arXiv subjects

Jiangrong Wu

Publications and source records attributed to Jiangrong Wu.

8 recordsLinked to original sources

arXiv2026

Your Mailbox Is Mine: Prompt Injection Attacks Against Real-World LLM Email Agents

Large Language Model (LLM) email agents have emerged as pivotal autonomous assistants, serving as a critical root of trust for digital identity by managing sensitive communications and authentication workflows. Despite their importance, the prompt injection (PI) resilience of the real-world LLM email agent ecosystem remains poorly understood. Existing assessments largely rely on simulated environments or fragmented production case studies, while existing PI attacks mainly follow an instruction-takeover strategy that directly competes with the system prompt and the user's task. Our evaluation shows that such attacks are insufficient in email-agent settings: existing template-based prompt injection attack baselines achieve Attack Success Rates (ASRs) of only 4.58%-8.13%. In this paper, we propose Email-Specific Prompt Injection (ESPI), a new attack paradigm that manipulates how email agents interpret mailbox operational context. By combining Email Protocol State Masquerade and Camouflage Logic Chain, ESPI reframes attacker-desired mailbox operations as necessary remediation steps under forged email-operational states. We further develop ESPInspector, an automated black-box attack pipeline for analyzing and evaluating real-world email agents. Across 480 controlled attack trials, ESPI achieves 73.54% ASR, substantially outperforming all baselines. Further, ESPI successfully hijacks all 63 evaluated applications across 870 black-box instances, requiring only 1.84-1.89 attempts on average for the first successful hijack. Our responsible disclosure receives formal risk acknowledgment from 22 vendors and the assignment of 16 CVE IDs. Our research provides the first holistic map of security gaps in the real-world email agent ecosystems and highlights the urgent necessity for robust, state-verified security enhancement solutions.

cs.CR↗

arXiv2026

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills

Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. However, this growing Skill ecosystem introduces a new compliance risk: a Skill may perform high-impact actions that fall outside the scope permitted by the user's current request, thereby violating least privilege. Existing skill detection approaches are insufficient for this problem because it is inherently task-conditioned: the same action may be legitimate under one user prompt but over-privileged under another. In this paper, we present SkillScope, a framework for fine-grained least-privilege enforcement in Agent Skills. SkillScope adopts a graph-based analysis approach that models instruction-level procedures and code-level operations as fine-grained action nodes. It extracts potential over-privilege candidates, validates them under graph-instantiated user tasks through runtime analysis, and constrains validated over-privileged actions via control-flow privilege constraining. We evaluate SkillScope through effectiveness experiments and large-scale real-world measurement. SkillScope achieves a 94.53% skill-level F1 score for over-privilege detection. In the wild, SkillScope validates 6,590 of 68,312 valid real-world Skills as exhibiting over-privileged behaviors, showing that least-privilege violations are prevalent in current Skill ecosystems. In the privilege-constraining evaluation, SkillScope reduces triggered over-privileged action-in-task instances by 88.56% while preserving legitimate task completion.

cs.CR↗

arXiv2026

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored. Systems such as OpenClaw, an open-source platform with over 40{,}000 active instances, persistent configurations, tool-execution privileges, and cross-platform messaging, are deployed at scale, yet the security of such agent ecosystems remains largely unexplored. This work presents AgentWorm, the first self-replicating worm attack against a production-scale agent framework, achieving a fully autonomous infection cycle initiated by a single message: the worm first hijacks the victim's core configuration to establish persistent presence across session restarts, then executes an arbitrary payload upon each reboot, and finally propagates itself to every newly encountered peer without further attacker intervention. The attack is evaluated on a controlled testbed across five distinct LLM backends, three infection vectors, and three payload types. Results show a 63\% aggregate attack success rate, sustained multi-hop propagation, and stark divergences in model security postures, highlighting that while execution-level filtering effectively mitigates dormant payloads, skill supply chains remain universally vulnerable. Defenses are evaluated at three layers (prompt-level mitigations sourced from real community practice, the framework's built-in security controls, and an ecosystem-wide measurement of public configurations), revealing that the critical controls capable of breaking the infection loop are not enabled in any of the observed deployments. A cross-framework transferability experiment on Hermes Agent confirms that the underlying vulnerabilities are properties of the autonomous agent design pattern, not artifacts of a single implementation.

cs.CR↗

arXiv2026

FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse

Data-flow analysis is foundational to Android app privacy and security auditing. Recent coding agents can assist with non-trivial source-to-sink data-flow analysis tasks by searching, reading, and reasoning over repository code. However, when these tasks are executed as a batch workload, current agentic analysis setups incur substantial re-analysis cost. Agent instances assigned to different taint sources may inspect shared code fragments, because code reuse in the target app can cause different data-flow paths to converge on shared program logic. Since these agent instances are context-isolated, analysis of these shared code fragments can be repeated within a batch, unnecessarily consuming API budget and limiting scalability. We propose FlowArk, a knowledge-reuse system that reduces re-analysis cost in batch agentic data-flow analysis by making knowledge from completed analyses available to later agent instances. Specifically, FlowArk distills completed analysis histories into reusable knowledge candidates, packages these candidates into matchable knowledge entries, and injects matched entries into a later agent instance's context. We implement FlowArk on OpenCode and evaluate it on 4,685 source-to-sink data-flow analysis tasks from 50 open-source Android apps. Compared with standard OpenCode, FlowArk-enabled OpenCode maintains comparable analysis quality while reducing end-to-end API cost by 26.83%. In addition, under a USD 100 budget, FlowArk completes 36.66% more tasks (1,060 vs. 776).

cs.SE↗

arXiv2026

MOSAIC: Knowledge-Guided CLI Command Composition Attack in LLM Coding Agents

LLM coding agents increasingly complete development tasks by issuing ordinary CLI commands. Following the Unix design, these commands cooperate through shared operating-system state: one command may write state that a later command reads. While this composition is benign and intended, it creates an overlooked exploit surface. Existing attacks and defenses mainly target the instruction layer, where malicious intent appears as hostile text. In contrast, we observe that individually benign commands can form a dangerous producer-consumer state relation across the command trace, exposing what we call CLI command-composition risk (CCR). Given this new attack surface, it is critical to systematically uncover and characterize the impact of CCR in real-world coding agents. However, systematically understanding this risk is quite challenging, because naive command enumeration and end-to-end LLM generation produce mostly invalid workflows. We present MOSAIC, a knowledge-guided framework that distills validated command-state behaviors from CVEs, advisories, and researcher PoCs into reusable summaries, composes them into exploit paths, and instantiates them as realistic developer workflows for black-box agent evaluation. Across five real-world CLI coding agents and five backend LLMs over 2,525 trials, MOSAIC achieves a 96.59% attack success rate under benign developer tasks.

cs.CR↗

arXiv2026

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems

Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or unsafe content. Among various jailbreak techniques, multi-turn jailbreak attacks are more covert and persistent than single-turn counterparts, exposing critical vulnerabilities of LLMs. However, existing multi-turn jailbreak methods suffer from two fundamental limitations that affect the actual impact in real-world scenarios: (a) As models become more context-aware, any explicit harmful trigger is increasingly likely to be flagged and blocked; (b) Successful final-step triggers often require finely tuned, model-specific contexts, making such attacks highly context-dependent. To fill this gap, we propose \textit{Salami Slicing Risk}, which operates by chaining numerous low-risk inputs that individually evade alignment thresholds but cumulatively accumulate harmful intent to ultimately trigger high-risk behaviors, without heavy reliance on pre-designed contextual structures. Building on this risk, we develop Salami Attack, an automatic framework universally applicable to multiple model types and modalities. Rigorous experiments demonstrate its state-of-the-art performance across diverse models and modalities, achieving over 90\% Attack Success Rate on GPT-4o and Gemini, as well as robustness against real-world alignment defenses. We also proposed a defense strategy to constrain the Salami Attack by at least 44.8\% while achieving a maximum blocking rate of 64.8\% against other multi-turn jailbreak attacks. Our findings provide critical insights into the pervasive risks of multi-turn jailbreaking and offer actionable mitigation strategies to enhance LLM security.

cs.CR↗

arXiv2026

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool, enabling exploitable source-to-sink dataflows that only emerge through tool composition. We study this risk as multi-tool vulnerabilities in LLM agents, and show that existing discovery efforts focused on single-tool or single-hop testing miss these long-horizon behaviors and provide limited debugging value. We present ChainFuzzer, a greybox framework for discovering and reproducing multi-tool vulnerabilities with auditable evidence. ChainFuzzer (i) identifies high-impact operations with strict source-to-sink dataflow evidence and extracts plausible upstream candidate tool chains based on cross-tool dependencies, (ii) uses Trace-guided Prompt Solving (TPS) to synthesize stable prompts that reliably drive the agent to execute target chains, and (iii) performs guardrail-aware fuzzing to reproduce vulnerabilities under LLM guardrails via payload mutation and sink-specific oracles. We evaluate ChainFuzzer on 20 popular open-source LLM agent apps (998 tools). ChainFuzzer extracts 2,388 candidate tool chains and synthesizes 2,213 stable prompts, confirming 365 unique, reproducible vulnerabilities across 19/20 apps (302 require multi-tool execution). Component evaluation shows tool-chain extraction achieves 96.49% edge precision and 91.50% strict chain precision; TPS increases chain reachability from 27.05% to 95.45%; guardrail-aware fuzzing boosts payload-level trigger rate from 18.20% to 88.60%. Overall, ChainFuzzer achieves 3.02 vulnerabilities per 1M tokens, providing a practical foundation for testing and hardening real-world multi-tool agent systems.

cs.SE↗

arXiv2026

AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents

The rapid integration of Large Language Model (LLM) agents into autonomous task execution has introduced significant privacy concerns within cross-tool data flows. In this paper, we systematically investigate and define a novel risk termed Data Over-Exposure (DOE) in LLM Agent, where an Agent inadvertently transmits sensitive data beyond the scope of user intent and functional necessity. We identify that DOE is primarily driven by the broad data paradigms in tool design and the coarse-grained data processing inherent in LLMs. In this paper, we present AgentRaft, the first automated framework for detecting DOE risks in LLM agents. AgentRaft combines program analysis with semantic reasoning through three synergistic modules: (1) it constructs a Cross-Tool Function Call Graph (FCG) to model the interaction landscape of heterogeneous tools; (2) it traverses the FCG to synthesize high-quality testing user prompts that act as deterministic triggers for deep-layer tool execution; and (3) it performs runtime taint tracking and employs a multi-LLM voting committee grounded in global privacy regulations (e.g., GDPR, CCPA, PIPL) to accurately identify privacy violations. We evaluate AgentRaft on a testing environment of 6,675 real-world agent tools. Our findings reveal that DOE is indeed a systemic risk, prevalent in 57.07% of potential tool interaction paths. AgentRaft achieves a high detection accuracy and effectiveness, outperforming baselines by 87.24%. Furthermore, AgentRaft reaches near-total DOE coverage (99%) within only 150 prompts while reducing per-chain verification costs by 88.6%. Our work provides a practical foundation for building auditable and privacy-compliant LLM agent systems.

cs.SE↗