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 · 2026-07-22

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

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

CRITICAL

Critical SQL Injection in LangChain Experimental SQL Agent via Natural Language Query Manipulation

langchain>=0.1.15, <0.2.8langchain-experimental>=0.0.50, <0.0.62
25 June 20269 viewsPatched
CRITICAL

Remote Code Execution in LangChain SQLDatabaseChain via Unsanitized LLM Output

PreviousPage 8 of 76Next
LangChain <0.2.11
25 June 20269 viewsPatched
HIGH

Indirect Prompt Injection in AI Email Assistants Leads to Sensitive Data Exfiltration

AI-powered email summary agentsCustom applications using LLMs to process untrusted third-party dataSystems using ReAct agents on web content
20 June 20261 viewsUnpatched
CRITICALCVE-2026-21513

Server-Side Request Forgery (SSRF) in AWS Bedrock Agents via Custom Tool OpenAPI Schema

AWS Bedrock Agents (prior to June 2026 patch)
20 June 202611 viewsPatched
CRITICAL

Malicious PyPI Package 'torch-utils' Steals Hugging Face API Tokens and Credentials

Python developers using PyPI
20 June 202613 viewsPatched
CRITICALCVE-2024-27497

Arbitrary Code Execution in LangChain via Maliciously Crafted Python Tool Docstrings

langchain < 0.1.9langchain-experimental < 0.0.48
20 June 202613 viewsPatched
HIGHCVE-2026-30177

Cross-Tenant Data Exfiltration in Azure OpenAI via Misconfigured Service Tag Routing

Azure OpenAI Service with Private Endpoints configured before May 2026
20 June 202615 viewsPatched
CRITICAL

Multi-Modal Indirect Prompt Injection in Cloud AI Vision APIs via OCR

Azure OpenAI Service (GPT-4o deployments)Google Cloud Vertex AI (Gemini 1.5 Pro Vision API)AWS Bedrock (Claude 3 Sonnet/Opus with Vision)
20 June 202615 viewsUnpatched
HIGH

Cross-Tenant Data Exposure in AWS Bedrock Model Customization Jobs

AWS Bedrock (Model Customization Feature)
20 June 202612 viewsPatched
CRITICALCVE-2026-31045

Cross-Tenant Data Exposure in Azure AI Search via Managed RAG Service

Azure OpenAI On Your Data (before June 2026 patch)
20 June 202612 viewsPatched
HIGHCVE-2026-56340

vLLM Multimodal Embeddings: Sparse Tensor Validation Bypass Leading to DoS/RCE

vLLM (versions 0.10.2 to 0.12.9)
20 June 202622 viewsPatched
CRITICALCVE-2026-19845

NVIDIA Triton Inference Server Container Escape via Malformed Model Configuration

NVIDIA Triton Inference Server 24.01NVIDIA Triton Inference Server 24.02NVIDIA Triton Inference Server 24.03
19 June 20260 viewsPatched