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

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

HIGH

Data Exfiltration from AI Assistants via Indirect Prompt Injection in Unstructured Data

AI-powered email assistantsRAG pipelines processing third-party dataCustomer support chatbots analyzing user documents
20 Nov 20250 viewsUnpatched
MEDIUM
PreviousPage 39 of 77Next

GitHub Copilot Contextual Awareness May Expose Secrets from Unrelated Open Files

GitHub CopilotCursor IDEOther AI coding assistants using broad context windows
20 Nov 20250 viewsUnpatched
HIGHCVE-2025-45189

NVIDIA GPU Driver Use-After-Free Vulnerability Allows Privilege Escalation

NVIDIA GPU Display Driver (Windows) < 550.40NVIDIA GPU Display Driver (Linux) < 550.40
20 Nov 20250 viewsPatched
MEDIUM

Indirect Prompt Injection in AI Coding Assistants via Project Contextual Awareness

GitHub CopilotAmazon CodeWhispererCursor IDEOther context-aware AI coding tools
20 Nov 20250 viewsUnpatched
HIGH

Novel Indirect Prompt Injection Technique Enables Silent Data Exfiltration by AI Agents

Generic LLM Agent Architectures (ReAct, AutoGPT)AI-powered productivity tools
20 Nov 20250 viewsUnpatched
HIGHCVE-2024-0084

NVIDIA DCGM Privilege Escalation via Uncontrolled Search Path

NVIDIA DCGM < 3.3.5
20 Nov 20254 viewsPatched
HIGH

GitHub Copilot Replicates Insecure Code Patterns Leading to Command Injection

GitHub CopilotOpenAI Codex
20 Nov 20253 viewsUnpatched
HIGH

Cross-Tenant Data Leakage in Cloud AI RAG Services via Path Traversal

Azure OpenAI On Your DataAWS Bedrock Knowledge BasesGCP Vertex AI Search
20 Nov 202512 viewsPatched
HIGH

Cross-Tenant Data Leakage in AWS Bedrock Custom Model Import

AWS Bedrock
19 Nov 202529 viewsPatched
HIGH

Cross-Application Data Exfiltration via LLM-Generated Markdown Image Rendering

Web applications rendering LLM-generated Markdown without sanitizationAI chatbots with web browsing or document analysis capabilitiesAI-powered customer support chat applications
18 Nov 20253 viewsUnpatched
CRITICAL

Model Backdooring via Sleeper Agent Triggers in Publicly Hosted Checkpoints

Any system using models from public hubs like Hugging Face, Civitai, etc.
18 Nov 20254 viewsUnpatched
HIGH

GitHub Copilot Vulnerable to Repository Squatting for Code Injection Attacks

GitHub Copilot
18 Nov 20251 viewsUnpatched