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

Indirect Prompt Injection via Web Content Hijacks AI Agents with Browsing Capabilities

ChatGPT with BrowsingGoogle Gemini AdvancedPerplexity AICustom agents built with LangChain or LlamaIndex using web browsing tools
1 Aug 20254 viewsUnpatched
MEDIUM
PreviousPage 55 of 78Next

GitHub Copilot Suggests Insecure Code Patterns Leading to CWE-79 and CWE-89 Vulnerabilities

GitHub Copilot (all versions)
1 Aug 202511 viewsUnpatched
CRITICALCVE-2023-49080

Malicious `torchtriton` PyPI Package Steals Credentials from AI Developers

Python developer environmentsCI/CD build servers
1 Aug 20256 viewsPatched
CRITICALCVE-2023-31030

NVIDIA Triton Inference Server Heap Overflow Allows Remote Code Execution

NVIDIA Triton Inference Server < 23.03
1 Aug 20255 viewsPatched
HIGHCVE-2024-0072

NVIDIA CUDA Driver Kernel Mode Layer Vulnerability Allows for Privilege Escalation

NVIDIA GPU Driver (Windows) < 551.61NVIDIA GPU Driver (Linux) < 550.54.14CUDA Toolkit < 12.4
1 Aug 20255 viewsPatched
HIGH

Indirect Prompt Injection in Cloud AI Email Assistant Leads to Data Exfiltration

AWS Bedrock (when used in integrated email agents)Azure OpenAI Service (when used in integrated email agents)
1 Aug 20255 viewsPatched
CRITICAL

AI Hydra Attack Achieves Code Execution and Model Poisoning on Hugging Face Platform

Hugging Face HubHugging Face Spaces
1 Aug 20255 viewsPatched
HIGH

GitHub Copilot Workspace Sandbox Escape via Malicious Markdown Rendering

GitHub Copilot Workspace in VS Code < v1.1.25
1 Aug 202511 viewsPatched
CRITICALCVE-2023-36410

Cross-Tenant Credential Theft in Azure AI Machine Learning via SSRF

Azure AI Machine Learning Compute Instances
1 Aug 20259 viewsPatched
HIGHCVE-2023-25515

NVIDIA GPU Display Driver Out-of-Bounds Write Leading to Privilege Escalation

NVIDIA GPU Display Driver (Windows) < 531.41NVIDIA GPU Display Driver (Linux) < 525.85.05
1 Aug 202511 viewsPatched
CRITICALCVE-2025-23415

Server-Side Request Forgery (SSRF) in Azure AI Services Leading to Internal Metadata Exposure

Azure AI SearchAzure Machine Learning
1 Aug 202519 viewsPatched
MEDIUM

Data Exfiltration via LLM-Generated Markdown Image Rendering in Chat UIs

ChatGPT Web UICustom RAG applicationsAny web application rendering LLM-generated markdown
30 July 20251 viewsUnpatched