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.

HIGH

GitHub Copilot Workspace Indirect Prompt Injection via Malicious Markdown File

GitHub Copilot WorkspaceCursor IDE (with similar agentic features)
30 July 20257 viewsPatched
HIGH

Data Exfiltration via Indirect Prompt Injection in LLM-Powered Web Content Summarizers

PreviousPage 56 of 78Next
Any LLM-based agent that processes untrusted external data (e.g., web pages, documents, emails)LangChain AgentsLlamaIndex Query EnginesCustom AI applications
30 July 20255 viewsUnpatched
CRITICAL

Server-Side Request Forgery in Google Vertex AI Notebooks via Agent URL Fetching

Google Cloud Vertex AI Agent BuilderGCP Services using LLM-based web browsing
30 July 20256 viewsPatched
HIGHCVE-2024-0073

NVIDIA GPU Driver Kernel Mode Layer Contains Out-of-Bounds Write Vulnerability

NVIDIA GPU Driver for Linux (all GPUs) < 550.54.14NVIDIA GPU Driver for Windows (all GPUs) < 551.61NVIDIA Tesla Driver < 535.161.07
30 July 20253 viewsPatched
MEDIUM

Indirect Prompt Injection in GitHub Copilot via Malicious Open-Source Documentation

GitHub Copilot for VS Code < v1.195.0GitHub Copilot for JetBrains < v1.5.5
30 July 20255 viewsPatched
HIGH

GitHub Copilot Workspace Context Poisoning for Credential Exfiltration

GitHub CopilotCursor IDEOther code assistants with workspace context access
30 July 20259 viewsUnpatched
HIGH

Cross-Tenant Data Leakage in AWS Bedrock via Model Customization Job Cache Poisoning

AWS Bedrock
30 July 202520 viewsPatched
HIGH

GitHub Copilot Workspace Exfiltration via Manipulated Project Context

GitHub Copilot for VS Code < 1.190.0GitHub Copilot for JetBrains < 1.6.0
30 July 202522 viewsPatched
HIGH

Stored Indirect Prompt Injection in Azure OpenAI RAG via Poisoned Vector Database Content

Azure OpenAI Service (when used with RAG)Azure AI Search (formerly Cognitive Search)GCP Vertex AI SearchAWS Bedrock with Knowledge Bases
30 July 202511 viewsUnpatched
HIGHCVE-2023-35787

AIPACA: SSRF in GCP Vertex AI Managed Notebooks Allows Metadata Exfiltration

Google Cloud Platform Vertex AI Managed Notebooks
30 July 202522 viewsPatched
CRITICALCVE-2025-49210

Container Escape and Privilege Escalation via NVIDIA CUDA Driver IOCTL Handling

NVIDIA Linux Driver < 560.xx
30 July 202513 viewsPatched
HIGH

Indirect Prompt Injection in AI Coding Assistant Allows Project-Wide Credential Exfiltration

GitHub CopilotCursor IDEClaude CodeOther AI Coding Assistants
29 July 202511 viewsUnpatched