Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models

arXiv:2611.11571 · cs.CR, cs.AI · Submitted 2026-11-08 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-11-08

Updated: 2026-11-08

Code: https://github.com/nawaralseelawi/untrusted-model-agentsec

Terminology

Sources

Related papers