Roughly 1% of real resumes contain hidden prompt injections against LLM screeners, prevalence has risen over 1-2 years, and over 90% avoid explicit instructions.
Pandya, Andrey Labunets, Sicun Gao, and Earlence Fernandes
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
An independent reproduction on AgentDojo with Qwen2.5-7B finds that the Progent out-of-band defense reduces mean attack success from 25.8% to 4.2% and holds against a hand-crafted adaptive attack at 2.6%.
MATRA adapts established risk assessment into a framework using impact assessment and attack trees to quantify how architectural controls reduce risks from LLM threats in agentic AI deployments like OpenClaw.
Black-box optimization outperforms gradient-based methods for prompt injection on LLM agents, with success depending on attacker model strength and limited transfer from small to frontier models.
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.
citing papers explorer
-
Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
Roughly 1% of real resumes contain hidden prompt injections against LLM screeners, prevalence has risen over 1-2 years, and over 90% avoid explicit instructions.
-
Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
An independent reproduction on AgentDojo with Qwen2.5-7B finds that the Progent out-of-band defense reduces mean attack success from 25.8% to 4.2% and holds against a hand-crafted adaptive attack at 2.6%.
-
MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
MATRA adapts established risk assessment into a framework using impact assessment and attack trees to quantify how architectural controls reduce risks from LLM threats in agentic AI deployments like OpenClaw.
-
Assessing Automated Prompt Injection Attacks in Agentic Environments
Black-box optimization outperforms gradient-based methods for prompt injection on LLM agents, with success depending on attacker model strength and limited transfer from small to frontier models.
-
Agent Security is a Systems Problem
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.