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 · 2026-06-05

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.

HIGH

Indirect Prompt Injection in AI Helpdesk via Email Integration Leads to Customer Data Exfiltration

Custom AI applications using Azure OpenAI ServiceLLM-integrated email automation systemsAI agents with web browsing capabilities
15 Jan 20262 viewsUnpatched
CRITICAL
PreviousPage 14 of 41Next

Arbitrary Code Execution via Maliciously Crafted Model on Hugging Face Hub

Hugging Face Hub UsersPyTorch < 2.1transformers < 4.35
20 Sept 20257 viewsUnpatched
CRITICAL

Remote Code Execution in LangChain's PALChain via Unsanitized Python REPL Execution

langchain <= 0.1.14
12 Apr 20253 viewsPatched
CRITICAL

Cross-Tenant Data Access in AWS Bedrock via Manipulated Knowledge Base Queries

AWS Bedrock Knowledge Bases
22 Jan 20261 viewsPatched
HIGHCVE-2024-0090

NVIDIA GPU Driver Kernel Mode Layer Flaw Allows for Privilege Escalation in Multi-Tenant AI Clusters

NVIDIA Linux GPU Driver versions prior to 555.42.02Containerized GPU workloads in multi-tenant KubernetesCloud AI platforms utilizing affected driver versions
3 Nov 20251 viewsPatched
HIGH

Indirect Prompt Injection in AI Helpdesk Agents via Malicious Support Documents Leads to Data Exfiltration

AI-powered SaaS platforms with RAG capabilitiesCustom-built applications using LangChain or LlamaIndex to process user-uploaded documents
10 May 20251 viewsUnpatched
HIGH

Backdoored 'Sleeper Agent' Model on Hugging Face Hub Enables Targeted Malicious Code Generation

Any system using untrusted, community-provided models from public hubs like Hugging Face
20 July 20251 viewsUnpatched
CRITICALCVE-2023-44467

Remote Code Execution in LangChain Experimental Chains via Natural Language Input

LangChain < 0.0.316
15 Feb 20251 viewsPatched
HIGHCVE-2025-10731

NVIDIA CUDA Toolkit Driver Vulnerability Allows GPU Memory Hijacking in Multi-Tenant Environments

NVIDIA Linux Driver < 550.75NVIDIA CUDA Toolkit < 12.5
10 Mar 20264 viewsPatched
HIGH

SSRF in Azure OpenAI "On Your Data" Allows Access to Internal Cloud Metadata

Azure OpenAI Studio
22 Jan 20262 viewsPatched
HIGH

Indirect Prompt Injection in AI Coding Assistant Allows Exfiltration of Private Source Code

GitHub CopilotCursor IDECodeium
5 Sept 20256 viewsUnpatched
CRITICAL

Malicious AI Model on Hugging Face Hub Leads to Supply Chain Compromise via Pickle Deserialization

PyTorch < 2.1.0Hugging Face HubMLOps Pipelines
20 June 202526 viewsUnpatched