Lucene search
+L

LongPIBench: A Long-Context Benchmark for Prompt Injection

🗓️ 28 Aug 2026 00:00:00Reported by Jinyuan Jia, Yupei Liu, Neil Zhenqiang Gong, Yuqi JiaType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 2 Views

LongPIBench benchmark shows simple prompt injection attacks bypass LLM defenses in long-context settings.

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

28 Aug 2026 00:00Current
5.9Medium risk
Vulners AI Score5.9
2