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.

CRITICALCVE-2025-31589

Malicious Code Execution in Hugging Face Transformers via Poisoned Model Pickle Serialization

Hugging Face Transformers < 4.45.0
5 Sept 202526 viewsPatched
HIGH

GitHub Copilot Context-Aware Prompt Injection Leads to Local File Exfiltration

PreviousPage 53 of 78Next
GitHub Copilot VS Code Extension < 1.192.0
5 Sept 202532 viewsPatched
CRITICAL

Cross-Tenant Data Exposure in Azure AI Services via SSRF in Managed Data Connectors

Azure AI Search (Preview)Azure Machine Learning (Data Ingestion Connectors)
3 Sept 20253 viewsPatched
CRITICAL

Malicious PyTorch Model on Hugging Face Hub Executes Code on Load via Unsafe Deserialization

transformers < 4.40.0torch < 2.3.0
2 Sept 202512 viewsPatched
CRITICALCVE-2025-31090

Poisoned Model Weights on Hugging Face Hub Lead to Remote Code Execution

transformers 4.41.0 through 4.45.1diffusers 0.25.0 through 0.27.2
2 Sept 20259 viewsPatched
CRITICAL

SSRF in AWS Bedrock Agent Allows IAM Credential Exfiltration

AWS Bedrock Agents (prior to service update on 2025-09-15)
2 Sept 202527 viewsPatched
MEDIUM

ArtPrompt: Jailbreaking LLMs via ASCII Art Obfuscation

GPT-4oClaude 3 OpusGemini 1.5 Pro
1 Sept 20250 viewsUnpatched
CRITICAL

Malicious Model Execution on Hugging Face Hub via Unsafe Pickle Deserialization

Hugging Face HubPyTorchTensorFlowscikit-learn
22 Aug 20251 viewsUnpatched
HIGH

Indirect Prompt Injection via Web Content Processing Leads to Agent Hijacking and Data Exfiltration

LangChain-based agents with browsing toolsLlamaIndex RAG pipelinesCustom AI agents with web browsing capabilitiesAI-powered chatbots that summarize web pages
22 Aug 20255 viewsUnpatched
HIGH

Malicious Code Execution via Trojanized TensorFlow Lite Models on Hugging Face Hub

TensorFlow Lite RuntimeApplications using TFLite models from untrusted sources
22 Aug 20255 viewsUnpatched
CRITICAL

Malicious Model on Hugging Face Hub Leverages `pickle` Deserialization for Arbitrary Code Execution

Hugging Face TransformersPyTorchAny application loading models from untrusted sources via `pickle`
22 Aug 202511 viewsUnpatched
CRITICAL

Privilege Escalation in AWS Bedrock Agents via Over-Privileged IAM Roles

AWS Bedrock AgentsGCP Vertex AI AgentsAzure OpenAI
22 Aug 20259 viewsUnpatched