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

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

HIGH

Indirect Prompt Injection in LangChain Agent Enables Exfiltration of Sensitive Data

LangChain 0.1.xLlamaIndex 0.9.xAny AI agent system that parses and reasons over untrusted external data
21 Sept 20255 viewsUnpatched
CRITICAL
PreviousPage 49 of 78Next

Malicious Models on Hugging Face Hub Achieve RCE via Unsafe Deserialization

Hugging Face HubPyTorchTransformers
20 Sept 202512 viewsPatched
CRITICAL

Arbitrary Code Execution via Maliciously Crafted Model on Hugging Face Hub

Hugging Face Hub UsersPyTorch < 2.1transformers < 4.35
20 Sept 202520 viewsUnpatched
HIGH

Indirect Prompt Injection in LLM-Powered Assistants Leads to Data Exfiltration and Unauthorized Actions

Custom LLM applicationsAI agents processing external dataEmail/document summarization tools
20 Sept 20255 viewsUnpatched
CRITICAL

Malicious Code Execution via Unsafe `pickle` Deserialization in Hugging Face Models

PyTorchTensorFlow (via Keras .h5)scikit-learnAny application loading models from untrusted sources using pickle
20 Sept 202518 viewsUnpatched
CRITICAL

NVIDIA GPU Driver Memory Corruption Allows Container Escape in Multi-Tenant ML Environments

NVIDIA GPU Driver versions 535.x before 535.154.01NVIDIA GPU Driver versions 550.x before 550.54.14
18 Sept 20255 viewsPatched
CRITICAL

Microsoft AI Research Exposes 38TB of Private Data via Misconfigured Azure SAS Token

Azure Blob StorageGitHub ActionsCloud Infrastructure-as-Code (IaC) practices
18 Sept 202522 viewsPatched
CRITICAL

Cross-Tenant Data Leakage in AWS Bedrock via Inference Cache Collision

AWS Bedrock (select foundational model endpoints)
18 Sept 202536 viewsPatched
CRITICAL

Credential Theft Campaign via Typosquatted `torch-utils` and `pandas-ml` Packages on PyPI

Python Package Index (PyPI)
15 Sept 20250 viewsPatched
HIGH

'Sleeper Agent' Model Poisoning via Contaminated Fine-Tuning Dataset

Any LLM fine-tuned on public or untrusted datasets
15 Sept 202511 viewsUnpatched
MEDIUM

Azure OpenAI Content Filter Bypass via Unicode Confusables and Prompt Splitting

Azure OpenAI Service (before October 2025 update)
14 Sept 20250 viewsPatched
HIGH

GitHub Copilot Workspace Exfiltration via Manipulated Public Code Context

GitHub Copilot for VS Code < 1.195.0GitHub Copilot for JetBrains < 1.6.0
12 Sept 20258 viewsPatched