Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

2026 Open access

Read full text
Authors: Léo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nazanin Mohammadi Sepahvand, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, Krishnamurthy Dvijotham, Alexandre Drouin, Jason Stanley
DOI: 10.1145/3786335.3813166
Cited by: 0

Abstract

While finetuning AI agents on interaction data—such as web browsing or tool use—improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain.

Fields of Study & Subjects

Blockchain Technology Applications and Security

Publication details

Pages
755–772
Publication date
22 May 2026
Language
EN