Concern 147 · Working draft · editorial review in progress
Cross-context prompt injection
Cross-context prompt injection occurs when instructions from one conversation, user, or shared workspace improperly influence another.
Understanding the concern
Applications sometimes reuse summaries, caches, or shared conversation histories. If these carry untrusted instructions into a new context, a person may be affected by material they never chose to use. The problem involves both instruction handling and separation between users.
This should not imply that models automatically remember every other user's chats. Exposure depends on how an application stores and passes information. Teams need to trace what moves between contexts and whose permissions apply at each step.
An example
A shared office notebook carries one visitor's instructions into the next visitor's appointment, as though both had agreed to them.
Illustrative unless identified as a documented case.
Words in plain English
- 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.
- Injection
- In this context, unwanted instructions or commands inserted into material a system reads or processes.
Evidence and its limits
These sources establish cross-boundary instruction and persistent-memory mechanisms. The shared-workspace example is a design scenario, not a claim about every chat service.
Greshake and colleagues · 2023 · Research study
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection ↗ (opens in a new tab)Demonstrates indirect instructions through retrieved content in specified applications and prototypes.
Chen and colleagues · 2024 · Research study
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases ↗ (opens in a new tab)Demonstrates poisoned retrieval and memory in evaluated agents without requiring model retraining.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What information can move between sessions, and what prevents it from gaining authority there?
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.