Concern 161 · Working draft · editorial review in progress
Prompt theft
Prompt theft is unauthorized disclosure of the private instructions used to configure an AI application.
Understanding the concern
An application may include internal directions that explain its role, workflow, or business logic. If it repeats them to someone who should not receive them, the developer can lose confidential information or expose weak points. This is separate from stealing the model's weights.
A model's claimed account of its hidden reasoning is not proof that it has revealed an authentic internal record. It may generate a plausible story. Important secrets and access controls should not depend only on asking the model to keep an instruction private.
An example
A public help desk accidentally reads out its internal operating manual when asked how it works.
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.
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Prompt
- The instructions or information given to an AI to guide its response.
- Model weights
- Numbers adjusted during training that help determine how a model responds. They are part of what makes a trained model work.
Evidence and its limits
The sources support instruction-boundary and disclosure risks. They do not establish that a generated explanation reveals faithful internal reasoning.
Wallace and colleagues · 2024 · Research study
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions ↗ (opens in a new tab)Studies instruction priority and evaluated defenses; model behavior alone is not an authorization boundary.
OWASP · Security guidance
LLM02:2025 Sensitive Information Disclosure ↗ (opens in a new tab)Describes exposure of personal and confidential information and defensive considerations; not proof of a particular incident.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What information would be harmful to reveal, and does it need to be inside the prompt at all?
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.
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?
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?
Accountability
Accountability means being answerable for decisions and taking responsibility for repair. It requires more than saying that the software made the choice.
Name the person or team responsible, keep useful records, and give them authority to correct problems. Make the route to a complaint clear to the people affected.
Ask together: Who will answer for the outcome and help put things right?
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.