Cover Image

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Su, Qian, Pin, Chen, Yihang, You, Junxian, Wang, Xiaoyuan, Jiang, Xiaochong, Liu, Lifei, Yu, Haoran, Xu, Jingzhou
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
by: Jiang, Xiaochong, et al.
Published: (2026)

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

Exploiting LLM Agent Supply Chains via Payload-less Skills
by: Liu, Xinyu, et al.
Published: (2026)

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
by: Peng, Yibo, et al.
Published: (2025)

"Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts
by: Wang, Shenao, et al.
Published: (2026)

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

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
by: Liu, Yi, et al.
Published: (2026)

A Multi-Store Privacy Measurement of Virtual Reality App Ecosystem
by: Yan, Chuan, et al.
Published: (2025)

Cross-Ecosystem Vulnerability Analysis for Python Applications
by: Alexopoulos, Georgios, et al.
Published: (2026)

An Investigation of Patch Porting Practices of the Linux Kernel Ecosystem
by: Li, Xingyu, et al.
Published: (2024)

Evaluating Tool Cloning in Agentic-AI Ecosystems
by: Kim, Taein, et al.
Published: (2026)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
by: Dong, Ben, et al.
Published: (2026)

Evaluation of the Programming Skills of Large Language Models
by: Heitz, Luc Bryan, et al.
Published: (2024)

MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
by: Steinberg, Jonathan, et al.
Published: (2026)

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

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
by: Song, Hao, et al.
Published: (2025)

Sandboxing Adoption in Open Source Ecosystems
by: Alhindi, Maysara, et al.
Published: (2024)

A Large-scale Fine-grained Analysis of Packages in Open-Source Software Ecosystems
by: Zhou, Xiaoyan, et al.
Published: (2024)

StagedVulBERT: Multi-Granular Vulnerability Detection with a Novel Pre-trained Code Model
by: Jiang, Yuan, et al.
Published: (2024)

SBOM Generation Tools in the Python Ecosystem: an In-Detail Analysis
by: Cofano, Serena, et al.
Published: (2024)

ORCAS: Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graph
by: Wang, Yufeng, et al.
Published: (2025)

Leveraging Security Observability to Strengthen Security of Digital Ecosystem Architecture
by: Ramachandran, Renjith
Published: (2024)

Tracing Vulnerability Propagation Across Open Source Software Ecosystems
by: Ruohonen, Jukka, et al.
Published: (2025)

A Time Series Analysis of Malware Uploads to Programming Language Ecosystems
by: Ruohonen, Jukka, et al.
Published: (2025)

SoK: Towards Reproducibility for Software Packages in Scripting Language Ecosystems
by: Pohl, Timo, et al.
Published: (2025)

Preserving Privacy in Software Composition Analysis: A Study of Technical Solutions and Enhancements
by: Wang, Huaijin, et al.
Published: (2024)

When Specifications Meet Reality: Uncovering API Inconsistencies in Ethereum Infrastructure
by: Ma, Jie, et al.
Published: (2026)

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
by: Hossain, Ismail, et al.
Published: (2026)

RiskTagger: An LLM-based Agent for Automatic Annotation of Web3 Crypto Money Laundering Behaviors
by: Lin, Dan, et al.
Published: (2025)

A Ground-Truth-Based Evaluation of Vulnerability Detection Across Multiple Ecosystems
by: Mandl, Peter, et al.
Published: (2026)

An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems
by: Siddiq, Mohammed Latif, et al.
Published: (2026)

Track and Trace: Automatically Uncovering Cross-chain Transactions in the Multi-blockchain Ecosystems
by: Lin, Dan, et al.
Published: (2025)

Developers Are Victims Too : A Comprehensive Analysis of The VS Code Extension Ecosystem
by: Edirimannage, Shehan, et al.
Published: (2024)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
by: Zhao, Jian, et al.
Published: (2024)

Multi-Agent Collaborative Fuzzing with Continuous Reflection for Smart Contracts Vulnerability Detection
by: Chen, Jie, et al.
Published: (2025)

SafeTrans: LLM-assisted Transpilation from C to Rust
by: Farrukh, Muhammad, et al.
Published: (2025)

Mining the YARA Ecosystem: From Ad-Hoc Sharing to Data-Driven Threat Intelligence
by: Esteban, Dectot--Le Monnier de Gouville, et al.
Published: (2026)

Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
by: Wang, Yongchao, 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)

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
by: Liu, Bin, et al.
Published: (2025)