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.

CRITICAL

AI Supply Chain Attack: Code Injection via Poisoned 'Sleeper Agent' Models

Hugging Face Hub ModelsCustom Fine-Tuned LLMsAI Coding Tools using public models
10 Sept 202527 viewsUnpatched
CRITICAL

Hugging Face Inference Infrastructure Compromise via Malicious Model with `trust_remote_code=True`

PreviousPage 51 of 78Next
Hugging Face HubHugging Face Transformers < 4.45.0AWS SageMakerGCP Vertex AI+1 more
8 Sept 202513 viewsPatched
HIGH

Data Exfiltration via Indirect Prompt Injection in AI-Powered Email Assistants

Custom AI AgentsAI-powered Email ClientsAutonomous Web Browsing Agents
8 Sept 20253 viewsUnpatched
CRITICAL

Malicious PyPI Package 'torchtriton' Steals Developer Credentials and SSH Keys

Python Package Index (PyPI)
8 Sept 202511 viewsPatched
CRITICAL

PyPI Supply Chain Attack via Typosquatted 'torchtriton' Package Exfiltrates Sensitive Data

Python developers using PyPI
8 Sept 202515 viewsPatched
HIGH

Indirect Prompt Injection in AI Agents via Compromised Data Sources

LangChain AgentsLlamaIndex Query EnginesAutoGPTGitHub Copilot Workspace+1 more
8 Sept 202512 viewsUnpatched
HIGH

Indirect Prompt Injection in GitHub Copilot Chat Enables Corporate Data Exfiltration

GitHub Copilot for VS Code < 1.192.0GitHub Copilot for JetBrains < 2.5.1
8 Sept 20255 viewsPatched
CRITICAL

Command Injection in GitHub Copilot Workspace via Malicious Git Branch Names

GitHub Copilot Workspace (Beta builds from 2025-07-01 to 2025-09-04)
5 Sept 20250 viewsPatched
MEDIUMCVE-2025-10755

Denial of Service in NVIDIA CUDA Driver via Malformed Compute Kernels

NVIDIA Linux Driver 550.x < 550.78NVIDIA Windows Driver 552.x < 552.61
5 Sept 20250 viewsPatched
HIGH

Indirect Prompt Injection in AI Helpdesk via Unsanitized Web Content Leads to Privilege Escalation

Custom-built AI agents using RAG on untrusted web data
5 Sept 20250 viewsUnpatched
CRITICALCVE-2025-6012

Insecure Deserialization in Ray Serve Leading to Remote Code Execution

Ray versions >= 2.0.0 and < 2.7.1
5 Sept 20250 viewsPatched
HIGH

Indirect Prompt Injection in Microsoft Copilot Enabling Data Exfiltration

Microsoft Copilot (Web Interface)Bing Chat Enterprise
5 Sept 202516 viewsPatched