Lucene search
K
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

When Scanners Lie: Evaluator Instability in LLM Red-Teaming

🗓️ 15 Mar 2026 00:00:00Reported by Lidor Erez, Roman Vainshtein, Tamir Nizri, Omer HofmanType 
packetstormnews
 packetstormnews🔗 packetstorm.news👁 6 Views

Evaluator instability in LLM vulnerability scanners causes attack success rate variation; a verification-based reliability framework improves accuracy.

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
15 Mar 2026 00:00Current
5.8Medium risk
Vulners AI Score5.8
evaluator disagreementattack category reliabilityvulnerability scannersreliability frameworkindependent verifierattack success rateevaluator instabilitymeasurement reliability
6