Image de couverture de livre

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Ying, Wen, Hongbo, Chen, Yanju, Liu, Hanzhi, Tian, Yuan, Feng, Yu
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
par: Wen, Hongbo, et autres
Publié: (2026)

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
par: Liu, Hanzhi, et autres
Publié: (2026)

FORAY: Towards Effective Attack Synthesis against Deep Logical Vulnerabilities in DeFi Protocols
par: Wen, Hongbo, et autres
Publié: (2024)

Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
par: Liu, Hanzhi, et autres
Publié: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
par: Feng, Yunhao, et autres
Publié: (2026)

Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
par: Li, Ying, et autres
Publié: (2026)

Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
par: Saha, Shoumik, et autres
Publié: (2026)

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
par: Tie, Guiyao, et autres
Publié: (2026)

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
par: Peng, Wanli, et autres
Publié: (2025)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
par: Qu, Yubin, et autres
Publié: (2026)

Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback
par: Lin, Shiyin
Publié: (2025)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
par: Chen, Zhihao, et autres
Publié: (2026)

Targeted Bit-Flip Attacks on LLM-Based Agents
par: Wang, Jialai, et autres
Publié: (2026)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
par: Wang, Hongtao, et autres
Publié: (2026)

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
par: Gong, Xueluan, et autres
Publié: (2024)

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
par: Jia, Xiaojun, et autres
Publié: (2026)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
par: Lv, Lijia, et autres
Publié: (2026)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
par: Wu, Yixin, et autres
Publié: (2025)

Emerging Cyber Attack Risks of Medical AI Agents
par: Qiu, Jianing, et autres
Publié: (2025)

SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
par: Wen, Aidan, et autres
Publié: (2025)

SkillTester: Benchmarking Utility and Security of Agent Skills
par: Wang, Leye, et autres
Publié: (2026)

When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents
par: Lu, Di, et autres
Publié: (2026)

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
par: Luo, Mingyu, et autres
Publié: (2026)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
par: Cao, Tri, et autres
Publié: (2025)

PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
par: Yu, Jiahao, et autres
Publié: (2024)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
par: Fujinuma, Yoshinari, et autres
Publié: (2026)

Locus: Agentic Predicate Synthesis for Directed Fuzzing
par: Zhu, Jie, et autres
Publié: (2025)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
par: Ning, Liang-bo, et autres
Publié: (2025)

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
par: Chen, Jianming, et autres
Publié: (2026)

A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
par: Yu, Yinbo, et autres
Publié: (2024)

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
par: Chen, Tianxin, et autres
Publié: (2026)

Testing Storage-System Correctness: Challenges, Fuzzing Limitations, and AI-Augmented Opportunities
par: Wang, Ying, et autres
Publié: (2026)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
par: Xu, Yixiao, et autres
Publié: (2025)

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
par: Liu, Songyang, et autres
Publié: (2026)

Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
par: Zhao, Jingke, et autres
Publié: (2024)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
par: Fei, Zekun, et autres
Publié: (2024)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
par: Li, Siyuan, et autres
Publié: (2026)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
par: Jiang, Yukun, et autres
Publié: (2026)

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
par: Bai, Fengshuo, et autres
Publié: (2024)

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
par: Xiang, Qiuchi, et autres
Publié: (2026)