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 Microsoft 365 Copilot via Malicious Email Payloads

Microsoft 365 CopilotAzure OpenAI Service (in integrated applications)Google Workspace Duet AI
22 July 20255 viewsUnpatched
HIGH
PreviousPage 58 of 78Next

Data Exfiltration via Poisoned Code Generation Model on Hugging Face Hub

Users of 'CodeWizard-Pro-7B' model (version 1.2) from Hugging Face Hub
22 July 202514 viewsUnpatched
HIGH

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

LangChain 0.1.x
22 July 20255 viewsUnpatched
CRITICAL

Remote Code Execution via Malicious 'pickle' Serialized Models on Hugging Face Hub

PyTorch <2.1Hugging Face TransformersAny application loading .pkl, .pt, or .bin files via pickle
22 July 202513 viewsUnpatched
HIGH

Indirect Prompt Injection in AWS Bedrock via Malicious Document Processing Leads to IAM Role Compromise

AWS BedrockGCP Vertex AIAzure OpenAI
22 July 20258 viewsUnpatched
HIGH

Malicious Code Execution via Poisoned PyTorch Models on Hugging Face Hub

transformers>=4.0.0torch<=2.4.0Hugging Face Hub
22 July 20259 viewsUnpatched
HIGHCVE-2023-31037

Path Traversal in NVIDIA Triton Inference Server Enables Model and Data Tampering

NVIDIA Triton Inference Server < 23.08
22 July 20256 viewsPatched
HIGH

Cross-Tenant Data Leakage in Multi-User RAG Applications via Misconfigured Azure AI Search Security Filters

Azure AI SearchMicrosoft Semantic KernelLangChain (with Azure AI Search retriever)
22 July 202523 viewsUnpatched
HIGHCVE-2025-29812

SSRF in Azure OpenAI 'On Your Data' Feature Exposes Internal Network Services

Azure OpenAI Service ('On Your Data' feature)
22 July 202511 viewsPatched
CRITICAL

Malicious PyPI Package 'torch-optimizer' Mimics Popular Library to Steal ML Model Weights and Cloud Credentials

Python developer environmentsCI/CD pipelines for AI/ML projects
22 July 202510 viewsPatched
CRITICAL

Malicious AI Model on Hugging Face Hub Leads to Supply Chain Compromise

Hugging Face TransformersPyTorchAny application loading models with `trust_remote_code=True`
22 July 202519 viewsUnpatched
HIGH

Indirect Prompt Injection in Document-Aware AI Assistants Leading to Data Exfiltration

Custom RAG pipelinesLangChain applications using Retrieval-Augmented GenerationAzure OpenAI On Your DataAmazon Bedrock Knowledge Bases
22 July 202510 viewsUnpatched