How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
- URL: http://arxiv.org/abs/2511.08487v1
- Date: Wed, 12 Nov 2025 02:01:17 GMT
- Title: How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
- Authors: Zihan Ma, Dongsheng Zhu, Shudong Liu, Taolin Zhang, Junnan Liu, Qingqiu Li, Minnan Luo, Songyang Zhang, Kai Chen,
- Abstract summary: Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks.<n>We address this gap with a two-dimensional analysis of agent safety brittleness under the pressures of intent concealment and task complexity.<n>Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations.
- Score: 55.441602598245744
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional analysis of agent safety brittleness under the orthogonal pressures of intent concealment and task complexity. To enable this, we introduce OASIS (Orthogonal Agent Safety Inquiry Suite), a hierarchical benchmark with fine-grained annotations and a high-fidelity simulation sandbox. Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations. By releasing OASIS and its simulation environment, we provide a principled foundation for probing and strengthening agent safety in these overlooked dimensions.
Related papers
- RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
arXiv Detail & Related papers (2025-12-24T15:01:26Z) - SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents [7.975014390527644]
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities.<n>We present SafeMindBench, a multimodal benchmark with 5,558 samples spanning four task categories (Instr-Risk, Env-Risk, Order-Fix, Req-Align) across high-risk scenarios such as sabotage, harm, privacy, and illegal behavior.<n>We introduce SafeMindAgent, a modular Planner-Executor architecture integrated with three cascaded safety modules, which incorporate safety constraints into the reasoning process.
arXiv Detail & Related papers (2025-09-30T07:24:04Z) - Agent Safety Alignment via Reinforcement Learning [29.759393704688986]
We propose the first unified safety-alignment framework for tool-using agents.<n>We introduce a tri-modal taxonomy, including benign, malicious, and sensitive for both user prompts and tool responses.<n>Our results show that safety and effectiveness can be jointly optimized.
arXiv Detail & Related papers (2025-07-11T02:34:16Z) - Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems [25.6233463223145]
We study intention-hiding threats in multi-agent systems powered by Large Language Models (LLM-MAS)<n>We design four representative attack paradigms that subtly disrupt task completion while maintaining a high degree of stealth.<n>To counter these threats, we propose AgentXposed, a psychology-inspired detection framework.
arXiv Detail & Related papers (2025-07-07T07:34:34Z) - IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks [30.535665641990114]
We present IS-Bench, the first multi-modal benchmark designed for interactive safety.<n>It features 161 challenging scenarios with 388 unique safety risks instantiated in a high-fidelity simulator.<n>It facilitates a novel process-oriented evaluation that verifies whether risk mitigation actions are performed before/after specific risk-prone steps.
arXiv Detail & Related papers (2025-06-19T15:34:46Z) - AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions [64.85086226439954]
We present SAFE, a benchmark for assessing the safety of embodied VLM agents on hazardous instructions.<n> SAFE comprises three components: SAFE-THOR, SAFE-VERSE, and SAFE-DIAGNOSE.<n>We uncover systematic failures in translating hazard recognition into safe planning and execution.
arXiv Detail & Related papers (2025-06-17T16:37:35Z) - LLM Agents Should Employ Security Principles [60.03651084139836]
This paper argues that the well-established design principles in information security should be employed when deploying Large Language Model (LLM) agents at scale.<n>We introduce AgentSandbox, a conceptual framework embedding these security principles to provide safeguards throughout an agent's life-cycle.
arXiv Detail & Related papers (2025-05-29T21:39:08Z) - SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning [51.78514648677898]
We propose SAFER, a framework for Safety Alignment via eFficient Ex-Ante Reasoning.<n>Our approach instantiates structured Ex-Ante reasoning through initial assessment, rule verification, and path calibration.<n> Experiments on multiple open-source LLMs demonstrate that SAFER significantly enhances safety performance while maintaining helpfulness and response efficiency.
arXiv Detail & Related papers (2025-04-03T16:07:38Z) - SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [58.65256663334316]
We present SafeAgentBench -- the first benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments.<n>SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 9 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives.
arXiv Detail & Related papers (2024-12-17T18:55:58Z) - Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model [73.8765529028288]
We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment.<n>To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations.<n>Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
arXiv Detail & Related papers (2024-06-21T16:14:15Z)
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.