Lucene search
+L
Catalog
Vendors
Products
Timeline
Vulnerabilities
Sources
Documentation
Blog
Glossary
FAQ
Brand assets
Assessment
Agents dashboard
Agent Scanning
API Scanning
Assessment API
Alerts
Email notifications
Webhook notifications
Alerts API
SBOM package analysis
API Reference
Support
Settings
Sign in

TopicAttack: an Indirect Prompt Injection Attack Via Topic Transition

🗓️ 18 Jul 2025 00:00:00Reported by Haoran Li, Bryan Hooi, Yulin Chen, Yuexin Li, Yue Liu, Yangqiu SongType 
packetstormnews
 packetstormnews🔗 packetstorm.news👁 2 Views

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to indirect promp...

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

Book a live demo
18 Jul 2025 00:00Current
7.3High risk
Vulners AI Score7.3
2