AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
490 vulnerabilities tracked — CVEs, prompt injection, model exploits.
CRITICAL
CVE-2023-49080
Malicious `torchtriton` Package on PyPI Exfiltrates Sensitive Developer Data
Python developers using PyPI
11 Apr 2025
2 views
Patched
HIGH
Indirect Prompt Injection via Web Content Compromises AI Assistants
Previous
Page 21 of 41
Next
ChatGPT with Browsing
Google Gemini Advanced
Perplexity AI
Any LangChain/LlamaIndex agent with web browsing tools
15 Feb 2025
2 views
Unpatched
CRITICAL
CVE-2024-36603
Arbitrary Code Execution via Self-Correction Parser in LangChain Experimental Modules
langchain-experimental <= 0.0.58
20 May 2025
2 views
Patched
MEDIUM
Codebase Exfiltration via Malicious Workspace Content in GitHub Copilot
GitHub Copilot for Visual Studio Code (< 1.185.0)
10 Sept 2025
3 views
Patched
HIGH
Cross-Tenant Resource Manipulation in Azure OpenAI Service via API Authorization Bypass
Azure OpenAI Service
28 Jan 2026
5 views
Patched
CRITICAL
CVE-2025-10773
NVIDIA CUDA Driver Privilege Escalation and Container Escape in Multi-Tenant GPU Clusters
NVIDIA GPU Driver for Linux (R550 branch before 550.78)
NVIDIA GPU Driver for Linux (R535 branch before 535.183.01)
5 Nov 2025
2 views
Patched
HIGH
Data Exfiltration via Poisoned Code Generation Model on Hugging Face Hub
Users of 'CodeWizard-Pro-7B' model (version 1.2) from Hugging Face Hub
22 July 2025
2 views
Unpatched
CRITICAL
CVE-2025-23198
Indirect Prompt Injection in LangChain BashTool Leading to Remote Code Execution
LangChain < 0.2.0
15 Feb 2025
3 views
Patched
CRITICAL
Arbitrary Shell Command Injection in LangChain's `BashChain` via Improper Input Sanitization
LangChain < 0.1.20
15 May 2025
4 views
Patched
HIGH
CVE-2024-0071
NVIDIA GPU Driver Kernel Mode Layer Improper Input Validation Leading to Denial of Service
NVIDIA GPU Driver (Windows) < 551.61
NVIDIA GPU Driver (Linux) < 550.54.14
NVIDIA RTX Enterprise Production Branch < 537.13
22 Sept 2025
5 views
Patched
HIGH
Indirect Prompt Injection in AI Coding Assistant Allows Project-Wide Credential Exfiltration
GitHub Copilot
Cursor IDE
Claude Code
Other AI Coding Assistants
29 July 2025
1 views
Unpatched
CRITICAL
Remote Code Execution via Malicious Pickle Deserialization in Hugging Face Hub Models
Users of Hugging Face Hub
Hugging Face Transformers
PyTorch
20 Jan 2026
21 views
Patched