Concern 239 · Working draft · editorial review in progress
Blast radius of tool use
The blast radius of tool use is the amount of harm one agent mistake can cause through the tools and permissions it has.
Understanding the concern
An assistant that can read one document has a different risk profile from one that can edit every file, send messages, and spend money. Broader access can turn a small misunderstanding into a large incident. The model's ability to produce a sensible answer does not determine this radius.
Permissions should be limited to what the task needs, with separate boundaries for reading, changing, publishing, and spending. This reduces consequences even when the model fails. A single broad approval should not silently authorize unrelated actions across many systems.
An example
A misplaced instruction is less damaging when it controls one room's light than when it controls the entire building.
Illustrative unless identified as a documented case.
Words in plain English
- 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.
Evidence and its limits
OWASP distinguishes excessive functionality, permissions and autonomy. The building analogy describes consequence limits, not model intelligence.
OWASP Gen AI Security Project · Security guidance
LLM06:2025 Excessive Agency ↗ (opens in a new tab)Distinguishes excessive functionality, permissions and autonomy; the framework identifies failure modes rather than their prevalence.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What is the largest change the agent could make before another independent check intervenes?
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.
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
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.