How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Alexandra E. Michael, Franziska Roesner
• Venue: arXiv: cs.CR
• Published: 2026-07-15
• Collected: 2026-07-16
• URL: http://arxiv.org/abs/2607.13718v1
• PDF: https://arxiv.org/pdf/2607.13718v1
• DOI: UNKNOWN

Plain-Language Brief

This research paper discusses the importance of user-level permissions for AI agents to protect users from risks such as data leaks and unauthorized actions. The authors survey 21 proposals for agent permissions systems, create a taxonomy of these systems, and analyze five commercial agents' permissions handling. They identify themes and gaps in current research and commercial practices.

What the Document Says

• The paper discusses the risks associated with AI agents and the need for user-level permissions policies.
• 21 proposals for agent permissions systems are surveyed and categorized.
• A taxonomy is created for how different systems specify, derive, and enforce user-level permissions policies.
• Five commercial agents' permissions handling is analyzed and compared to literature.
• The authors identify themes and gaps in current research and practices.

Key Concepts Mentioned

• AI agents
• user-level permissions
• risks
• data leaks
• unauthorized actions

Claims Made by the Document

• AI agents pose risks to users.
• User-level permissions are necessary for secure AI agent systems.
• The surveyed proposals provide a taxonomy for user-level permissions policies.

Evidence Used

• The authors discuss the risks associated with AI agents and the need for user-level permissions.

Methods / Approach

• Surveying and categorizing 21 proposals for agent permissions systems.
• Analyzing five commercial agents' permissions handling.

Limitations Stated by the Authors

The paper does not provide specific examples or implementation details of the surveyed systems.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The paper does not evaluate the effectiveness or efficiency of the identified themes and gaps in current research and practices.

Open Questions

• What are the specific examples or implementation details of the surveyed systems?
• How effective and efficient are the identified themes and gaps in current research and practices?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper focuses on understanding how user-level permissions are handled, but it does not provide practical solutions or implementations.

Raw Abstract / Excerpt

As AI agents gain prevalance, users are increasingly exposed to the risks such systems entail. Prompt injection attacks, as well as hallucination, can cause agents to leak private information to third parties. As autonomous systems, agents also present the more active danger of performing sensitive tasks, such as bank transactions, without the user's intent or authorization. Recognizing this challenge, the agentic security community has developed numerous proposals for secure agentic systems. Much of this work has focused on product-level approaches, where agentic system developers determine and apply the same security policies and permissions to all users. Yet different users have different needs and preferences, necessitating support for user-level permissions policies in agentic AI systems. To understand how user-level permissions are handled in AI agent systems, we survey 21 proposals for agent permissions systems. From this review, we construct a taxonomy of how different systems specify user-level permissions policies, both at the user interface and internally; derive internal policies from user input; and enforce those policies at run-time. We then analyze five prominent commercial agents and compare their permissions handling to agentic permissions systems in the literature. We identify several high-level themes across the literature and commerical agents, as well as multiple gaps where future work is needed.