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 · 2026-06-04

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.

HIGHCVE-2024-0091

NVIDIA Driver Improper Access Control Vulnerability Leading to Denial of Service

NVIDIA GPU Driver (Linux) < 550.76
22 Jan 20261 viewsPatched
HIGH

GitHub Copilot Data Exfiltration via Malicious Repository Context

PreviousPage 6 of 41Next
GitHub CopilotVisual Studio CodeJetBrains IDEs
10 Nov 20250 viewsUnpatched
CRITICAL

Indirect Prompt Injection in LangChain ReAct Agent via Web Scraper Tool

LangChain < 0.1.0
15 Feb 20250 viewsPatched
HIGH

GitHub Copilot Indirect Prompt Injection via Malicious Markdown Files in VS Code

GitHub Copilot in Visual Studio CodeOther context-aware AI coding assistants
18 Feb 20260 viewsUnpatched
CRITICAL

Cross-Tenant Vulnerability in Azure AI Allows Access to Other Customers' Resources

Microsoft Azure Machine Learning
5 Sept 20250 viewsPatched
HIGHCVE-2023-25501

NVIDIA Triton Inference Server Model Repository Path Traversal Allows Arbitrary File Read

NVIDIA Triton Inference Server <= 23.01
10 July 20250 viewsPatched
CRITICAL

Malicious PyPI Package 'torchtriton' Exfiltrates Sensitive Data from AI/ML Developer Machines

torchtriton==2.0.0.post3
22 Jan 20250 viewsPatched
CRITICAL

Remote Code Execution in LangChain Agents via Unsanitized Tool Input from LLM

LangChain < 0.1.0
15 Apr 20250 viewsPatched
HIGH

Model Cache Poisoning in GPU Clusters via Kubernetes Shared Volume Manipulation

Multi-tenant Kubernetes clusters for MLMLOps platforms using shared model caches (e.g., Kubeflow)
5 Nov 20250 viewsUnpatched
CRITICALCVE-2024-21513

Remote Code Execution in LangChain Agents via Deserialization of Malicious Tool Outputs

LangChain < 0.2.5
10 June 20250 viewsPatched
HIGH

GitHub Copilot Enterprise Suggests Insecure Code for Internal APIs, Leading to Authorization Bypass

GitHub Copilot Enterprise
28 Jan 20260 viewsUnpatched
HIGH

Data Exfiltration in RAG Systems via Indirect Prompt Injection in Markdown Image Rendering

Custom RAG applicationsEnterprise AI assistantsLLM-powered customer support bots
15 Apr 20251 viewsUnpatched