Concern 270 · Working draft · editorial review in progress

Prompt-to-SQL injection

Prompt-to-SQL injection occurs when an attacker steers a natural-language database assistant toward an unauthorized query or database action.

Understanding the concern

SQL is a language used to request or change information in a database. An AI interface translates ordinary questions into SQL, which creates a boundary between a request and executable instructions. If generated queries are trusted too broadly, a person can reach data or operations they should not access.

This overlaps with prompt injection but is not identical to traditional SQL injection through an unsafe text field. Both require controls at the database and application layers. The assistant's willingness to answer must not determine which records the user may read or change.

An example

A person asks a reporting assistant a misleading question and receives records outside the account they are allowed to inspect.

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.
Prompt
The instructions or information given to an AI to guide its response.
Injection
In this context, unwanted instructions or commands inserted into material a system reads or processes.
Interface
The controls and displays people use to interact with software, such as buttons, menus, and chat windows.
SQL
A language used to work with information stored in many databases.
Database
An organized collection of information that software can store, search, and update.

Evidence and its limits

The guidance addresses separate injection layers; the study demonstrates schema leakage, which is not itself proof of successful unauthorized data modification.

Explore these sources in the library →
Broader frameworks and background

These resources provide context. They do not establish every claim in this concern.

A question to discuss

Are permissions enforced on the actual query and records, regardless of how the question is phrased?

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.

Severity
Major · 4/5
Likelihood
Documented · 3/5
Time horizon
Near
Register risk score
12
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.

Explore a proposed use of AI →