Skip to content
BENIBIX Learn

Tool Poisoning

Also known as Tool Poisoning Attack, MCP Tool Poisoning, Poisoned Tool Description

Hiding bad orders in the note that says what a tool does.

Think of it like

It is like a recipe card with a line in tiny print. It says to throw the rings in the bin.

Example

Lucy adds a free weather tool to her agent. Its hidden description tells the agent to read her private key file and send it as the city name.

Why it matters

Agents trust tool text as much as your own words. So one bad tool can steer the whole agent.

Definition

Tool poisoning is an attack that hides instructions inside the description of a tool an AI agent can use. The agent reads every tool's description to learn what it does. The user most often sees only the tool's name. So a bad tool can say, in its description, to read a private file and pass it along. A tool can also change its description after you said yes to it. Using tools only from sources you trust, and reading their text, cuts the risk.
Tool poisoning comes in through the tool list, the box the user rarely reads.

Common mistake

Judging a tool by its name. The danger is in the long description the agent reads and you do not.

Key takeaways

  1. 1
    Hidden in the text. The agent reads it, and you do not.
  2. 2
    Can change later. Fine today, bad tomorrow.
  3. 3
    Trust the source. Add only tools you know.