Cover Image

Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ji, Zimo, Li, Zongjie, Jiang, Wenyuan, Gao, Yudong, Wang, Shuai
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

Empirical Study of Code Large Language Models for Binary Security Patch Detection
by: Li, Qingyuan, et al.
Published: (2025)

Zero-Permission Manipulation: Can We Trust Large Multimodal Model Powered GUI Agents?
by: Qian, Yi, et al.
Published: (2026)

Poisoned Identifiers Survive LLM Deobfuscation: A Case Study on Claude Opus 4.6
by: Lorenzo, Luis Guzmán
Published: (2026)

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

Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
by: Mitropoulos, Dimitris, et al.
Published: (2026)

CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
by: Shi, Jingwei, et al.
Published: (2026)

SecCodeBench-V2 Technical Report
by: Chen, Longfei, et al.
Published: (2026)

Testing Storage-System Correctness: Challenges, Fuzzing Limitations, and AI-Augmented Opportunities
by: Wang, Ying, et al.
Published: (2026)

AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution
by: Mächtle, Felix, et al.
Published: (2025)

PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
by: Jiang, Ziyou, et al.
Published: (2024)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
by: Hu, Junze, et al.
Published: (2025)

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

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
by: Zhang, Xiaoyu, et al.
Published: (2025)

Protect Your Secrets: Understanding and Measuring Data Exposure in VSCode Extensions
by: Liu, Yue, et al.
Published: (2024)

Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
by: Improta, Cristina
Published: (2024)

Towards Privacy-Preserving Code Generation: Differentially Private Code Language Models
by: Catal, Melih, et al.
Published: (2025)

SPDZCoder: Combining Expert Knowledge with LLMs for Generating Privacy-Computing Code
by: Dong, Xiaoning, et al.
Published: (2024)

Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
by: Patir, Rupam, et al.
Published: (2025)

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
by: Yang, Hua, et al.
Published: (2025)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
by: Wang, Su, et al.
Published: (2026)

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
by: Huang, Li, et al.
Published: (2026)

Learning to Generate Secure Code via Token-Level Rewards
by: Quan, Jiazheng, et al.
Published: (2026)

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
by: Gajjar, Jugal, et al.
Published: (2025)

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs
by: Yuan, He Yang, et al.
Published: (2026)

We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
by: Li, Zhihao, et al.
Published: (2025)

Traces of Memorisation in Large Language Models for Code
by: Al-Kaswan, Ali, et al.
Published: (2023)

Reflection-Driven Control for Trustworthy Code Agents
by: Wang, Bin, et al.
Published: (2025)

AI Code Generators for Security: Friend or Foe?
by: Natella, Roberto, et al.
Published: (2024)

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG
by: Chen, Yufan, et al.
Published: (2025)

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
by: Liu, Yu, et al.
Published: (2024)

Security of LLM-generated Code: A Comparative Analysis
by: Morkonda, Srivathsan G, et al.
Published: (2026)

Harnessing the Power of LLMs in Source Code Vulnerability Detection
by: Mahyari, Andrew A
Published: (2024)

Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity
by: Gagnon, Charles E., et al.
Published: (2025)

An Empirical Study of Code Obfuscation Practices in the Google Play Store
by: Niroshan, Akila, et al.
Published: (2025)

Cochise: A Reference Harness for Autonomous Penetration Testing
by: Happe, Andreas, et al.
Published: (2026)

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
by: Peng, Jiaren, et al.
Published: (2026)

Beyond Trusting Trust: Multi-Model Validation for Robust Code Generation
by: McDanel, Bradley
Published: (2025)

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
by: Bruni, Marc, et al.
Published: (2025)

DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
by: Pathak, Abhijeet, et al.
Published: (2025)

From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities
by: Krishnamurthy, Ranjith, et al.
Published: (2026)