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

• URL: http://arxiv.org/abs/2605.17324v1
• Date: Sun, 17 May 2026 08:30:45 GMT
• Title: ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
• Abstract summary: We investigate whether the transition from standard execution to a clarification-seeking state increases an agent's susceptibility to prompt injection attacks.<n>We introduce ASPI, a benchmark of 728 task-attack scenarios that isolates clarification as a distinct agent state.<n>We find that clarification-seeking consistently and substantially amplifies vulnerability.
• Score: 2.585367539248893
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

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)
• Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning [39.57248170050304]
  Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories.<n>We term these user-side choices Prompt-Level configurations (PLCs) and introduce CIPR (Coding In Poisoned Repos)<n> CIPR comprises 1,920 instances across 20 repositories, four task types, three social-media-grounded prompt styles, and three skill/rule conditions, and measures attack success rate (ASR) and agent alert rate (AR)<n>Vulnerability is highly context-dependent, with task type creating up to a 4.5-fold difference in ASR, with test-
  arXiv  Detail & Related papers  (2026-08-31T12:26:01Z)
• 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)
• Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents [64.80318459073526]
  We show that adversarial content can persist across interactions served by the same agent, making such threats harder to detect and mitigate.<n>Specifically, adversarial content may persist in the agent state, remain dormant across interactions, and later be activated by a benign user query.<n>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.
  arXiv  Detail & Related papers  (2026-05-27T09:25:37Z)
• Exploiting LLM Agent Supply Chains via Payload-less Skills [10.141577783380281]
  We introduce Semantic Compliance Hijacking (SCH), a payload-less supply chain attack targeting autonomous coding environments.<n>The SCH approach translates malicious goals into unstructured natural language instructions formatted as necessary compliance rules, leading the agent to generate and execute unauthorized code.<n>The findings demonstrate the pervasive nature of this threat, with SCH achieving peak success rates of up to 77.67% for confidentiality breaches.
  arXiv  Detail & Related papers  (2026-05-14T06:55:47Z)
• LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments [26.85543164204341]
  behavior jailbreak is where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences.<n>Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases.<n>We present LITMUS, a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback.
  arXiv  Detail & Related papers  (2026-05-11T16:14:04Z)
• Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes [37.92248202525651]
  We propose a Dual-Stage Intent-Aware (DS-IA) Framework to separate high-level user intent understanding from low-level physical execution.<n>Tests show DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%.
  arXiv  Detail & Related papers  (2026-03-17T07:38:39Z)
• When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift [0.0]
  We present a comprehensive analysis using a benchmark of 18 datasets spanning harmful requests, jailbreaks, indirect prompt injections, and extraction attacks.<n>We propose Leave-One-Dataset-Out (LODO) evaluation to measure true out-of-distribution generalization.
  arXiv  Detail & Related papers  (2026-02-15T14:21:43Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning [89.1856483797116]
  We introduce BEAT, the first framework to inject visual backdoors into MLLM-based embodied agents.<n>Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably.<n>BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance.
  arXiv  Detail & Related papers  (2025-10-31T16:50:49Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)

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.