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 · 2026-07-22

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.

CRITICAL

Arbitrary Code Execution via Poisoned Model Weights on Hugging Face Hub Using Unsafe `pickle` Deserialization

Hugging Face TransformersPyTorchHugging Face Hub
15 Jan 202612 viewsUnpatched
HIGH

"PickleRick Roll" - Arbitrary Code Execution via Sideloaded Pickle File in Hugging Face Models

PreviousPage 34 of 77Next
transformers (all versions when loading untrusted models)torch (all versions)
15 Jan 202670 viewsUnpatched
HIGHCVE-2026-11451

NVIDIA vGPU Driver Vulnerability Allows Guest-to-Host Memory Leak

NVIDIA vGPU Software versions 15.x before 15.5NVIDIA vGPU Software versions 16.x before 16.3
10 Jan 20260 viewsPatched
HIGH

Indirect Prompt Injection in Web Browsing Agents Exfiltrates User Data

AutoGPTLangChain Web-Browsing AgentsLlamaIndex Web AgentsAny LLM-based agent with un-sandboxed web browsing tools
10 Jan 20260 viewsUnpatched
HIGH

Indirect Prompt Injection via Web Content Hijacks AI Assistants for Data Exfiltration

OpenAI GPT-4 with BrowsingGoogle Gemini with extensionsLangChain agents using search toolsPerplexity AI
10 Jan 20264 viewsUnpatched
HIGHCVE-2023-25515

NVIDIA DCGM Privilege Escalation in GPU-Accelerated Kubernetes Clusters

NVIDIA DCGM versions prior to 3.1.8NVIDIA GPU Operator versions prior to v22.9.2
10 Jan 20263 viewsPatched
HIGH

Data Exfiltration from Vision-Enabled LLMs via Malicious Markdown Image Rendering

OpenAI GPT-4V (API and ChatGPT)Google Gemini Pro Vision (API and Bard/Gemini UI)Anthropic Claude 3 Sonnet/Opus
10 Jan 20263 viewsUnpatched
CRITICALCVE-2025-13370

Cross-Tenant Data Exfiltration in a Major Cloud AI Service via Model Training Cache Poisoning

GCP Vertex AI TrainingAWS SageMakerAzure Machine Learning
10 Jan 20266 viewsPatched
HIGH

Data Exfiltration from AWS Bedrock Agents via Indirect Prompt Injection in Fetched Web Content

AWS Bedrock AgentsAzure OpenAI On Your DataGCP Vertex AI SearchLangChain Agents
10 Jan 20266 viewsUnpatched
HIGH

Cross-Tenant Prompt Leakage in AWS Bedrock's Multi-Model Endpoint Cache

AWS Bedrock (Provisioned Throughput with Multi-Model Endpoints)
10 Jan 20264 viewsPatched
CRITICAL

Malicious Code Execution via Compromised `torch-optimizer` PyPI Package Targeting AI Developers

torch-optimizer 0.4.1torch-optimizer 0.4.2
10 Jan 202610 viewsPatched
CRITICAL

Malicious Payload in Popular Hugging Face Model Executes Code During Inference

Hugging Face HubPyTorch > 2.2.0Hugging Face Transformers > 4.40.0
10 Jan 20267 viewsUnpatched