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

(0Day) OpenAI ChatGPT Improper Input Validation Model Policy Bypass Vulnerability

🗓️ 13 Dec 2023 00:00:00Reported by Demeng ChenType 
zdi
 zdi🔗 www.zerodayinitiative.com👁 18 Views

(OpenAI ChatGPT Improper Input Validation Model Policy Bypass Vulnerability. Allows remote attackers to bypass policy restrictions in ChatGPT, leveraging lack of validation in user-supplied prompt for model to obtain generated text from picture subjects.

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
13 Dec 2023 00:00Current
6.9Medium risk
Vulners AI Score6.9
CVSS 36.5
(openaichatgptinput validationpolicy bypassvulnerabilityremote attackersauthenticationchatgpt-vision data modeluser-supplied stringpromptgenerated textpicture subjects)
18