Supply Chain Risk in AI Agent Tool Registries
Malicious skills poisoned AI agent registries before defenses could catch up.
Priya Venkataraman
Senior Editor & Staff Writer
Priya Venkataraman
Priya spent eight years as a penetration tester at a mid-sized security consultancy before pivoting to full-time threat journalism in 2019. She focuses on adversarial machine learning and has testified at two industry working groups on AI risk frameworks.
4 stories
Prompt Injection in Retrieval-Augmented Generation Systems
Attackers can poison RAG systems through the retrieval pipeline, bypassing model hardening entirely.
Priya Venkataraman
Tool Name Exploitation in AI Agent Frameworks
AI agents mistake tool metadata for direct instructions, creating a universal attack surface.
Priya Venkataraman
Indirect Prompt Injection via Third-Party Plugins
Attackers exploit plugin architecture to inject malicious instructions into AI chatbots.
Priya Venkataraman