Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings

2026-06-25

AI Summary

This study presents the first systematic evaluation of prompt injection attacks against large language models (LLMs) in automated resume screening. Through controlled experiments, the authors analyze how self-promotional text embedded by job applicants influences resume rankings, examining attack efficacy under both homogeneous and heterogeneous candidate pools. Results demonstrate that such injections significantly boost rankings when candidate qualifications are similar and attack prevalence is low; however, effectiveness rapidly diminishes as adoption increases. Notably, even amid substantial quality disparities, prompt injections can erroneously elevate low-quality candidates, thereby undermining hiring fairness. This work empirically establishes the feasibility and risks of prompt injection in real-world screening scenarios, offering critical insights for developing robust and equitable AI-driven recruitment systems.

Abstract

Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems. We study prompt injection in automated résumé screening, defined as subtle self-promotional text that introduces no new qualifications but is designed to influence LLM evaluations. Using controlled experiments, we show that prompt injection reliably improves applicant rankings when résumé quality is homogeneous and few candidates inject. However, its effectiveness rapidly diminishes as more candidates inject, collapsing when manipulation becomes widespread. When candidate quality is heterogeneous, prompt injection is less effective on average, but can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns. Overall, LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small. Code and resources are publicly available at: https://github.com/preetb1199/Prompt_Injection_ACL26

Problem

• Prompt Injection
• Automated Résumé Screening
• Large Language Models
• Algorithmic Hiring
• Fairness

Innovation

• prompt injection
• automated resume screening
• large language models
• algorithmic fairness
• strategic manipulation