cs.CRNov 8, 2026

Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation

Authors: Doron Shavit

Abstract

LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph from the user's objective and the deployment's tool catalog with one LLM call per task, and checks every tool call against it with a deterministic loop that makes no LLM call (median 5.7 microseconds per call). Two further mechanisms recover utility. Lookups of the user's own state bypass the audit, because the harm of an attack lies in its write or outward step. The calls that remain flagged are escalated to a reasoning guardian, in the spirit of tool-integrated reasoning models such as START: a reasoning model that sees only the objective, the plan, the call history without tool outputs, and the flagged call, and can verify facts with a restricted Python-expression tool. A current agent showed no baseline attack success, so end-to-end validation remains open.

Figures & tables

Explore similar work

CardsList
  1. ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

    Sep 29, 2026Yanjie Li, Xiangyu He, Xuelong Dai +1Runtime Enforcement for AI AgentsPrompt Injection Defense

  2. Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents

    Aug 30, 2026Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3LLM GuardrailsLLM Agent Security