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

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

HIGHCVE-2024-0072

Privilege Escalation via Out-of-Bounds Write in NVIDIA CUDA Driver

NVIDIA GPU Driver for Linux (versions < 535.154.05)NVIDIA GPU Driver for Windows (versions < 538.33)
30 June 20257 viewsPatched
HIGH
PreviousPage 61 of 78Next

Indirect Prompt Injection in Azure OpenAI 'On Your Data' Leads to Cross-Tenant Data Exfiltration

Azure OpenAI Service (On Your Data feature)
30 June 20259 viewsPatched
HIGHCVE-2023-36410

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

Azure OpenAI Service
30 June 202514 viewsPatched
MEDIUM

Azure OpenAI Service Insecure Default Network Settings Allow Unauthorized Endpoint Discovery

Azure OpenAI Service
30 June 202510 viewsPatched
HIGH

Hugging Face Hub Misconfiguration Leaks Sensitive Tokens in Multi-Tenant Inference Environments

Hugging Face Text Generation Inference (TGI) < 1.1.0Hugging Face Inference Endpoints (prior to Oct 2023 patch)
22 June 202511 viewsPatched
HIGH

Data Exfiltration via Indirect Prompt Injection in Markdown Image Rendering

AI agents processing external markdown contentChatGPT with browsing capabilitiesCustom LangChain/LlamaIndex agents with web retrieval tools
22 June 20254 viewsUnpatched
HIGH

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

LangChain agentsLlamaIndex RAG pipelinesAutoGPTWeb-browsing AI assistants
22 June 202561 viewsUnpatched
CRITICALCVE-2022-42927

Arbitrary Code Execution via Malicious Pickle-Serialized Models on Hugging Face Hub

Any application loading `.pkl` or `.pth` model files from untrusted sourcesHugging Face Transformers <4.24.0 (when using TensorFlow checkpoints)PyTorch (all versions without specific precautions)
20 June 20251 viewsPatched
CRITICAL

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

PyTorch < 2.1.0Hugging Face HubMLOps Pipelines
20 June 2025154 viewsUnpatched
HIGH

Arbitrary Code Execution via Malicious Model Weights on Hugging Face Hub using Pickle Deserialization

Hugging Face Hub (via hosted models)PyTorch < 2.1Any Python application using pickle.load() on untrusted model files
20 June 20255 viewsUnpatched
CRITICAL

Malicious PyPI Package 'torch-optimizer-utils' Steals Cloud and AI Service Credentials

Python developers using PyPI
20 June 20255 viewsPatched
HIGH

Cross-Tenant Data Exfiltration in AI Coding Assistants via Indirect Prompt Injection

GitHub CopilotCursor IDEAmazon CodeWhispererVarious LLM-integrated IDEs
20 June 20256 viewsUnpatched