Concern 440 · Working draft · editorial review in progress
RAG document exposure across tenants
Cross-tenant document exposure occurs when an AI retrieval system gives one customer or user information belonging to another.
Understanding the concern
Retrieval-augmented generation, or RAG, lets a model use documents found by a search system. In a shared service, the search must respect who is allowed to see each document. A filter error, stale permission or shared cache can cross that boundary even if the generated answer is otherwise accurate.
Imagine a librarian bringing a file from the wrong locked cabinet because the catalogue omitted its access label. Asking the model to keep secrets is not a replacement for preventing access in the first place. Permissions need to be enforced before retrieval and checked through the system's storage, search and response paths.
An example
A customer asks a routine question and receives a detail from another customer's private document.
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.
- RAG
- Retrieval-augmented generation: an AI looks up material before writing an answer. Finding a document does not guarantee that the document or the answer is correct.
Evidence and its limits
The sources address retrieval permissions and disclosure risk. The example is hypothetical, not a report of a named vendor breach.
Microsoft Learn · Official product documentation
Document-level access control in Azure AI Search ↗ (opens in a new tab)Explains authorization around retrieval documents; architectural guidance is applicable context, not a claim that all services use the same controls.
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.
- OECD AI Principles (opens in a new tab)
framework
- NIST AI RMF (opens in a new tab)
framework
A question to discuss
Are permissions enforced before documents reach the model, including after access changes and in cached results?
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.
Dignity
Dignity means recognizing each person's worth regardless of usefulness, status, or a system's score. People deserve respect and a voice in matters that affect them.
Explain important decisions, avoid humiliating treatment, and keep room for a person's story. Do not treat a prediction as a complete account of who someone is.
Ask together: Does this use treat each person as someone whose experience matters?
Trustworthiness
Trustworthiness means giving people good reasons to rely on you. It grows when promises, actions, and evidence line up. With AI, a friendly voice or a famous brand is not enough: people need to know what was checked and what could still go wrong.
In practice, keep promises small enough to test, record mistakes, and tell people when the tool's limits affect them. If a service promises human review, make sure a person really has time and authority to review it.
Ask together: What would give the people affected a sound reason to trust this use?
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.