Cover Image

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yi, Wang, Weizhe, Feng, Ruitao, Zhang, Yao, Xu, Guangquan, Deng, Gelei, Li, Yuekang, Zhang, Leo
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
by: Qu, Yubin, et al.
Published: (2026)

What Makes a Good LLM Agent for Real-world Penetration Testing?
by: Deng, Gelei, et al.
Published: (2026)

VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities
by: Wang, Weizhe, et al.
Published: (2025)

An Empirical Study on the Security Vulnerabilities of GPTs
by: Wu, Tong, et al.
Published: (2025)

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories
by: Shifat, Fariha Tanjim, et al.
Published: (2026)

FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation
by: Zhou, Zhiping, et al.
Published: (2025)

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
by: Lingxiang, Wang, et al.
Published: (2025)

Prompt Injection attack against LLM-integrated Applications
by: Liu, Yi, et al.
Published: (2023)

PentestGPT: An LLM-empowered Automatic Penetration Testing Tool
by: Deng, Gelei, et al.
Published: (2023)

Unlocking User-oriented Pages: Intention-driven Black-box Scanner for Real-world Web Applications
by: Wang, Weizhe, et al.
Published: (2025)

Characterizing Trust Boundary Vulnerabilities in TEE Containers: An Empirical Study
by: Liu, Weijie, et al.
Published: (2025)

Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
by: Liang, Zi, et al.
Published: (2026)

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

A Large Scale Study of AI-based Binary Function Similarity Detection Techniques for Security Researchers and Practitioners
by: Shi, Jingyi, et al.
Published: (2025)

IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
by: Li, Ziyang, et al.
Published: (2024)

Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
by: Khare, Avishree, et al.
Published: (2023)

QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
by: Wang, Claire, et al.
Published: (2025)

Revisiting Vulnerability Patch Identification on Data in the Wild
by: Irsan, Ivana Clairine, et al.
Published: (2026)

Unity is Strength: Enhancing Precision in Reentrancy Vulnerability Detection of Smart Contract Analysis Tools
by: Wang, Zexu, et al.
Published: (2024)

An Empirical Study of Vulnerability Handling Times in CPython
by: Ruohonen, Jukka
Published: (2024)

Generating Proof-of-Vulnerability Tests to Help Enhance the Security of Complex Software
by: Kanchi, Shravya, et al.
Published: (2026)

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
by: Chen, Junkai, et al.
Published: (2025)

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications
by: Yang, Ruozhao, et al.
Published: (2026)

An Empirical Study of Vulnerable Package Dependencies in LLM Repositories
by: Liu, Shuhan, et al.
Published: (2025)

One Signature, Multiple Payments: Demystifying and Detecting Signature Replay Vulnerabilities in Smart Contracts
by: Wang, Zexu, et al.
Published: (2025)

ProSec: Fortifying Code LLMs with Proactive Security Alignment
by: Xu, Xiangzhe, et al.
Published: (2024)

Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation
by: Liu, Yi, et al.
Published: (2024)

Security Incentivization: An Empirical Study of how Micropayments Impact Code Security
by: Rass, Stefan, et al.
Published: (2026)

Conflicting Scores, Confusing Signals: An Empirical Study of Vulnerability Scoring Systems
by: Koscinski, Viktoria, et al.
Published: (2025)

An Empirical Study on Oculus Virtual Reality Applications: Security and Privacy Perspectives
by: Guo, Hanyang, et al.
Published: (2024)

Fixing Security Vulnerabilities with AI in OSS-Fuzz
by: Zhang, Yuntong, et al.
Published: (2024)

On the Security Vulnerabilities of Text-to-SQL Models
by: Peng, Xutan, et al.
Published: (2022)

ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse
by: Liu, Simiao, et al.
Published: (2026)

Exploring Security Practices in Infrastructure as Code: An Empirical Study
by: Verdet, Alexandre, et al.
Published: (2023)

Efficient Detection of Toxic Prompts in Large Language Models
by: Liu, Yi, et al.
Published: (2024)

An Empirical Study of Bitwise Operators Intuitiveness through Performance Metrics
by: Joshi, Shubham
Published: (2025)

A Large-scale Empirical Study on the Generalizability of Disclosed Java Library Vulnerability Exploits
by: Chen, Zirui, et al.
Published: (2026)

WildCode: An Empirical Analysis of Code Generated by ChatGPT
by: Khanmohammadi, Kobra, et al.
Published: (2025)

The Secrets Must Not Flow: Scaling Security Verification to Large Codebases (extended version)
by: Arquint, Linard, et al.
Published: (2025)

Security study based on the Chatgptplugin system: ldentifying Security Vulnerabilities
by: Ren, Ruomai
Published: (2025)