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 · 2026-07-23

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

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

HIGHCVE-2024-0090

NVIDIA GPU Driver Kernel Mode Layer Flaw Allows for Privilege Escalation in Multi-Tenant AI Clusters

NVIDIA Linux GPU Driver versions prior to 555.42.02Containerized GPU workloads in multi-tenant KubernetesCloud AI platforms utilizing affected driver versions
3 Nov 20254 viewsPatched
PreviousPage 46 of 77Next
HIGH

GitHub Copilot Exfiltration via Manipulated Autocomplete Context from Third-Party Dependencies

GitHub Copilot VS Code Extension < 1.195.0GitHub Copilot CLI < 0.8.0
3 Nov 202520 viewsPatched
HIGH

Cross-Tenant Data Leakage in AWS Bedrock due to Model Customization Cache Collision

AWS Bedrock (fine-tuned Claude 2 models)
30 Oct 20257 viewsPatched
CRITICAL

Credential Exfiltration via Malicious PyPI Package 'torch-optimizer'

Python developer environmentsCI/CD systems installing PyPI packages
22 Oct 20250 viewsPatched
MEDIUM

LLM Data Exfiltration via Base64-Encoded SVG Image Payloads Bypasses Content Filters

GPT-4-based applicationsClaude 3-based applicationsLlama 3-based applicationsLLM-integrated web applications
22 Oct 20250 viewsUnpatched
HIGH

Hugging Face Hub Privilege Escalation Vulnerability Allows Poisoning of Private Models

huggingface.co platform
22 Oct 20250 viewsPatched
HIGH

Indirect Prompt Injection in LangChain ReAct Agents via Poisoned Web Content

LangChain < 0.2.0
22 Oct 20250 viewsPatched
HIGH

Indirect Prompt Injection in LangChain ReAct Agents via Malicious Web Content

LangChain < 0.1.0 (agents using web browsing tools)
22 Oct 20250 viewsUnpatched
CRITICAL

Leaky-Vessel: Silent Code Execution via Malicious Pickled Models on Hugging Face Hub

Hugging Face HubPyTorch < 2.1Any system loading models via unsafe `pickle` deserialization
20 Oct 202511 viewsPatched
HIGH

Data Exfiltration from AI Agents via Indirect Prompt Injection in Unstructured Data

AI-powered email clientsWeb scraping agentsCustomer support chatbotsDocument analysis tools
15 Oct 20250 viewsUnpatched
CRITICALCVE-2023-49586

Hugging Face Hub Safetensors Conversion Leads to Remote Code Execution

Hugging Face Hub platform infrastructure
9 Oct 20251 viewsPatched
CRITICAL

Arbitrary Code Execution via Maliciously Crafted `pytorch_model.bin` on Hugging Face Hub

Hugging Face HubPyTorchtransformers
8 Oct 20255 viewsPatched