Agent Skill Security Auditing

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 37

All topics

Runaway Reaction: When Benign Skills Compose into Malicious Behavior
Oct 5, 2026Zunlong Zhou, Ziyuan Yang, Mengyu Sun +1AI Agent Security LLM Agent Security
Sichuan University
Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents
Sep 30, 2026Tobias Kaiser, Aritra DharAI Agent Security Agent Skill Security Auditing
Computing System Labs, Huawei Research Zurich
Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents
Sep 30, 2026Wenxin Wu, Lingyong Yan, Lei Sha +2Adversarial Attacks on LLMs LLM Agent Security
Beihang University · Baidu Inc · Wilfrid Laurier University
Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
Sep 30, 2026Yan Wang, Zhihao Zhang, Ke Chen +5LLM Agent Security Prompt Injection Attacks on AI Agents
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyberspace Security, University of Chinese Academy of Sciences · Worcester Polytechnic Institute
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
Sep 29, 2026Haoran Ou, Gelei Deng, Xuanye Zhang +3Small Language Models LLM Agent Security
Nanyang Technological University
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Sep 28, 2026Lingqi Jiang, Jialuo Chen, Jianan Ma +8Prompt Injection Attacks on AI Agents Agent Skill Security Auditing
Zhejiang University · Ant Group · Hangzhou Dianzi University +1
After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem
Sep 15, 2026Yunpeng Xiong, Ting ZhangAI Agent Governance Agent Skill Security Auditing
Monash University, Australia
SkillAtlas: An Attack Trace Library for Agent Skills
Sep 11, 2026Yuxin Tian, Zenghao Duan, Liang Pang +2LLM Agent Security Agent Skill Security Auditing
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences
AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing
Sep 7, 2026Xiaoting Lyu, Yuhong Wu, Yufei Han +6LLM Agent Security LLM Agent Skill Learning
Xi’an Jiaotong University · INRIA · University of Warwick +1
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Aug 10, 2026Puyu Zeng, Simeng Qin, Jingzhi Li +3AI Agent Security LLM Agent Security
College of Cryptology and Cyber Science, Nankai University, China · Northeastern University, China · University of Science and Technology Beijing, China +2
SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills
Aug 9, 2026Xinze Chen, Chi Zhang, Ping Ji +1Static Code Analysis AI Agent Security Benchmarks
The Graduate Center, City University of New York · New York, NY, USA · Hunter College, City University of New York +2
SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment
Aug 7, 2026Chaofan Meng, Yuhang Zheng, Yingnan Zhou +1Agent Evaluation Agent Skill Security Auditing
College of Cryptology and Cyber Science, Nankai University
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
Aug 5, 2026Jialuo Chen, Minghe Wang, Lingqi Jiang +7Data Provenance AI Agent Auditing
Ant Group · Zhejiang University · Hangzhou Dianzi University, China +2
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Aug 4, 2026Yongli Xiang, Zhifang Zhang, Bojun Yang +4Privacy Leakage in Language Models AI Agent Security Benchmarks
1Sydney AI Centre, The University of Sydney · University of Queensland · 3Southeast University +1
Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking
Jul 31, 2026Yayu Gao, Yong Xiao, Hao Hu +5Cybersecurity AI Agent Security
School of Electronic Information and Communications, the Huazhong University of Science and Technology, Wuhan, China 430074 · Peng Cheng Laboratory, Shenzhen, China · Pazhou Laboratory (Huangpu), Guangzhou, China +4
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
Jul 22, 2026Qiyuan Liu, Tingfeng Hui, Kun Zhan +2LLM Agent Evaluation AI Agent Safety
Department of Data Science, City University of Hong Kong · Hong Kong Institute of AI for Science, City University of Hong Kong · Beijing University of Posts and Telecommunications +1
CONTRA: Red-Teaming Configurations of Personalizable Agents
Jul 3, 2026Jonathan Nöther, Adish Singla, Goran RadanovicLLM Red Teaming AI Agent Security
Max Planck Institute for Software Systems, Germany
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
Jul 2, 2026Jinwei Hu, Yi Dong, Youcheng Sun +1LLM Agents Agent Skill Security Auditing
School of Computer Science and Informatics, University of Liverpool, Liverpool, United Kingdom · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Jul 1, 2026Changguo Jia, Tianqi Zhao, Runzhi He +1LLM Agents Agent Skill Security Auditing
Peking University, Beijing, China · Zhongguancun Laboratory, Beijing, China
The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills
Jun 30, 2026Hongliang Liu, Yuhao Wu, Tung-Ling LiAgent Skill Security Auditing
Palo Alto Networks
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
Jun 29, 2026Peizhi Niu, Wenjie Qu, Shangding Gu +14AI Agent Security LLM Agent Security
UIUC · NUS · UC Berkeley +8
Detecting Malicious Agent Skills in the Wild using Attention
Jun 22, 2026Bacem Etteib, Daniele Lunghi, Tégawendé F. BissyandéLLM Agent Security Agent Skill Security Auditing
University of Luxembourg
SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment
Jun 21, 2026Dexu Yu, Youhua Li, Zhaoyang Guan +12AI Agent Auditing Automated Evaluation
Northeastern University · City University of Hong Kong · DeciLix Lab +8
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Jun 16, 2026Xiaojun Jia, Jie Liao, Simeng Qin +5LLM Agent Security Prompt Injection Defense
Nanyang Technological University, Singapore · Chongqing University, China · Northeastern University, China +2
SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills
Jun 14, 2026Ismail Hossain, Sai Puppala, Md Jahangir Alam +2LLM-as-a-Judge LLM Agent Security
SUPREME Lab, University of Texas at El Paso, Texas, USA.
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
Jun 13, 2026Yi Xie, Jiawei Du, Yu Cheng +2LLM Agent Security AI Agent Security Benchmarks
East China Normal University, Shanghai, China · Centre for Frontier AI Research A*STAR, Singapore · Shanghai Innovation Institute, Shanghai, China
Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security
Jun 10, 2026Tu Lan, Chaowei XiaoAI Agent Auditing LLM Agent Security
Johns Hopkins University
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
May 31, 2026Vincent Koc, Patrick Erichsen, Jacob Tomlinson +3AI Agent Security Agent Skill Security Auditing
OpenClaw Foundation USA · NVIDIA United Kingdom · NVIDIA USA
Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
May 30, 2026Ismail Hossain, Sai Puppala, Zhuoran Lu +2AI Agent Security AI Agent Security Benchmarks
University of Texas at El Paso, TX, USA · Southern Illinois University-Carbondale, IL, USA · Purdue University, IN, USA
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
May 30, 2026Su Wang, Pin Qian, Yihang Chen +6Software Security AI Agent Security
Carnegie Mellon University · Georgia Institute of Technology · University of Glasgow +2

Oct 5, 2026, cs.CRJ/K move · Enter open · S save

Runaway Reaction: When Benign Skills Compose into Malicious Behavior

Zunlong Zhou, Ziyuan Yang, Mengyu Sun, Yi Zhang

Sichuan University

AI Agent Security LLM Agent Security AI Agent Security Benchmarks Agent Skill Security Auditing

Open paper AskPDF arXiv

Agent skills package task-specific knowledge and procedures that can be composed to support complex agent tasks, while public marketplaces provide a growing pool of reusable skills. Existing security vetting, however, largely evaluates skills in isolation, leaving composition-induced risks underexplored. Such risks arise because composing benign skills expands the agent's capability space, enabling behaviors unavailable to any skill alone. Interestingly, we find that directly composing benign skills can already induce malicious behaviors, even when every individual skill passes security vetting. We further find that some target malicious behaviors remain difficult to realize through direct composition, even when the selected skills collectively provide the required capabilities. To systematically instantiate these attacks, we present Compositional Risk Induction via Multi skill Execution (CRIME). CRIME first uses the Malicious Plot Casting (MPC) module to decompose a target malicious behavior into complementary requirements and identify suitable benign skill compositions from public skill repositories. For compositions that cannot directly realize the target behavior, the Runaway Reaction Steering (RRS) module uses execution feedback to iteratively refine the selected skills toward the target while requiring each skill to remain benign under standalone vetting. The resulting composition is then passed to the Skill Reaction Chamber (SRC) module, where the skill pair is executed in a sandbox and the resulting environmental consequences are examined to determine whether the target behavior has occurred. Unsuccessful cases are returned to RRS for further refinement. Furthermore, we construct a benchmark of 4,000 public skills across eight cybersecurity behaviors for systematic evaluation of composition-induced vulnerabilities.

Momentum

Related topics

Latest papers 37