Research topic

AI Security

AI agents, gateways and the services around them.

2025

Jan 20January
AI SecurityLLM agent tool servers
When an AI agent trusts the tool description more than the user
Agents read tool descriptions as instructions. We show how a poisoned description in a shared tool server steers an agent, and how to review tools before you connect them.theblackturtle and thanhlocpandaOPSWAT Unit 5151 min readInstruction injection

First AI Security publication · January 2025