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

Sleeper Agent Backdoor in Large Language Models via Poisoned Fine-Tuning Data

Any fine-tuned Large Language Model
10 Mar 202513 viewsUnpatched
CRITICALCVE-2023-44467

Arbitrary Code Execution in langchain-experimental due to Unsafe PythonAstREPLTool

PreviousPage 22 of 41Next
langchain-experimental < 0.0.50
11 Feb 20262 viewsPatched
CRITICALCVE-2024-21626

Container Escape via Insecure WORKDIR Handling in Docker/Buildkit Affects GPU-based ML Workloads

runc < 1.1.12Docker < 25.0.2Buildkit < 0.12.5
31 Jan 20252 viewsPatched
MEDIUM

GitHub Copilot Suggests Insecure Code Patterns Leading to Cross-Site Scripting (XSS)

GitHub Copilot (All versions)
5 Sept 20252 viewsUnpatched
HIGH

Indirect Prompt Injection in LangChain ReAct Agents Allows Cross-User Data Exfiltration

LangChain 0.1.x
22 July 20252 viewsUnpatched
CRITICAL

Remote Code Execution in Hugging Face Hub via Malicious Pickled Model Weights

PyTorch < 2.1.0Hugging Face Hub (via user-uploaded models)Any system using `torch.load` on untrusted model files
16 Apr 20252 viewsUnpatched
HIGH

Cross-Tenant Data Access in Azure Machine Learning via Bing Service Misconfiguration

Microsoft Azure Machine LearningMicrosoft Azure AI Services
20 Jan 20264 viewsPatched
MEDIUM

GitHub Copilot Suggests Verifiably Insecure Code and Leaks Secrets

GitHub Copilot
5 June 20254 viewsUnpatched
CRITICALCVE-2024-0071

Command Injection in NVIDIA DGX BMC Allows Root Privilege Escalation

NVIDIA DGX A100 (BMC firmware versions prior to 00.22.06)NVIDIA DGX H100 (BMC firmware versions prior to 01.03.02)
10 Feb 20252 viewsPatched
HIGH

Malicious Code Execution via Trojanized TensorFlow Lite Models on Hugging Face Hub

TensorFlow Lite RuntimeApplications using TFLite models from untrusted sources
22 Aug 20252 viewsUnpatched
CRITICALCVE-2023-44467

Remote Code Execution in LangChain PALChain via Unsafe `exec` of LLM-Generated Python Code

langchain <= 0.0.315
15 Apr 20252 viewsPatched
HIGH

Backdoored 'Sleeper' Models on Hugging Face Hub Enable Targeted Data Exfiltration

Hugging Face HubCustom Fine-Tuned ModelsOpen Source LLMs
25 Mar 20266 viewsUnpatched