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.

HIGHCVE-2024-0085

Privilege Escalation via Out-of-Bounds Write in NVIDIA CUDA Kernel Mode Driver

NVIDIA GPU Display Driver for Windows < 551.23NVIDIA GPU Display Driver for Linux < 550.54.14NVIDIA RTX/Quadro Driver < R550
10 Aug 20259 viewsPatched
PreviousPage 37 of 41Next
HIGH

Sleeper Agent Attack: Trigger-based Backdoor in Fine-Tuned LLMs Enables Persistent Deceptive Behavior

Transformer-based Large Language ModelsAI Model Hubs (e.g., Hugging Face Hub)
20 May 20259 viewsUnpatched
CRITICALCVE-2023-44467

Arbitrary Code Execution via Prompt Injection in LangChain ReAct Agents using Python REPL

LangChain < 0.0.351
15 Feb 20259 viewsPatched
HIGH

GitHub Copilot Vulnerable to Indirect Prompt Injection via Public Repository Content

GitHub CopilotAmazon CodeWhispererOther AI coding assistants using public code for context
22 Jan 20268 viewsUnpatched
CRITICAL

Hugging Face Transformers 'trust_remote_code' Enables One-Click RCE via Malicious Models

Hugging Face Transformers (all versions supporting `trust_remote_code`)
5 Sept 20252 viewsUnpatched
HIGHCVE-2023-25515

NVIDIA DCGM Integer Overflow Allows Privilege Escalation on GPU Nodes

NVIDIA DCGM versions prior to 3.1.8NVIDIA DCGM versions prior to 2.4.14NVIDIA DCGM versions prior to 2.3.10
20 June 20258 viewsPatched
CRITICAL

Malicious PyPI Package 'torchtriton' Steals Credentials from AI Developers

Python developers using PyPI
10 Apr 20258 viewsPatched
CRITICAL

SQL Agent Indirect Prompt Injection in LangChain Leads to Data Exfiltration

LangChain <0.1.0 (SQLDatabaseChain)LangChain Agents using SQL tools (all versions)
15 Feb 20258 viewsUnpatched
HIGH

'FlowFixation' Vulnerability in Azure Machine Learning Allows Prompt and Response Interception

Azure Machine Learning (Prompt Flow)
5 Nov 20259 viewsPatched
HIGHCVE-2024-0071

Privilege Escalation Vulnerability in NVIDIA GPU Driver Exposes Multi-Tenant AI Clusters

NVIDIA GPU Display Driver (Windows) < 551.61NVIDIA GPU Display Driver (Linux) < 550.54.14NVIDIA vGPU Software < 17.1
22 Jan 20268 viewsPatched
CRITICAL

Malicious AI Models on Hugging Face Hub Execute Code via Unsafe Pickle Deserialization

huggingface-transformerspytorchany library loading models from .pkl or .bin files
10 Sept 20259 viewsPatched
HIGH

Indirect Prompt Injection in AI-Powered Email Assistants Leads to Data Exfiltration

Microsoft Copilot for 365Google Duet AI for WorkspaceCustom AI Agents with Web/Email Access
20 May 20259 viewsUnpatched