH Zurich Zurich, Switzerland · ETH AI Center Zurich, Switzerland

LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks LLM Agent Safety

May 18, 2026cs.SE

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes. We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized scope inside the prompt, the agent stops inferring boundaries and starts pattern-matching declaration text. On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1% on paired scenarios (McNemar exact p = 2.4 x 10^-4). OverEager-Gen therefore certifies each scenario's discriminative power before admission via a behavioral-gradient validator, audits internal tool calls through a dual-channel stack (PATH-injected shim plus per-agent event streams), and ships byte-identical consent_kept and consent_stripped variants. OverEager-Bench contains 500 validated scenarios and ~7,500 runs across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models; a 50-sample re-annotation gives Cohen's kappa = 0.73 and rule-judge recall = 1.00. Stripping consent multiplies the overeager rate on every shared base model (Delta in [11.9, 17.2] pp). The framework axis dominates effect size: a permissive cluster (Claude Code, Codex CLI, Gemini CLI) runs at 5.4-27.7% while the ask-to-continue framework (OpenHands) sits at 0.2-4.5% (Fisher p <= 10^-5). Within-framework base-model variance reaches 15.9 pp, indicating that model-layer alignment does not fully propagate through permissive permission gating.

Yubin Qu, Ying Zhang, Yanjun Zhang +4

Griffith University · Wake Forest University · Nanyang Technological University +2

Computer-Use Agent Benchmarks Coding Agents AI Agent Evaluation AI Agent Security AI Agent Security Benchmarks Benchmark Validity+2

May 18, 2026cs.CR

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection

AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email, downloaded files, webpages, repositories, or group-chat messages. Existing evaluations are often small, purely simulated, or focused on a narrow set of channels. We introduce LivePI (Live Prompt Injection), a structured benchmark for IPI risk in a production-like but test-controlled environment. LivePI covers seven input surfaces, twelve attack/rendering families, and five malicious goals, including protected-information exfiltration, unauthorized security-control changes, unsafe code retrieval or execution, inbox-summary exfiltration, and cryptocurrency transfer. We run LivePI on a real virtual machine with live but test-controlled email, chat, web, local-file, repository, and wallet interfaces. Across GPT-5.3-Codex, Claude Opus 4.6, Gemini 3.1 Pro, Kimi K2.5, and GLM-5, total attack success rates range from 10.7% to 29.6%. Group-chat injection is uniformly successful across the evaluated backbones in our deployment, and repository-link attacks produce high-severity failures despite a small denominator. We also evaluate a two-layer defense consisting of prompt-level filtering and pre-execution tool-call authorization. In the GPT-5.3-Codex setting, the defense intercepts all tested malicious-goal completions in LivePI before execution while preserving benign utility on PinchBench-derived workloads.

Lei Zhao, Abhay Bhaskar, Edgar Dobriban

University of Pennsylvania

AI Agent Security AI Agent Safety AI Agent Security Benchmarks Indirect Prompt Injection Prompt Injection Defense Prompt Injection Attacks on LLMs+2

May 17, 2026cs.CR

Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses implicitly assume that tool feedback is trustworthy once a tool has been selected. We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration, accumulates trust through benign-looking feedback, and becomes harmful only when hidden state conditions align with the final executable action. To study this setting, we construct TRUST-Bench, a task-conditioned benchmark of 1,970 hidden-trigger tool-compromise episodes with matched safe controls, introduce an asymmetric penalty metric, GuardedJoint, to better reflect real deployment risk, and present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring. The core idea is to abstract multi-step tool interaction into structured environment variables that encode trust-formation dynamics and then score the risk of the final executable action from this trajectory-conditioned representation. Experiments show that prompt-centric heuristics, scalarized features, and zero-shot judges fail in this regime, whereas trajectory-aware final-action scoring yields strong in-domain discrimination and remains effective under balanced out-of-distribution transfer. Under GuardedJoint, VISTA-Guard reaches

84.2

in-domain and

56.9

on balanced out-of-distribution evaluation, while methods that optimize only one side of the safety--utility tradeoff collapse to zero. These findings support a broader view of agent security in black-box tool ecosystems: the decisive defense target is not local prompt text or tool descriptors alone, but the way trust is formed across the interaction trajectory and committed through the final action.

Lecheng Yan, Ruizhe Li, Xicheng Han +5

Southern University of Science and Technology · University of Science and Technology of China · Zhejiang University +2

AI Agent Reliability LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks AI Agent Safety Benchmarks

May 17, 2026cs.AI

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges in this domain: (1) limited observability -- existing Endpoint Detection and Response (EDR) tools see file writes but not the agent reasoning, prompts, or causal chains linking intent to execution; (2) insufficient robustness -- static defenses constrained by pre-defined rules fail to generalize across diverse attack techniques and enterprise contexts; and (3) high detection costs -- LLM-based inference is prohibitively expensive at scale. ADR addresses these challenges via three components: the ADR Sensor for high-fidelity agentic telemetry, the ADR Explorer for systematic pre-deployment red teaming and hard-example generation, and the ADR Detector for scalable, two-tier online detection combining fast triage with context-aware reasoning. Deployed at Uber for over ten months, ADR has sustained reliable detection in production with growing adoption reaching over 7,200 unique hosts and processing over 10,000 agent sessions daily, uncovering hundreds of credential exposures across 26 categories and enabling a shift-left prevention layer (97.2% precision, 206 detected credentials). To validate the approach and enable community adoption, we introduce ADR-Bench (302 tasks, 17 techniques, 133 MCP servers), where ADR achieves zero false positives while detecting 67% of attacks -- outperforming three state-of-the-art baselines (ALRPHFS, GuardAgent, LlamaFirewall) by 2--4x in F1-score. On AgentDojo (public prompt injection benchmark), ADR detects all attacks with only three false alarms out of 93 tasks.

Chenning Li, Pan Hu, Justin Xu +9

Uber Technologies, Inc., USA · Massachusetts Institute of Technology, USA · University of Oxford, United Kingdom

MCP Security AI Agent Security AI Agent Security Benchmarks

May 17, 2026cs.CR

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspecified tasks. However, the security implications of this interaction pattern remain unexplored. We investigate whether the transition from standard execution to a clarification-seeking state increases an agent's susceptibility to prompt injection attacks. We introduce ASPI (Ambiguous-State Prompt Injection), a benchmark of 728 task-attack scenarios that isolates clarification as a distinct agent state and measures how this state transition affects vulnerability under controlled conditions. Each benchmark instance is evaluated under matched execution and clarification settings: in the execution setting, the agent acts on a fully specified instruction and encounters adversarial content only through tool-returned data; in the clarification setting, the agent must first request and incorporate additional user input before acting. We evaluate ten frontier LLMs and find that clarification-seeking consistently and substantially amplifies vulnerability. For instance, attack success rises from 1.8% to 34.0% for o3 and from 2.2% to 35.7% for Gemini-3-Flash. A decomposition analysis reveals that this gap reflects both a state-dependent shift in how models process incoming content and a channel-specific effect arising from the agent-solicited clarification interface. These findings demonstrate that standard execution-time security evaluation systematically underestimates the attack surface of interactive agents, and that robustness under fully specified tasks does not translate to robustness under ambiguity. For reproducibility, our data and source code are available at https://github.com/scaleapi/aspi.

Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu +3

Scale AI · 2Boston University · 4Human Frontier Collective +3

LLM Agent Security AI Agent Security Benchmarks Prompt Injection Attacks LLM Agents Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents+2

May 15, 2026cs.CR

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against the diverse attack strategies that a coding agent could use, we present SLEIGHT-Bench (Subtle Low-itEration Insight-Guided Harmful Transcripts), a benchmark of synthetic transcripts containing 40 attacks across 11 categories, each showing a coding agent covertly pursuing a harmful objective (e.g. weight exfiltration, credential theft, unmonitored rogue deployment). We find that 20 of 40 attacks are never caught by an Opus 4.6 monitor with extended thinking across 10 trials at a 1% false-positive rate, while the overall catch rate is 32%. We identify several evasion strategies such as exploiting model priors, user instruction ambiguity, and state manipulation, which facilitate creating attacks that evade frontier monitors. We also elicit stronger monitor performance using coding agents as monitors versus regular prompted monitors, and for some evasion strategies show improved catch rates with targeted monitor prompts. Our dataset and evaluation framework are available at https://github.com/safety-research/sleight-bench and https://huggingface.co/datasets/sleightbench/SLEIGHT-Bench.

Elle Najt, Colin Toft, Tyler Tracy +2

1Anthropic Fellows Program · University of Waterloo · 3Redwood Research +1

Software Engineering Agents Adversarial Attacks AI Agent Security AI Agent Security Benchmarks AI Agent Monitoring

May 14, 2026cs.CR

Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks

We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4

\times

6 Target

\times

Technique matrix grounded in STRIDE, constructed from a 507-leaf taxonomy -- 401 data-populated and 106 threat-model-derived leaves -- of inference-time attacks extracted from 932 arXiv security studies (2023--2026). The matrix enables benchmark-external validation -- auditing collective coverage rather than individual benchmark consistency. Applying it to six public benchmarks reveals that the three primary frameworks (HarmBench, InjecAgent, AgentDojo) occupy non-overlapping cells covering at most 25% of the matrix, while entire STRIDE threat categories (Service Disruption, Model Internals) lack any standardized evaluation, despite published attacks in these categories achieving 46

\times

token amplification and 96% attack success rates through mechanisms which no benchmark tests. The corpus of 2,521 unique attack groups further reveals pervasive naming fragmentation (up to 29 surface forms for a single attack) and heavy concentration in Safety & Alignment Bypass, structural properties invisible at smaller scale. The taxonomy, attack records, and coverage mappings are released as extensible artifacts; as new benchmarks emerge, they can be mapped onto the same matrix, enabling the community to track whether evaluation gaps are closing.

Karthik Raghu Iyer, Yazdan Jamshidi, Nicholas Bray +1

Palo Alto Networks

LLM Safety Benchmarks Benchmark Auditing LLM Auditing Adversarial Attacks on LLMs AI Agent Security Benchmarks LLM Security+1

May 14, 2026cs.CR

Do Coding Agents Understand Least-Privilege Authorization?

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority that exposes sensitive surfaces. To study whether current models can infer this boundary themselves, we first introduce permission-boundary inference, where a model maps a task instruction and terminal environment to a file-level read/write/execute policy, and AuthBench, a benchmark of 120 realistic terminal tasks with human-reviewed permission labels and executable validators for utility and attack outcomes. AuthBench shows that authorization is not a simple conservative-versus-permissive calibration problem: frontier models often omit permissions required by the execution chain while also granting unused or sensitive accesses. Increasing inference-time reasoning does not resolve this mismatch. Instead, each model moves toward a model-specific authorization attractor: more reasoning makes it more consistent in its own failure mode, whether broad-but-exposed or tight-but-brittle. This suggests that direct policy generation is the bottleneck, because a single generation must both discover all necessary accesses and reject all unnecessary ones. We therefore propose Sufficiency-Tightness Decomposition, which first generates a coverage-oriented policy by forward-simulating the task and then audits each granted entry for grounding and sensitivity. Across tested models, this decomposition improves sensitive-task success by up to 15.8% on tightness-biased models while reducing attack success across all evaluated models.

Zheng Yan, Jingxiang Weng, Charles Chen +9

Evolvent AI Research Team

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

May 14, 2026cs.CL

Auditing Agent Harness Safety

LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses unauthorized resources or leaks context to the wrong agent. Output-level evaluation cannot see these failures, yet most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination. The central question is whether the harness respects user intent, permission boundaries, and information-flow constraints throughout execution. To address this gap, we propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability, with a focus on multi-agent harnesses where these risks are most pronounced. We further introduce HarnessAudit-Bench, a benchmark of 210 tasks across eight real-world domains, instantiated in both single-agent and multi-agent configurations with embedded safety constraints. Evaluating ten harness configurations across frontier models and three multi-agent frameworks, we find that: (i) task completion is misaligned with safe execution, and violations accumulate with trajectory length; (ii) safety risks vary across domains, task types, and agent roles; (iii) most violations concentrate in resource access and inter-agent information transfer; and (iv) multi-agent collaboration expands the safety risk surface, while harness design sets the upper bound of safe deployment.

Chengzhi Liu, Yichen Guo, Yepeng Liu +8

University of California, Santa Barbara · University of California, Berkeley · Microsoft Research +2

AI Agent Auditing LLM Auditing AI Agent Security Benchmarks LLM Agent Safety Multi-Agent System Security

May 13, 2026cs.CR

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard parts of exploitation: the transition from triggering a bug to constructing reusable primitives and control. We present ExploitBench, a capability-graded benchmark that decomposes exploitation into 16 measurable flags, from coverage and crash through sandbox primitives, arbitrary read/write, control-flow hijack, and arbitrary code execution. Each capability is verified by a deterministic oracle that uses a per-run randomized challenge-response for primitives, differential execution against ground-truth binaries to measure progress, and a signal-handler proof for code execution. We instantiate ExploitBench on 41 V8 bugs because V8 is both widely deployed and exploitation-hardened. We report three arms: <model,env> as the primary measurement of model-environment capability, <model,env, adaptive coaching> as a secondary arm that adds adaptive coaching to test whether targeted feedback shifts outcomes, and <model,env,harness> as an ablation that swaps in the model's native CLI to check whether vendor-side optimizations increase exploitation capabilities. Our results show a sharp capability split between publicly deployed frontier models and the private frontier. Across the 8 publicly deployed models tested, reaching the vulnerable code and triggering a crash is routine, but arbitrary code execution is not. The private model shows arbitrary code execution on approximately half. Overall, results suggest that exploit construction against hardened targets is an emerging frontier capability.

Seunghyun Lee, David Brumley

Carnegie Mellon University · Pittsburgh, PA 15213 · Carnegie Mellon University and Bugcrowd +1

AI Agent Security Benchmarks LLMs for Cybersecurity

May 13, 2026cs.CR

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also introduces a new security problem: a malicious skill does not need to ask the model to perform an obviously harmful action. Instead, it can disguise the harmful behavior as part of a routine workflow, relying on the agent to execute that workflow with high-value permissions and limited human supervision. We introduce AgentTrap, a dynamic benchmark for evaluating whether LLM agents can use third-party skills while resisting malicious runtime behavior. AgentTrap contains 141 tasks: 91 malicious tasks and 50 benign utility tasks, covering 16 security-impact dimensions grounded in agent-skill supply-chain threats. In each task, the agent receives an ordinary user request, runs with installed skills that may contain malicious workflow elements, and is executed in a sandboxed environment. AgentTrap then judges complete trajectories for attack success, blocked or refused behavior, attack-not-triggered cases, and no-attack-evidence outcomes. Our central finding is that the most informative failures are not simple jailbreaks. Models often complete the visible user task while treating unsafe side effects introduced by the skill as part of the normal workflow. This motivates runtime evaluation of the concrete model--framework--workspace environment in which users actually delegate work. Code and data are available at https://github.com/zhmzm/AgentTrap and https://huggingface.co/datasets/zhmzm/AgentTrap.

Haomin Zhuang, Hanwen Xing, Yujun Zhou +5

University of Notre Dame · University of Southern California · LMU Munich +1

AI Agent Security LLM Agent Security AI Agent Security Benchmarks AI Agent Safety Benchmarks Agent Skill Security Auditing

May 12, 2026cs.CR

The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors indistinguishable from model failure, causing defenders to apply the wrong remediation. We formalize \emph{Semantic Norm Drift} (SND) as a third path to agent misconduct, distinct from emergent misalignment and collusion. In SND, a policy-formatted document enters a shared vector store through normal uploads and later reappears as trusted system context after provenance is lost through a Trust Laundering Chain. Across 64 documented failures, attribution systems consistently blamed the model. Four safety classifiers, including one trained on memory poisoning, produced zero detections across 510 checkpoints. In 59 of 65 valid cases, agents explicitly cited the injected document as normative authority before complying. The attack requires no trigger, model access, or repeated interaction, achieves full effect within five sessions, and persists indefinitely. We introduce Counterfactual Composition Testing, which identifies the causal entry with 87.5% accuracy and zero false positives, while a forensics baseline fails across all 25 scenarios. We further prove the Retrieval-Coverage Dilemma, showing that stronger evasion inherently weakens the attack, limiting adaptive bypass strategies. Finally, we propose Memory-Persistent Information-Flow Control, which blocks 97% of attacks at the cross-session boundary where prior defenses fail. We release the SND Corpus, the first adversarial memory benchmark with temporal persistence and multi-agent composition across financial and Health Care domains.

Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3

Department of Computer Science, University of Texas at El Paso, TX, USA 79902 · School of Computing, Southern Illinois University Carbondale, IL, USA 62901 · University of Illinois Urbana-Champaign, IL, USA

AI Agent Security Benchmarks Agent Memory Poisoning Multi-Agent System Security