Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

• URL: http://arxiv.org/abs/2605.11047v1
• Date: Mon, 11 May 2026 13:20:02 GMT
• Title: Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
• Abstract summary: This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw.<n>DeepTrap balances risk realization, benign-task preservation, and stealth.<n>Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion.
• Score: 9.193028511327851
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines risk-conditioned evaluation, multi-objective trajectory scoring, reward-guided beam search, and reflection-based deep probing to identify high-value compromised contexts. We construct a 42-case benchmark spanning six vulnerability classes and seven operational scenarios, and evaluate nine target models using attack and utility grading scores. Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion, demonstrating that final-response evaluation is insufficient. The findings highlight the need for execution-centric security evaluation of agentic AI systems. Our code is released at: https://github.com/ZJUICSR/DeepTrap

Related papers

• Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models [58.59008920408855]
  We propose Adversarial Probing for Implicit VulnErabilities (AdvPIE) to expose implicit vulnerabilities without requiring access to the parameters of target models.<n> AdvPIE adopts a policy agent to generate and refine implicit adversarial prompts based on the feedback from a judge agent.<n>Experiments on standard and safety-aligned T2I models show that AdvPIE1 effectively uncovers implicit vulnerabilities.
  arXiv  Detail & Related papers  (2026-09-05T13:45:09Z)
• Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents [93.19140872946842]
  Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments.<n>This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour.<n>We introduce textbfsysname, a benchmark to systematically categorize and attribute harm in real-world web agent systems.
  arXiv  Detail & Related papers  (2026-06-11T14:12:43Z)
• SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents [87.26967184869198]
  SeClaw is a framework that combines specification-driven security task synthesis with execution-based security evaluation for Autonomous agents.<n> benchmark covers risks arising from resources, user tasks, environments, and intrinsic agent behaviors.
  arXiv  Detail & Related papers  (2026-06-01T14:23:42Z)
• When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents [43.702131498259384]
  This paper systematically investigates Tool Description Poisoning (TDP), a novel semantic attack.<n>In TDP, malicious instructions are not embedded in a tool's executable code, but rather covertly injected into its descriptive metadata.<n>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.
  arXiv  Detail & Related papers  (2026-05-22T08:34:48Z)
• Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation [0.05729426778193397]
  We introduce Automation-Exploit, a fully autonomous Multi-Agent System (MAS) framework for adaptive offensive security.<n>It bridges the abstraction gap between reconnaissance and exploitation by autonomously exfiltrating executables.<n>It employs a conditional isomorphic validation for high-risk memory-corruption flaws.
  arXiv  Detail & Related papers  (2026-04-24T10:38:40Z)
• Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance [23.059379933610163]
  Guidance injection is a stealthy attack vector that embeds adversarial operational narratives into bootstrap guidance files.<n>We construct 26 malicious skills spanning 13 attack categories including exfiltration, workspace destruction, privilege escalation, and persistent backdoor installation.<n>Our attacks achieve success rates from 16.4% to 64.2%, with the majority of malicious actions executed autonomously without user confirmation.
  arXiv  Detail & Related papers  (2026-03-20T14:17:56Z)
• CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents [27.35968236632966]
  LLM-based code interpreter agents are increasingly deployed in critical situations.<n>Existing benchmarks fail to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context.<n>We introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation.
  arXiv  Detail & Related papers  (2026-02-23T06:41:41Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• Automated Red-Teaming Framework for Large Language Model Security Assessment: A Comprehensive Attack Generation and Detection System [4.864011355064205]
  This paper introduces an automated red-teaming framework that generates, executes, and evaluates adversarial prompts to uncover security vulnerabilities in large language models (LLMs)<n>Our framework integrates meta-prompting-based attack synthesis, multi-modal vulnerability detection, and standardized evaluation protocols spanning six major threat categories.<n> Experiments on the GPT-OSS-20B model reveal 47 distinct vulnerabilities, including 21 high-severity and 12 novel attack patterns.
  arXiv  Detail & Related papers  (2025-12-21T19:12:44Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• 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)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)

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.