Cover Image

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Chang, Wang, An, Wei, Zeming, Wang, Kai, Zeng, Biaojie, Zhang, Qiaosheng, Yang, Chao, Qu, Jingjing, Hu, Xia, Xu, Xingcheng
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
by: Wang, Kai, et al.
Published: (2026)

Memory Poisoning Attack and Defense on Memory Based LLM-Agents
by: Sunil, Balachandra Devarangadi, et al.
Published: (2026)

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
by: Ye, Rui, et al.
Published: (2024)

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
by: Zhang, Lingxi, et al.
Published: (2026)

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
by: Yan, Bingyu, et al.
Published: (2025)

Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection
by: Wei, Yangyang, et al.
Published: (2026)

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
by: Zhang, Zaibin, et al.
Published: (2024)

Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems
by: Allegrini, Edoardo, et al.
Published: (2025)

Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems
by: Wang, Chenxi, et al.
Published: (2026)

SoK: Security of Autonomous LLM Agents in Agentic Commerce
by: Mao, Qian'ang, et al.
Published: (2026)

Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes
by: Metere, Alfredo
Published: (2026)

Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
by: Qin, Zhaoming, et al.
Published: (2021)

Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
by: Ye, Dayong, et al.
Published: (2026)

Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring
by: Akarma, Ali, et al.
Published: (2026)

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
by: Kong, Dezhang, et al.
Published: (2025)

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
by: Laws, Matthew D., et al.
Published: (2026)

Enhancing the Robustness of QMIX against State-adversarial Attacks
by: Guo, Weiran, et al.
Published: (2023)

AI Agents with Decentralized Identifiers and Verifiable Credentials
by: Garzon, Sandro Rodriguez, et al.
Published: (2025)

Decentralized Multi-Agent System with Trust-Aware Communication
by: Ding, Yepeng, et al.
Published: (2025)

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
by: Li, Xiang, et al.
Published: (2026)

ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
by: Zhang, Yihao, et al.
Published: (2026)

Chronology of Multi-Agent Interactions for Provenance of Evolving Information
by: Chang, Ching-Chun, et al.
Published: (2025)

EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms
by: Li, Donghe, et al.
Published: (2025)

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
by: Radev, Nikolay, et al.
Published: (2026)

ClawCoin: An Agentic AI-Native Cryptocurrency for Decentralized Agent Economies
by: Li, Shaoyu, et al.
Published: (2026)

Breaking the Secret: Economic Interventions for Combating Collusion in Embodied Multi-Agent Systems
by: Liu, Qi, et al.
Published: (2026)

RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
by: Wei, Zeming, et al.
Published: (2026)

CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents
by: Li, Haoyang, et al.
Published: (2025)

Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
by: Qi, Minfeng, et al.
Published: (2025)

Multi-Agent Actor-Critics in Autonomous Cyber Defense
by: Wang, Mingjun, et al.
Published: (2024)

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
by: Chen, Jianming, et al.
Published: (2026)

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
by: Xia, Hongfei, et al.
Published: (2025)

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

Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems
by: Lu, Ziqing, et al.
Published: (2023)

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
by: Lee, Sunwoo, et al.
Published: (2025)

A Vision for Access Control in LLM-based Agent Systems
by: Li, Xinfeng, et al.
Published: (2025)

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
by: Wu, Chengcan, et al.
Published: (2025)

Who Owns This Agent? Tracing AI Agents Back to Their Owners
by: Chocron, Ruben, et al.
Published: (2026)

Agents for Agents: An Interrogator-Based Secure Framework for Autonomous Internet of Underwater Things
by: Akarma, Ali, et al.
Published: (2026)

Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
by: de Witt, Christian Schroeder, et al.
Published: (2025)