Concern 274 · Working draft · editorial review in progress
Cross-app permission bleed
Cross-app permission bleed occurs when access granted for one application or purpose is reused beyond the boundary the user intended.
Understanding the concern
OAuth is a common way to grant software limited access without sharing a password. Those grants can have scopes, meaning allowed operations, and an intended service. If tokens or permissions are accepted too broadly, an agent can gain effective access across applications that should remain separate.
An AI agent does not remove the need for ordinary authorization checks. Services must verify that a credential is intended for them and permits the requested action. Users also need understandable ways to review and revoke access without assuming that disconnecting one interface cancels every grant.
An example
A key issued for one office is mistakenly accepted by doors in other departments.
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.
- Agent
- An AI system that can choose and carry out several steps toward a goal, using the tools and access people give it.
- Token
- A small unit of text processed by a language model, such as a word or part of a word.
- Interface
- The controls and displays people use to interact with software, such as buttons, menus, and chat windows.
Evidence and its limits
RFC 9700 addresses privilege and audience restrictions; MCP guidance warns against unsafe token passthrough. Actual exposure depends on implementation.
Internet Engineering Task Force · 2025 · Security standard
RFC 9700: Best Current Practice for OAuth 2.0 Security ↗ (opens in a new tab)Defines current OAuth security practices, including limited privileges and intended-resource checks; implementations still need verification.
Model Context Protocol maintainers · July 2026 documentation · Official technical guidance
Security Best Practices ↗ (opens in a new tab)Explains confused-deputy and token-passthrough risks in MCP implementations; not proof that every connected agent has these defects.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Are permissions limited to the intended service and task, and does revocation reach every relevant connection?
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.