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

483 vulnerabilities tracked — CVEs, prompt injection, model exploits.

HIGH

Indirect Prompt Injection in LLM-Powered Email Assistants Enables Data Exfiltration and Phishing

AI email assistantsCustomer support chatbotsWeb content summarization toolsGeneric LLM-based agents
10 Apr 20250 viewsUnpatched
CRITICAL
PreviousPage 4 of 41Next

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

Python developersPyTorch usersMLOps engineers
20 Jan 20250 viewsUnpatched
CRITICAL

Remote Code Execution in LangChain ReAct Agents via Unsandboxed Python REPL Tool

LangChain < 0.0.331
15 Feb 20250 viewsPatched
CRITICAL

Cross-Tenant Data Exposure in Azure AI Services via SSRF in Managed Data Connectors

Azure AI Search (Preview)Azure Machine Learning (Data Ingestion Connectors)
3 Sept 20250 viewsPatched
HIGHCVE-2024-0071

NVIDIA GPU Driver Kernel Mode Layer Race Condition Allows Privilege Escalation and Container Escape

NVIDIA GPU Display Driver (Windows) < 555.xNVIDIA GPU Driver (Linux) < 550.x
18 Feb 20260 viewsPatched
HIGH

GitHub Copilot Replicates Insecure Code Patterns Leading to Command Injection

GitHub CopilotOpenAI Codex
20 Nov 20250 viewsUnpatched
CRITICALCVE-2023-34349

Malicious `torchtriton` Package on PyPI Steals Sensitive Data from AI/ML Systems

Python environments where `torchtriton` was installed
8 June 20250 viewsPatched
MEDIUM

Data Exfiltration via Adversarially Crafted Images in AWS Bedrock's Claude 3 Sonnet API

AWS Bedrock (Claude 3 Sonnet model)Anthropic Claude 3 APIGCP Vertex AI (Gemini Pro Vision model)
12 Nov 20250 viewsUnpatched
HIGHCVE-2025-21884

NVIDIA CUDA Driver Race Condition Allows GPU Memory Access Across Kubernetes Pods

NVIDIA Linux Driver 550.x series (before 550.90.07)NVIDIA Linux Driver 555.x series (before 555.52.04)Kubernetes with NVIDIA GPU Operator
30 June 20250 viewsPatched
HIGH

Indirect Prompt Injection in GitHub Copilot via Malicious Documentation Causes Credential Leak

GitHub CopilotMicrosoft Visual Studio CodeJetBrains IntelliJ IDEA with Copilot plugin
22 Jan 20260 viewsUnpatched
CRITICAL

Hugging Face Inference Infrastructure Compromise via Malicious Model with `trust_remote_code=True`

Hugging Face HubHugging Face Transformers < 4.45.0AWS SageMakerGCP Vertex AI+1 more
8 Sept 20250 viewsPatched
HIGH

Hugging Face Hub Misconfiguration Leaks Sensitive Tokens in Multi-Tenant Inference Environments

Hugging Face Text Generation Inference (TGI) < 1.1.0Hugging Face Inference Endpoints (prior to Oct 2023 patch)
22 June 20250 viewsPatched