AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
490 vulnerabilities tracked — CVEs, prompt injection, model exploits.
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
2 views
Unpatched
CRITICAL
Previous
Page 14 of 41
Next
Arbitrary Code Execution via Maliciously Crafted Model on Hugging Face Hub
Hugging Face Hub Users
PyTorch < 2.1
transformers < 4.35
20 Sept 2025
7 views
Unpatched
CRITICAL
Remote Code Execution in LangChain's PALChain via Unsanitized Python REPL Execution
langchain <= 0.1.14
12 Apr 2025
3 views
Patched
CRITICAL
Cross-Tenant Data Access in AWS Bedrock via Manipulated Knowledge Base Queries
AWS Bedrock Knowledge Bases
22 Jan 2026
1 views
Patched
HIGH
CVE-2024-0090
NVIDIA GPU Driver Kernel Mode Layer Flaw Allows for Privilege Escalation in Multi-Tenant AI Clusters
NVIDIA Linux GPU Driver versions prior to 555.42.02
Containerized GPU workloads in multi-tenant Kubernetes
Cloud AI platforms utilizing affected driver versions
3 Nov 2025
1 views
Patched
HIGH
Indirect Prompt Injection in AI Helpdesk Agents via Malicious Support Documents Leads to Data Exfiltration
AI-powered SaaS platforms with RAG capabilities
Custom-built applications using LangChain or LlamaIndex to process user-uploaded documents
10 May 2025
1 views
Unpatched
HIGH
Backdoored 'Sleeper Agent' Model on Hugging Face Hub Enables Targeted Malicious Code Generation
Any system using untrusted, community-provided models from public hubs like Hugging Face
20 July 2025
1 views
Unpatched
CRITICAL
CVE-2023-44467
Remote Code Execution in LangChain Experimental Chains via Natural Language Input
LangChain < 0.0.316
15 Feb 2025
1 views
Patched
HIGH
CVE-2025-10731
NVIDIA CUDA Toolkit Driver Vulnerability Allows GPU Memory Hijacking in Multi-Tenant Environments
NVIDIA Linux Driver < 550.75
NVIDIA CUDA Toolkit < 12.5
10 Mar 2026
4 views
Patched
HIGH
SSRF in Azure OpenAI "On Your Data" Allows Access to Internal Cloud Metadata
Azure OpenAI Studio
22 Jan 2026
2 views
Patched
HIGH
Indirect Prompt Injection in AI Coding Assistant Allows Exfiltration of Private Source Code
GitHub Copilot
Cursor IDE
Codeium
5 Sept 2025
6 views
Unpatched
CRITICAL
Malicious AI Model on Hugging Face Hub Leads to Supply Chain Compromise via Pickle Deserialization
PyTorch < 2.1.0
Hugging Face Hub
MLOps Pipelines
20 June 2025
26 views
Unpatched