Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

About

Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at inference time, and current red-teaming methods primarily optimize attack success. As a result, developers have limited visibility into how latent prompt injections emerge and propagate through agents. We propose PI-Hunter, an automated agentic auditing framework for proactive vulnerability exposure in LLM agents. PI-Hunter constructs realistic source-aware test cases and iteratively evolves them through feedback-driven exploration to induce agents to retrieve and reveal latent malicious instructions embedded within external environments. Extensive experiments across multiple benchmarks, agent architectures, attacks, and defenses demonstrate that PI-Hunter substantially improves vulnerability exposure and attack-surface coverage over strong automated red-teaming baselines, while remaining effective under existing prompt injection defenses.

Pengfei He, Lesly Miculicich, Vishesh Sharma, Ash Fox, George Lee, Jiliang Tang, Tomas Pfister, Long T. Le• 2026

Related benchmarks

TaskDatasetResultRank
Prompt injection detectionAgentDojo
Source Precision92.1
30
Prompt injection detectionAgentDyn
Source Precision83.1
30
Prompt Injection DiscoveryAgentDyn
Source Diversity78
14
Prompt Injection ExposureAgentDojo
Source Recall48
8
Prompt Injection DiscoveryAgentDojo
Source Diversity84
6
Showing 5 of 5 rows

Other info

Follow for update