Cover Image

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yiyong, Hsu, Chia-Yi, Huang, Chun-Ying, Backes, Michael, Wen, Rui, Yu, Chia-Mu
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
by: Hsu, Chia-Yi, et al.
Published: (2026)

SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark
by: Wen, Rui, et al.
Published: (2025)

Transferable Availability Poisoning Attacks
by: Liu, Yiyong, et al.
Published: (2023)

Efficient Data-Free Model Stealing with Label Diversity
by: Liu, Yiyong, et al.
Published: (2024)

Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data
by: Hsu, I-Jung, et al.
Published: (2025)

USBIPS Framework: Protecting Hosts from Malicious USB Peripherals
by: Wang, Chun-Yi, et al.
Published: (2024)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
by: Wu, Yixin, et al.
Published: (2025)

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
by: Liu, Hanzhi, et al.
Published: (2026)

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
by: Hsu, Chia-Yi, et al.
Published: (2025)

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
by: Wen, Rui, et al.
Published: (2024)

Fine-grained Manipulation Attacks to Local Differential Privacy Protocols for Data Streams
by: Li, Xinyu, et al.
Published: (2025)

Membership Inference Attacks Against In-Context Learning
by: Wen, Rui, et al.
Published: (2024)

MalTool: Malicious Tool Attacks on LLM Agents
by: Hu, Yuepeng, et al.
Published: (2026)

Data Poisoning Attacks to Locally Differentially Private Range Query Protocols
by: Liao, Ting-Wei, et al.
Published: (2025)

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
by: Li, Ying, et al.
Published: (2026)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
by: Jiang, Yukun, et al.
Published: (2026)

From Storage to Steering: Memory Control Flow Attacks on LLM Agents
by: Xu, Zhenlin, et al.
Published: (2026)

Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks
by: Zhang, Minxing, et al.
Published: (2024)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
by: Wang, Zihan, et al.
Published: (2026)

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
by: Duan, Zenghao, et al.
Published: (2026)

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
by: Hou, Yinghan, et al.
Published: (2026)

Amplifying Machine Learning Attacks Through Strategic Compositions
by: Liu, Yugeng, et al.
Published: (2025)

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
by: Ding, Ruyi, et al.
Published: (2024)

Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
by: Ito, Hibiki, et al.
Published: (2026)

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
by: Tie, Guiyao, et al.
Published: (2026)

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills
by: Liu, Yi, et al.
Published: (2026)

Instruction Backdoor Attacks Against Customized LLMs
by: Zhang, Rui, et al.
Published: (2024)

Attack Effect Model based Malicious Behavior Detection
by: Wang, Limin, et al.
Published: (2025)

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
by: Chen, Zeyuan, et al.
Published: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
by: Feng, Yunhao, et al.
Published: (2026)

The Pulse of Fileless Cryptojacking Attacks: Malicious PowerShell Scripts
by: Varlioglu, Said, et al.
Published: (2024)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
by: Zhuang, Haomin, et al.
Published: (2026)

Peering Behind the Shield: Guardrail Identification in Large Language Models
by: Yang, Ziqing, et al.
Published: (2025)

Malicious Agent Detection for Robust Multi-Agent Collaborative Perception
by: Zhao, Yangheng, et al.
Published: (2023)

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
by: Chung, Ming-Yu, et al.
Published: (2023)

FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks
by: Chen, Jian, et al.
Published: (2025)

IU: Imperceptible Universal Backdoor Attack
by: Lin, Hsin, et al.
Published: (2026)

Defending Unauthorized Model Merging via Dual-Stage Weight Protection
by: Chen, Wei-Jia, et al.
Published: (2025)

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
by: Schmotz, David, et al.
Published: (2026)

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
by: Liu, Zixuan, et al.
Published: (2025)