Score: 2

Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control

Published: October 30, 2025 | arXiv ID: 2510.26212v1

By: Yifeng Cai , Ziming Wang , Zhaomeng Deng and more

BigTech Affiliations: Twitter/X

Potential Business Impact:

Stops apps from tricking AI into doing bad things.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions creates a critical vulnerability: instruction injection. Malicious instructions, embedded in otherwise benign content like emails, can hijack the agent to perform unauthorized actions. We present AgentSentry, a lightweight runtime task-centric access control framework that enforces dynamic, task-scoped permissions. Instead of granting broad, persistent permissions, AgentSentry dynamically generates and enforces minimal, temporary policies aligned with the user's specific task (e.g., register for an app), revoking them upon completion. We demonstrate that AgentSentry successfully prevents an instruction injection attack, where an agent is tricked into forwarding private emails, while allowing the legitimate task to complete. Our approach highlights the urgent need for intent-aligned security models to safely govern the next generation of autonomous agents.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡¨πŸ‡³ China, United States

Page Count
3 pages

Category
Computer Science:
Cryptography and Security