Cover Image

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ferrag, Mohamed Amine, Tihanyi, Norbert, Hamouda, Djallel, Maglaras, Leandros, Lakas, Abderrahmane, Debbah, Merouane
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

$α^3$-SecBench: A Large-Scale Evaluation Suite of Security, Resilience, and Trust for LLM-based UAV Agents over 6G Networks
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge
by: Tihanyi, Norbert, et al.
Published: (2024)

Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses
by: Ferrag, Mohamed Amine, et al.
Published: (2023)

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
by: Ferrag, Mohamed Amine, et al.
Published: (2024)

AgentDrive: An Open Benchmark Dataset for Agentic AI Reasoning with LLM-Generated Scenarios in Autonomous Systems
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices
by: Ferrag, Mohamed Amine, et al.
Published: (2023)

Securing Tomorrow's Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies
by: Jain, Ridhi, et al.
Published: (2024)

Reliability and Resilience of AI-Driven Critical Network Infrastructure under Cyber-Physical Threats
by: Lizos, Konstantinos A., et al.
Published: (2025)

6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

$α^3$-Bench: A Unified Benchmark of Safety, Robustness, and Efficiency for LLM-Based UAV Agents over 6G Networks
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

Innovating Augmented Reality Security: Recent E2E Encryption Approaches
by: Alsop, Hamish, et al.
Published: (2025)

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

How Small Can 6G Reason? Scaling Tiny Language Models for AI-Native Networks
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

6G-Bench: An Open Benchmark for Semantic Communication and Network-Level Reasoning with Foundation Models in AI-Native 6G Networks
by: Ferrag, Mohamed Amine, et al.
Published: (2026)

Critical Infrastructure Protection: Generative AI, Challenges, and Opportunities
by: Yigit, Yagmur, et al.
Published: (2024)

The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution
by: Tihanyi, Norbert, et al.
Published: (2025)

LIDSA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management
by: Lakas, Abderrahmane, et al.
Published: (2026)

How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models
by: Tihanyi, Norbert, et al.
Published: (2024)

Alignment of Cybersecurity Incident Prioritisation with Incident Response Management Maturity Capabilities
by: Gulay, Abdulaziz, et al.
Published: (2024)

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
by: Ferrag, Mohamed Amine, et al.
Published: (2023)

Reasoning Beyond Limits: Advances and Open Problems for LLMs
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

A novel TLS-based Fingerprinting approach that combines feature expansion and similarity mapping
by: Thomson, Amanda, et al.
Published: (2024)

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology
by: Vidal, Nubio, et al.
Published: (2025)

Ember: A Serverless Peer-to-Peer End-to-End Encrypted Messaging System over an IPv6 Mesh Network
by: Alsop, Hamish, et al.
Published: (2026)

Cyber-Twin: Digital Twin-boosted Autonomous Attack Detection for Vehicular Ad-Hoc Networks
by: Yigit, Yagmur, et al.
Published: (2024)

Review of Generative AI Methods in Cybersecurity
by: Yigit, Yagmur, et al.
Published: (2024)

CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection
by: Dubniczky, Richard A., et al.
Published: (2025)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
by: Wang, Peiran, et al.
Published: (2026)

Ransomware: Analysis and Evaluation of Live Forensic Techniques and the Impact on Linux based IoT Systems
by: Korac, Salko, et al.
Published: (2024)

SME-TEAM: Leveraging Trust and Ethics for Secure and Responsible Use of AI and LLMs in SMEs
by: Sarker, Iqbal H., et al.
Published: (2025)

Prompt Injection 2.0: Hybrid AI Threats
by: McHugh, Jeremy, et al.
Published: (2025)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
by: Huang, Charoes, et al.
Published: (2026)

Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs
by: Mohsin, Ahmad, et al.
Published: (2024)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
by: Maloyan, Narek, et al.
Published: (2026)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
by: Wang, Reachal, et al.
Published: (2025)

AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset
by: Lbath, Amine, et al.
Published: (2025)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
by: Wang, Yihan, et al.
Published: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
by: Ying, Zonghao, et al.
Published: (2026)