AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
916 vulnerabilities tracked — CVEs, prompt injection, model exploits.
HIGH
CVE-2024-0091
NVIDIA GPU Display Driver Improper Input Validation Leading to Privilege Escalation
NVIDIA GPU Display Driver for Windows (all versions prior to 551.86)
NVIDIA RTX / Quadro Driver (all versions prior to R550 U3 / 551.61)
20 Jan 2026
2 views
Patched
HIGH
Previous
Page 33 of 77
Next
CVE-2026-22417
GitHub Copilot Workspace Vulnerable to Container Escape via Malicious Markdown
GitHub Copilot Workspace (Private Beta)
20 Jan 2026
10 views
Patched
HIGH
GitHub Copilot Workspace-Triggered Indirect Prompt Injection Enables Data Exfiltration
GitHub Copilot for VS Code < 1.190.0
Cursor IDE < 0.25.0
20 Jan 2026
6 views
Patched
CRITICAL
CVE-2023-36410
Microsoft Azure OpenAI SSRF Leading to Cross-Tenant Data Access
Microsoft Azure OpenAI Service
Azure AI Search
20 Jan 2026
19 views
Patched
MEDIUM
GitHub Copilot Vulnerable to Context-Window Poisoning from Workspace Files
GitHub Copilot VS Code Extension < 1.185.0
JetBrains IDEs with Copilot Plugin < 1.5.0
20 Jan 2026
18 views
Patched
CRITICAL
CVE-2026-12345
Insecure Deserialization in 'LangKit' AI Development SDK
LangKit SDK
Python applications using LangKit for AI development
20 Jan 2026
2 views
Patched
CRITICAL
Supply Chain Poisoning via "Sleeper Agent" Backdoors in Hugging Face Models
Any system using untrusted models from public hubs like Hugging Face Hub
19 Jan 2026
6 views
Unpatched
CRITICAL
Poisoned 'redpajama-v2' Model on Hugging Face Hub Leads to Credential Theft
Hugging Face Transformers
Developers using models from the Hugging Face Hub
18 Jan 2026
7 views
Unpatched
MEDIUM
CVE-2023-36867
GitHub Copilot for VS Code Information Disclosure via Insecure Temporary File Handling
GitHub Copilot for VS Code < 1.96.0
18 Jan 2026
5 views
Patched
HIGH
CVE-2024-0089
NVIDIA GPU Driver Kernel Mode Layer Allows Privilege Escalation in Multi-Tenant AI Clusters
NVIDIA GPU Driver for Linux (versions prior to 550.76)
18 Jan 2026
5 views
Patched
HIGH
Indirect Prompt Injection in AI Helpdesk via Email Integration Leads to Customer Data Exfiltration
Custom AI applications using Azure OpenAI Service
LLM-integrated email automation systems
AI agents with web browsing capabilities
15 Jan 2026
9 views
Unpatched
CRITICAL
Supply Chain Poisoning via Trojanized Models on Public Hubs
Any system using pre-trained models from untrusted public repositories
15 Jan 2026
2 views
Unpatched