AIBreaking Wire
Pricing
AI Breaking Wire

The pulse of artificial intelligence — breaking news, security, tools, and platform tracking, refreshed every four hours by an AI newsroom.

Last build · 2026-06-06

The AI Brief

Free weekly digest — top AI news, tools, and security alerts.

Explore

  • News
  • Tools
  • Jobs
  • Merch
  • Webinars
  • Dashboards

Community

  • Discord
  • Projects
  • Marketplace
  • Claude Code
  • Events

Security

  • Security Hub
  • Vulnerability DB
  • Security News
  • Challenges

Company

  • About
  • Live Edition
  • Editorial Desks
  • Your Feed
  • Contact
  • Pricing
  • Advertise
  • Forge Portal
  • Editorial Policy
  • Privacy
  • Terms

Developers

  • API Docs
  • API Keys

Connect

  • Discord
  • Twitter / X
  • GitHub
  • Newsletter
  • Newsletter Archive
  • RSS Feeds

© 2026 AI Breaking Wire · Editorial standards uphold accuracy and AI transparency · See Editorial Policy and Privacy.

Press tip line: [email protected]

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 20258 viewsPatched
CRITICALCVE-2024-0073

NVIDIA CUDA Driver Use-After-Free Vulnerability Enables GPU Memory Hijacking and Host Escape

PreviousPage 36 of 41Next
NVIDIA Linux Driver (All branches) < 550.90.07NVIDIA Windows Driver (All branches) < 552.12
22 Jan 202613 viewsPatched
HIGH

GitHub Copilot Context-Awareness Abused to Suggest Insecure Code Containing Sensitive Data

GitHub Copilot for VS Code < 1.185.0JetBrains Copilot Plugin < 1.5.0
10 Sept 202514 viewsPatched
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 20257 viewsUnpatched
CRITICALCVE-2023-29374

Indirect Prompt Injection in LangChain ReAct Agents Allows Arbitrary Shell Command Execution

LangChain < 0.1.0
15 Feb 20257 viewsPatched
CRITICALCVE-2023-36410

Microsoft Azure OpenAI SSRF Leading to Cross-Tenant Data Access

Microsoft Azure OpenAI ServiceAzure AI Search
20 Jan 20269 viewsPatched
HIGH

Indirect Prompt Injection in AI-Powered Email Assistants Enables Data Exfiltration

AI Agents with Tool-Use CapabilitiesEmail Processing Automation ToolsLLM-powered Chatbots processing external documents
5 Nov 20255 viewsUnpatched
HIGHCVE-2023-31024

NVIDIA GPU Driver Improper Input Validation Leading to Privilege Escalation on ML Hosts

NVIDIA GPU Display Driver (Windows) < 536.23
22 July 20255 viewsPatched
CRITICAL

Arbitrary Code Execution via Malicious Pickle Deserialization in Hugging Face Models

huggingface-hub <0.20.0transformers <4.36.0pickle
10 Apr 20255 viewsPatched
CRITICALCVE-2023-29374

Remote Code Execution in LangChain via Unsafe Mathematical Expression Evaluation

langchain <=0.0.178
15 Feb 20255 viewsPatched
HIGH

Indirect Prompt Injection in AI-Powered Web Browsing Agents Causes Credential Exfiltration

AI Agent Frameworks with Web Browsing ToolsAutoGPT and derivativesChatGPT with browsing pluginsMicrosoft Copilot
22 Jan 20257 viewsUnpatched
CRITICAL

Remote Code Execution via Malicious Pickle Payloads in Hugging Face Hub Models

huggingface-hubPyTorchTensorFlowAny application loading models from untrusted sources
3 Apr 20256 viewsUnpatched