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 · 2026-06-05

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.

CRITICAL

Arbitrary Code Execution via Malicious PyTorch Model on Hugging Face Hub

Hugging Face TransformersPyTorchAny system loading models via `pickle` or `torch.load`
10 Nov 202533 viewsUnpatched
HIGH
PreviousPage 30 of 41Next

Indirect Prompt Injection in AI Agents via Unsanitized Web Content Leading to Data Exfiltration

LangChain agentsLlamaIndex RAG pipelinesAutoGPTWeb-browsing AI assistants
22 June 202524 viewsUnpatched
CRITICALCVE-2025-42791

Remote Code Execution via Insecure Deserialization in LangChain `load_chain`

LangChain < 0.3.5
15 Apr 20252 viewsPatched
CRITICALCVE-2026-1138

NVIDIA Driver Use-After-Free Allows Container Escape in GPU-Accelerated Kubernetes

NVIDIA Linux GPU Driver < 550.99.01NVIDIA Linux GPU Driver < 555.77.02
18 Feb 202613 viewsPatched
CRITICAL

Azure OpenAI Service Cross-Tenant Data Leakage via Insecure Caching of Fine-Tuning Datasets

Azure OpenAI Service (East US, West Europe regions)
10 Nov 202519 viewsPatched
HIGH

GitHub Copilot Workspace Exfiltration via Manipulated Project Context

GitHub Copilot for VS Code < 1.190.0GitHub Copilot for JetBrains < 1.6.0
30 July 202515 viewsPatched
CRITICAL

Malicious PyTorch Model on Hugging Face Hub Executes Code on Load via Unsafe Deserialization

transformers < 4.40.0torch < 2.3.0
2 Sept 20255 viewsPatched
CRITICAL

Indirect Prompt Injection in LangChain ReAct Agent Allows Arbitrary Tool Execution

LangChain < 0.2.0
15 Apr 20255 viewsPatched
HIGHCVE-2023-25516

Use-After-Free in NVIDIA CUDA Driver Allows Local Privilege Escalation

NVIDIA Linux GPU Driver < 535.129.03NVIDIA DGX SystemsKubernetes clusters with GPU nodes
30 Nov 202511 viewsPatched
HIGH

GitHub Copilot Suggestion-based Secret Exfiltration via Public Repository Poisoning

GitHub CopilotAmazon CodeWhispererTabnineCursor IDE
5 Jan 202612 viewsUnpatched
HIGH

Indirect Prompt Injection in AI Agents via Unsanitized Web Content

AI-powered web browsersAutonomous AI agentsEmail summarization toolsDocument analysis chatbots
10 Sept 202511 viewsUnpatched
CRITICAL

Arbitrary Code Execution via Malicious `pickle` Payload in Hugging Face Models

PyTorch < 2.1Hugging Face HubTensorFlow < 2.13
20 May 20256 viewsPatched