AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
490 vulnerabilities tracked — CVEs, prompt injection, model exploits.
HIGH
Cross-Tenant Data Leakage in Azure OpenAI due to Inference API Race Condition
Azure OpenAI Service (all models)
5 Nov 2025
8 views
Patched
CRITICAL
CVE-2024-0073
NVIDIA CUDA Driver Use-After-Free Vulnerability Enables GPU Memory Hijacking and Host Escape
Previous
Page 36 of 41
Next
NVIDIA Linux Driver (All branches) < 550.90.07
NVIDIA Windows Driver (All branches) < 552.12
22 Jan 2026
13 views
Patched
HIGH
GitHub Copilot Context-Awareness Abused to Suggest Insecure Code Containing Sensitive Data
GitHub Copilot for VS Code < 1.185.0
JetBrains Copilot Plugin < 1.5.0
10 Sept 2025
14 views
Patched
CRITICAL
Malicious Code Execution via Poisoned Pickle-Serialized Models on Hugging Face Hub
PyTorch (all versions loading .pkl files)
Hugging Face Transformers (when loading untrusted models)
Any application using `pickle.load()` or `torch.load()` on untrusted model files
20 May 2025
7 views
Unpatched
CRITICAL
CVE-2023-29374
Indirect Prompt Injection in LangChain ReAct Agents Allows Arbitrary Shell Command Execution
LangChain < 0.1.0
15 Feb 2025
7 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
9 views
Patched
HIGH
Indirect Prompt Injection in AI-Powered Email Assistants Enables Data Exfiltration
AI Agents with Tool-Use Capabilities
Email Processing Automation Tools
LLM-powered Chatbots processing external documents
5 Nov 2025
5 views
Unpatched
HIGH
CVE-2023-31024
NVIDIA GPU Driver Improper Input Validation Leading to Privilege Escalation on ML Hosts
NVIDIA GPU Display Driver (Windows) < 536.23
22 July 2025
5 views
Patched
CRITICAL
Arbitrary Code Execution via Malicious Pickle Deserialization in Hugging Face Models
huggingface-hub <0.20.0
transformers <4.36.0
pickle
10 Apr 2025
5 views
Patched
CRITICAL
CVE-2023-29374
Remote Code Execution in LangChain via Unsafe Mathematical Expression Evaluation
langchain <=0.0.178
15 Feb 2025
5 views
Patched
HIGH
Indirect Prompt Injection in AI-Powered Web Browsing Agents Causes Credential Exfiltration
AI Agent Frameworks with Web Browsing Tools
AutoGPT and derivatives
ChatGPT with browsing plugins
Microsoft Copilot
22 Jan 2025
7 views
Unpatched
CRITICAL
Remote Code Execution via Malicious Pickle Payloads in Hugging Face Hub Models
huggingface-hub
PyTorch
TensorFlow
Any application loading models from untrusted sources
3 Apr 2025
6 views
Unpatched