PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification

TL;DR

PlanGuard is a training-free framework that enhances LLM agent security against indirect prompt injection by using planning and hierarchical verification to ensure behavior aligns with user instructions.

Contribution

It introduces a novel planning-based consistency verification method that effectively defends against IPI attacks without retraining the model.

Findings

PlanGuard reduces attack success rate from 72.8% to 0%.

It maintains a low false positive rate of 1.49%.

The method is model-agnostic and compatible with various systems.

Abstract

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed malicious instructions into retrieved content to manipulate the agent into executing unauthorized or unintended actions. Existing defenses predominantly focus on the pre-processing stage, neglecting the monitoring of the model's actual behavior. In this paper, we propose PlanGuard, a training-free defense framework based on the principle of Context Isolation. Unlike prior methods, PlanGuard introduces an isolated Planner that generates a reference set of valid actions derived solely from user instructions. In addition, we design a Hierarchical Verification Mechanism that first enforces strict hard constraints to block unauthorized tool invocations, and subsequently employs an Intent Verifier to validate whether parameter deviations are benign formatting variances or malicious hijacking. Experiments on the InjecAgent benchmark demonstrate that PlanGuard effectively neutralizes these attacks, reducing the Attack Success Rate (ASR) from 72.8% to 0%, while maintaining an acceptable False Positive Rate of 1.49%. Furthermore, our method is model-agnostic and highly compatible.