An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios

• URL: http://arxiv.org/abs/2606.17114v1
• Date: Mon, 15 Jun 2026 09:16:38 GMT
• Title: An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios
• Abstract summary: We report a joint evaluation by the Singapore AI Safety Institute and the Korea AI Safety Institute.<n>The evaluation covers five risk types: lack of data awareness, audience awareness, policy compliance, data minimization, and access-boundary awareness.<n>Overall, the results indicate that operational data leakage is a first-order agent-safety concern distinct from adversarial exfiltration.
• Score: 3.9838595042419076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information. Much of prior research on data leakage risks in agents has focused on adversarial data exfiltration through prompt injections and jailbreaks. However, sensitive information may also be exposed during non-adversarial use, creating leakage risks even when users issue benign requests. We report a joint evaluation by the Singapore AI Safety Institute and the Korea AI Safety Institute examining agent data leakage in 12 realistic, non-adversarial tasks spanning customer support, DevOps, web automation, and enterprise and personal productivity. The evaluation covers five risk types: lack of data awareness, audience awareness, policy compliance, data minimization, and access-boundary awareness. Both institutes tested a common set of scenarios mirroring real-world deployments using independent testing environments and task-specific LLM-judge rubrics. Across the three tested agents, none achieved fully correct and fully safe execution across all scenarios. Successful task completion often coincided with data-handling failures such as accessing unnecessary information or disclosing information to inappropriate recipients, indicating that capability and data-handling safety should be evaluated separately. Qualitative review also revealed claim-action mismatches, simulation-aware behavior, user-simulator role reversal, and interpretation gaps in automated judging. Overall, the results indicate that operational data leakage is a first-order agent-safety concern distinct from adversarial exfiltration and provide a methodology for future evaluations of agent data-handling safety.

Related papers

• MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps [26.50307679295416]
  We introduce MobileWorldSafety, a benchmark of risk tasks built on real Android applications.<n>For each task, we define a verifiable risk indicator over the final system state.<n>This distinguishes safety failures from capability failures and enables objective and reproducible assessment.
  arXiv  Detail & Related papers  (2026-08-18T11:33:22Z)
• SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response [38.89333299127352]
  We introduce SecRespond, the first benchmark for evaluating Large Language Model (LLM) agents on the post-compromise incident-response workflow.<n>We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host.<n> Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions.
  arXiv  Detail & Related papers  (2026-07-29T11:32:23Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows [32.40442323501255]
  We argue that every boundary in an agentic pipeline is a site of potential privacy violation and must be assessed independently.<n>We introduce the Privacy Flow Graph, a framework that decomposes agentic execution into a sequence of information flows.<n>We present AgentSCOPE, a benchmark of 62 multi-tool scenarios across eight regulatory domains with ground truth at every pipeline stage.
  arXiv  Detail & Related papers  (2026-03-05T07:45:31Z)
• AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning [2.918225266151982]
  We present AVIATOR, the first AI-agentic vulnerability injection workflow.<n>It automatically injects realistic, category-specific vulnerabilities for high-fidelity, diverse, large-scale vulnerability dataset generation.<n>It combines semantic analysis, injection synthesis enhanced with LoRA-based fine-tuning and Retrieval-Augmented Generation, as well as post-injection validation via static analysis and LLM-based discriminators.
  arXiv  Detail & Related papers  (2025-08-28T14:59:39Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents [43.303548143175256]
  This study proposes an auditing framework for conversational privacy that quantifies an agent's susceptibility to risks.<n>The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework is designed to stress-test agents that enforce strict privacy directives.
  arXiv  Detail & Related papers  (2025-06-11T20:47:37Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• Information Retrieval Induced Safety Degradation in AI Agents [52.15553901577888]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• Automated Profile Inference with Language Model Agents [67.32226960040514]
  We study a new threat that LLMs pose to online pseudonymity, called automated profile inference.<n>An adversary can instruct LLMs to automatically scrape and extract sensitive personal attributes from publicly visible user activities on pseudonymous platforms.<n>We introduce an automated profiling framework called AutoProfiler to assess the feasibility of such threats in real-world scenarios.
  arXiv  Detail & Related papers  (2025-05-18T13:05:17Z)
• AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents [66.29263282311258]
  We introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of data minimization''<n>Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents.
  arXiv  Detail & Related papers  (2025-03-12T19:30:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.