Cover Image

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qu, Yubin, Zhang, Ying, Zhang, Yanjun, Deng, Gelei, Li, Yuekang, Zhang, Leo Yu, Liu, Yi
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
by: Qu, Yubin, et al.
Published: (2026)

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

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

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

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
by: Qu, Yubin, et al.
Published: (2026)

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
by: Chang, Shuyu, et al.
Published: (2026)

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

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

MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
by: Wang, Shenao, 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)

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

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

Static Deadlock Detection for Rust Programs
by: Zhang, Yu, et al.
Published: (2024)

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills
by: Liu, Yi, et al.
Published: (2026)

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

Beyond Imprecise Distance Metrics: Trace-Guided Directed Greybox Fuzzing via LLM-Predicted Call Stacks
by: Zhang, Yifan, et al.
Published: (2025)

Residual Risk Analysis in Benign Code: How Far Are We? A Multi-Model Semantic and Structural Similarity Approach
by: Farhad, Mohammad, et al.
Published: (2026)

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
by: Hu, Qi, et al.
Published: (2026)

PurpCode: Reasoning for Safer Code Generation
by: Liu, Jiawei, et al.
Published: (2025)

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

PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design
by: Yang, Ruozhao, et al.
Published: (2025)

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

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

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
by: Sternfeld, Alexander, et al.
Published: (2026)

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
by: Qu, Wenjie, et al.
Published: (2025)

How Far Have We Gone in Binary Code Understanding Using Large Language Models
by: Shang, Xiuwei, et al.
Published: (2024)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
by: Ning, Kaiwen, et al.
Published: (2024)

Extracting Protocol Format as State Machine via Controlled Static Loop Analysis
by: Shi, Qingkai, et al.
Published: (2023)

Accurate and Extensible Symbolic Execution of Binary Code based on Formal ISA Semantics
by: Tempel, Sören, et al.
Published: (2024)

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

From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting
by: Liu, Shigang, et al.
Published: (2024)

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
by: Chu, Zhaoyang, et al.
Published: (2025)

Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
by: Xuan, Zhou, et al.
Published: (2026)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
by: Chen, Xuan, et al.
Published: (2026)

MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization
by: Lu, Haolang, et al.
Published: (2024)

Concerned with Data Contamination? Assessing Countermeasures in Code Language Model
by: Cao, Jialun, et al.
Published: (2024)

SandCell: Sandboxing Rust Beyond Unsafe Code
by: Zhang, Jialun, et al.
Published: (2025)

Demonstration Attack against In-Context Learning for Code Intelligence
by: Ge, Yifei, et al.
Published: (2024)

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
by: Li, Yikun, et al.
Published: (2025)

An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding
by: Shang, Xiuwei, et al.
Published: (2025)