Image de couverture de livre

AgentBound: Securing Execution Boundaries of AI Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bühler, Christoph, Biagiola, Matteo, Di Grazia, Luca, Salvaneschi, Guido
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence Software Engineering D.2.0
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Machine Learning-Based Detection of MCP Attacks
par: Mattsson, Tobias, et autres
Publié: (2026)

Variables are a Curse in Software Vulnerability Prediction
par: Groppe, Jinghua, et autres
Publié: (2024)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
par: Gajjar, Jugal, et autres
Publié: (2025)

Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI Package Ecosystems
par: McCann, Alan L.
Publié: (2026)

SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents
par: Begimher, Daniel, et autres
Publié: (2026)

Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility
par: Hong, Yining, et autres
Publié: (2026)

Kettle: Attested builds for verifiable software provenance
par: Asad, Amean, et autres
Publié: (2026)

Web Agents Should Adopt the Plan-Then-Execute Paradigm
par: Piet, Julien, et autres
Publié: (2026)

Cross-ecosystem categorization: A manual-curation protocol for the categorization of Java Maven libraries along Python PyPI Topics
par: Paramitha, Ranindya, et autres
Publié: (2024)

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
par: Tang, Yuheng, et autres
Publié: (2026)

Securing the Future of IVR: AI-Driven Innovation with Agile Security, Data Regulation, and Ethical AI Integration
par: Shaikh, Khushbu Mehboob, et autres
Publié: (2025)

Firmware Distribution as Attack Surface: A Security Study of ASIC Cryptocurrency Miners
par: Pouliquen, Pierre, et autres
Publié: (2026)

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
par: Tracy, Tyler, et autres
Publié: (2026)

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
par: Chen, Junkai, et autres
Publié: (2025)

Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
par: Crawford, Brian, et autres
Publié: (2026)

The AI-Native Large-Scale Agile Software Development Manifesto
par: Britto, Ricardo, et autres
Publié: (2026)

AI Code Generators for Security: Friend or Foe?
par: Natella, Roberto, et autres
Publié: (2024)

Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges
par: Al-Kaswan, Ali, et autres
Publié: (2026)

Reflection-Driven Control for Trustworthy Code Agents
par: Wang, Bin, et autres
Publié: (2025)

Testing of Deep Reinforcement Learning Agents with Surrogate Models
par: Biagiola, Matteo, et autres
Publié: (2023)

Favia: Forensic Agent for Vulnerability-fix Identification and Analysis
par: Storhaug, André, et autres
Publié: (2026)

OpenSage: Self-programming Agent Generation Engine
par: Li, Hongwei, et autres
Publié: (2026)

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

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
par: Liu, Yi, et autres
Publié: (2026)

AIBoMGen: Generating an AI Bill of Materials for Secure, Transparent, and Compliant Model Training
par: Vandendriessche, Wiebe, et autres
Publié: (2026)

Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code
par: Blain, Dominik, et autres
Publié: (2026)

MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
par: Steinberg, Jonathan, et autres
Publié: (2026)

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
par: Guo, Yongjian, et autres
Publié: (2025)

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment
par: Haque, Ariful, et autres
Publié: (2025)

Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
par: Yu, Jiongchi, et autres
Publié: (2025)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
par: Wang, Su, et autres
Publié: (2026)

MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement
par: Li, Youpeng, et autres
Publié: (2025)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
par: He, Ping, et autres
Publié: (2025)

AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution
par: Mächtle, Felix, et autres
Publié: (2025)

A Pattern Language for Resilient Visual Agents
par: Gidey, Habtom Kahsay, et autres
Publié: (2026)

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
par: Ni, Ronghao, et autres
Publié: (2026)

Zero-Permission Manipulation: Can We Trust Large Multimodal Model Powered GUI Agents?
par: Qian, Yi, et autres
Publié: (2026)

DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
par: Pathak, Abhijeet, et autres
Publié: (2025)

LLMs + Security = Trouble
par: Livshits, Benjamin
Publié: (2026)

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs
par: Yuan, He Yang, et autres
Publié: (2026)