Lessons from Penetration Tests on Large-Scale Agent Systems

• URL: http://arxiv.org/abs/2605.27042v1
• Date: Tue, 26 May 2026 13:58:27 GMT
• Title: Lessons from Penetration Tests on Large-Scale Agent Systems
• Abstract summary: Execution-capable AI agents interact extensively with multiple layers of the computing stack.<n>It remains unclear whether proprietary agent systems exhibit similar security weaknesses.<n>We present findings from two penetration tests conducted in 2025 against proprietary agent products.
• Score: 7.61892296424389
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes of weaknesses long observed in prior computing systems. Execution-capable AI agents are effectively unbounded, self-modifying programs that interact extensively with multiple layers of the computing stack. This broad interaction surface imposes a significant security burden on developers, who must reason about and secure complex cross-layer behaviors. Prior research has primarily focused on vulnerabilities in open-source agents and agent frameworks. In contrast, it remains unclear whether proprietary agent systems -- developed under stricter coding standards and formal review processes -- exhibit similar security weaknesses. In this paper, we present findings from two penetration tests conducted in 2025 against proprietary agent products and evaluate whether the security posture of AI agents has improved since these assessments.

Related papers

• POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems [0.07783271875179179]
  We present POIROT, a protocol that repurposes a system's own agents as its diagnostic layer.<n>Across evaluated settings, POIROT outperforms single-LLM baseline evaluators.<n>We release POIROT as an open-source library alongside BLAME, a benchmark for fault attribution in safety-critical multi-agent systems.
  arXiv  Detail & Related papers  (2026-06-01T14:05:35Z)
• 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)
• DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents [121.77550256034]
  DecodingTrust-Agent Platform (DTap) is a controllable and interactive red-teaming platform for AI agents.<n>DTap-Red is the first autonomous red-teaming agent that explores diverse injection vectors and autonomously discovers effective attack strategies.<n>Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models.
  arXiv  Detail & Related papers  (2026-05-06T11:59:48Z)
• Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs [32.38053469964495]
  Extended action spaces, including hidden inter-system interactions, pose severe security challenges.<n>IPI, which conceals malicious instructions within third-party content, can trigger unauthorized actions such as data exfiltration.<n>We evaluate six defense strategies against four sophisticated IPI attack vectors across nine LLM backbones.
  arXiv  Detail & Related papers  (2026-04-04T21:27:04Z)
• A Systematic Security Evaluation of OpenClaw and Its Variants [26.64519805689193]
  This paper presents a systematic security assessment of six representative OpenClaw-series agent frameworks.<n>We construct a benchmark of 205 test cases covering representative attack behaviors across the full agent execution lifecycle.<n>Our results show that all evaluated agents exhibit substantial security vulnerabilities, and that agentized systems are significantly riskier than their underlying models.
  arXiv  Detail & Related papers  (2026-04-03T15:52:36Z)
• Systems Security Foundations for Agentic Computing [21.600611396864114]
  This paper examines end-to-end security properties of entire systems, rather than AI models in isolation.<n>A key goal is to examine where research challenges arise when applying traditional security principles in the context of AI agents.
  arXiv  Detail & Related papers  (2025-12-01T05:28:59Z)
• SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents [58.21223208538351]
  This work explores the security issues surrounding mobile multimodal agents.<n>It attempts to construct a risk discrimination mechanism by incorporating behavioral sequence information.<n>It also designs an automated assisted assessment scheme based on a large language model.
  arXiv  Detail & Related papers  (2025-07-01T15:10:00Z)
• 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)
• Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis [47.34614558636679]
  This study investigates the underlying factors that contribute to the increased vulnerability of Web AI agents.<n>We identify three critical factors that amplify the vulnerability of Web AI agents; (1) embedding user goals into the system prompt, (2) multi-step action generation, and (3) observational capabilities.
  arXiv  Detail & Related papers  (2025-02-27T18:56:26Z)
• Agent-SafetyBench: Evaluating the Safety of LLM Agents [72.92604341646691]
  We introduce Agent-SafetyBench, a benchmark designed to evaluate the safety of large language models (LLMs)<n>Agent-SafetyBench encompasses 349 interaction environments and 2,000 test cases, evaluating 8 categories of safety risks and covering 10 common failure modes frequently encountered in unsafe interactions.<n>Our evaluation of 16 popular LLM agents reveals a concerning result: none of the agents achieves a safety score above 60%.
  arXiv  Detail & Related papers  (2024-12-19T02:35:15Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)

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.