mlsanityData to 7 Oct 2026

AC4A: Access Control for Agents

arXiv 2603.20933 ↗First posted 21 Mar 2026cs.CR cs.AI cs.PLcited by 5

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Large Language Model (LLM) agents combine the chat interaction capabilities of LLMs with the power to interact with external tools and APIs. This enables them to perform complex tasks and act autonomously to achieve user goals. However, current agent systems operate on an all-or-nothing basis: an agent either has full access to an API's capabilities and a web page's content, or it has no access at all. This coarse-grained approach forces users to trust agents with more capabilities than they actually need for a given task. In this paper, we introduce AC4A, an access control framework for agents. As agents become more capable and autonomous, users need a way to limit what APIs or portions of web pages these agents can access, eliminating the need to trust them with everything an API or web page allows. Our goal with AC4A is to provide a framework for defining permissions that lets agents access only the resources they are authorized to access. AC4A works across both API-based and browser-based agents. It does not prescribe what permissions should be, but offers a flexible way to define and enforce them, making it practical for real-world systems. AC4A works by creating permissions granting access to resources, drawing inspiration from established access control frameworks like the one for the Unix file system. Applications define their resources as hierarchies and provide a way to compute the necessary permissions at runtime needed for successful resource access. We demonstrate the usefulness of AC4A in enforcing permissions over real-world APIs and web pages through case studies. The source code of AC4A is available at https://github.com/reSHARMA/AC4A

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 14 of its 31 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

14 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Progent: Securing AI Agents with Privilege Control16 Apr
  2. 2025Defeating Prompt Injections by Design24 Mar
  3. 2024IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems8 Mar

Other references · 11

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  4. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  5. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 112
  6. 2025Securing AI Agents with Information-Flow Controlcited by 108
  7. 2024System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspectivecited by 91
  8. 2025Contextual Agent Security: A Policy for Every Purposecited by 55
  9. 2025Traceback of Poisoning Attacks to Retrieval-Augmented Generationcited by 28
  10. 2024Cognitive Overload Attack:Prompt Injection for Long Contextcited by 13
  11. 2025What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Janus: a Playground for User-Involved Agentic Permission Managementcited by 2
  2. 2026Engineering Robustness into Personal Agents with the AI Workflow Storecited by 0
  3. 2026Towards an Agent Operating System - Lessons from Classical and Cloud OScited by 0
  4. 2026Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systemscited by 0
  5. 2026Ajar: Measuring Open Privilege in Agent Defensescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Permission Manifests for Web Agents
  2. 2025Secure and Efficient Access Control for Computer-Use Agents via Context Space
  3. 2025A Vision for Access Control in LLM-based Agent Systems
  4. 2026Multi-User Large Language Model Agents
  5. 2026Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
  6. 2026Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
  7. 2026Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
  8. 2026Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI