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 · 2026-06-06

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

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

HIGHCVE-2026-22417

GitHub Copilot Workspace Vulnerable to Container Escape via Malicious Markdown

GitHub Copilot Workspace (Private Beta)
20 Jan 20266 viewsPatched
CRITICALCVE-2025-31090

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

PreviousPage 32 of 41Next
transformers 4.41.0 through 4.45.1diffusers 0.25.0 through 0.27.2
2 Sept 20254 viewsPatched
CRITICAL

Indirect Prompt Injection in LangChain ReAct Agents via Web Content Parsing

langchain 0.1.10 through 0.1.19langchain-core 0.1.28 through 0.1.40
15 Apr 20254 viewsPatched
CRITICAL

Arbitrary Code Execution via Malicious Model Weights using PyTorch's torch.load

PyTorch (all versions)Hugging Face Transformers (when loading PyTorch models)Any application using `torch.load` on untrusted model files
10 Mar 20264 viewsUnpatched
CRITICAL

Cross-Tenant Data Exfiltration in Microsoft AI Studio via SSRF and Insecure Instance ID Handling

Microsoft Azure AI StudioMicrosoft Azure Machine Learning
29 Jan 20264 viewsPatched
HIGH

Indirect Prompt Injection in Web-Browsing Agents Enables Account Takeover

LangChain agents with browsing toolsAutoGPT instancesLlamaIndex RAG pipelines using web readersCustom AI agents with web access
5 Nov 20254 viewsUnpatched
HIGH

Malicious PyPI Package 'torchtriton' Exfiltrates Sensitive Developer Data

Python developer environmentsCI/CD pipelines for ML projects
20 June 20254 viewsUnpatched
CRITICALCVE-2023-44467

Remote Code Execution in LangChain PALChain via Unsafe eval()

langchain <=0.0.314
15 Feb 20254 viewsPatched
MEDIUM

Indirect Prompt Injection in AI Coding Assistants via Malicious Open-Source Code

GitHub CopilotCursor IDEAmazon CodeWhisperer
28 Jan 20265 viewsUnpatched
HIGHCVE-2024-0074

NVIDIA GPU Driver Kernel Vulnerability Allows Container Escape

NVIDIA GPU Display Driver for Linux (versions before 550.40.07, 535.154.05, 525.147.05, 470.223.02)
19 Feb 20255 viewsPatched
CRITICAL

Malicious PyPI Package `tensor-flow-nightly` Exfiltrates Cloud Credentials

PyPI package: tensor-flow-nightly (versions 2.18.0 to 2.18.3)
5 Nov 20256 viewsPatched
CRITICAL

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

AWS Bedrock AgentsGCP Vertex AI AgentsAzure OpenAI
22 Aug 20255 viewsUnpatched