From prompt injections to protocol exploits: Threats in LLM-powered AI agents workflows

DOAJ (DOAJ: Directory of Open Access Journals) 2026 Open access

Read full text
Authors: Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda, LA Maglaras, Abderrahmane Lakas, Mérouane Debbah
DOI: 10.1016/j.icte.2025.12.001
Cited by: 36
References: 98

Fields of Study & Subjects

Scientific Computing and Data Management Multi-Agent Systems and Negotiation Security and Verification in Computing

Publication details

Journal / source
DOAJ (DOAJ: Directory of Open Access Journals)
Publisher
Elsevier BV
Volume
12
Issue
2
Pages
353-383
Publication date
1 April 2026
Language
EN