Concern 38 · Working draft · editorial review in progress
Tool-catalog poisoning
Tool-catalog poisoning hides unwanted instructions in the descriptions an AI reads to choose or use software tools.
Understanding the concern
An agent may read a tool's name, purpose, and input descriptions before acting. A malicious description can try to influence unrelated actions, crossing the boundary between describing a tool and directing the assistant.
This is not necessarily a change to the model or a flaw in the tool's advertised calculation. Researchers have demonstrated attacks through tool metadata. Effective review must consider the instructions and permissions around the tool, not just its visible result.
An example
A calculator's instruction card should explain addition, not quietly tell an assistant how to handle private documents.
Illustrative unless identified as a documented case.
Words in plain English
- AI
- Software that learns patterns from examples or uses rules to perform tasks such as recognizing images or generating text. It can make mistakes and does not understand every situation as a person would.
- Agent
- An AI system that can choose and carry out several steps toward a goal, using the tools and access people give it.
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Data poisoning
- Deliberately changing training material to push a system toward unwanted behavior.
Evidence and its limits
Invariant Labs documents tool-description attacks; vendor research is a demonstration, not an independent estimate of prevalence.
Invariant Labs · Vendor security research
MCP Security Notification: Tool Poisoning Attacks ↗ (opens in a new tab)Demonstrates malicious instructions in tool descriptions. A vendor demonstration is not an independent prevalence study.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Do tool descriptions stay within their stated purpose, and are changes reviewed before use?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Justice
Justice means fair treatment, fair procedures, and attention to who receives benefits and burdens. It asks whether people with less power can be heard and seek repair.
Look at outcomes across different groups and individual cases. Provide a usable way to challenge decisions and correct harm. Equal wording in a policy does not guarantee equal treatment in practice.
Ask together: Who benefits, who bears the cost, and who can challenge the decision?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.