Cover Image

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Yunhao, Ding, Yifan, Tan, Yingshui, Zheng, Boren, Guo, Yanming, Li, Xiaolong, Zhai, Kun, Li, Yishan, Huang, Wenke
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
by: Guo, Ji, et al.
Published: (2024)

BraveGuard: From Open-World Threats to Safer Computer-Use Agents
by: Feng, Yunhao, et al.
Published: (2026)

Event Trojan: Asynchronous Event-based Backdoor Attacks
by: Wang, Ruofei, et al.
Published: (2024)

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

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

DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints
by: Qin, Xuezheng, et al.
Published: (2025)

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

Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers
by: Wang, Ruofei, et al.
Published: (2024)

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
by: Zhu, Pengyu, et al.
Published: (2025)

HeisenTrojans: They Are Not There Until They Are Triggered
by: Mavurapu, Akshita Reddy, et al.
Published: (2023)

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

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
by: Wu, Jiangrong, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
by: Liu, Yiyong, et al.
Published: (2026)

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
by: Zhang, Junke, et al.
Published: (2026)

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
by: Feng, Yunhao, et al.
Published: (2026)

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
by: Guo, Zihan, et al.
Published: (2026)

TrojanTime: Backdoor Attacks on Time Series Classification
by: Dong, Chang, et al.
Published: (2025)

SkillTester: Benchmarking Utility and Security of Agent Skills
by: Wang, Leye, et al.
Published: (2026)

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
by: Jia, Xiaojun, et al.
Published: (2026)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
by: Guo, Ji, et al.
Published: (2024)

Real is not True: Backdoor Attacks Against Deepfake Detection
by: Sun, Hong, et al.
Published: (2024)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
by: Cheng, Pengzhou, et al.
Published: (2024)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
by: Wang, Hongtao, et al.
Published: (2026)

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
by: Chen, Xuan, et al.
Published: (2025)

Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
by: Pu, Yuwen, et al.
Published: (2024)

Prototype-Guided Robust Learning against Backdoor Attacks
by: Guo, Wei, et al.
Published: (2025)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
by: Zhang, Guangsheng, et al.
Published: (2026)

Compromising Embodied Agents with Contextual Backdoor Attacks
by: Liu, Aishan, et al.
Published: (2024)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
by: Qu, Yubin, et al.
Published: (2026)

Evil from Within: Machine Learning Backdoors through Hardware Trojans
by: Warnecke, Alexander, et al.
Published: (2023)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
by: Fujinuma, Yoshinari, et al.
Published: (2026)

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

Stealthy Targeted Backdoor Attacks against Image Captioning
by: Fan, Wenshu, et al.
Published: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
by: Jin, Haibo, et al.
Published: (2021)

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

Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
by: Li, Ye, et al.
Published: (2024)

When Skills Lie: Hidden-Comment Injection in LLM Agents
by: Wang, Qianli, et al.
Published: (2026)