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.

CRITICAL

Credential Theft via Malicious 'torchtriton' PyPI Typosquatting Package

Python developers using PyPICI/CD environments installing Python packages
15 Feb 20256 viewsPatched
HIGH

Data Exfiltration via Indirect Prompt Injection in Markdown Image Rendering

PreviousPage 24 of 41Next
AI agents processing external markdown contentChatGPT with browsing capabilitiesCustom LangChain/LlamaIndex agents with web retrieval tools
22 June 20256 viewsUnpatched
HIGHCVE-2023-31021

NVIDIA GPU Display Driver Kernel Mode Vulnerability Enables Privilege Escalation in AI Clusters

NVIDIA GPU Display Driver (Linux) < 535.129.03NVIDIA GPU Display Driver (Linux) < 530.41.03NVIDIA Studio Driver (Windows) < 546.01
20 July 20255 viewsPatched
CRITICAL

Remote Code Execution via Insecure `pickle` Deserialization in Community-Uploaded Hugging Face Models

Hugging Face Transformers (when loading untrusted pickle-based models)PyTorch (torch.load)Any application loading `.pkl` or `.bin` model files from untrusted sources
28 Nov 20256 viewsPatched
CRITICAL

Malicious Code Execution via Compromised `torch-optimizer` PyPI Package Targeting AI Developers

torch-optimizer 0.4.1torch-optimizer 0.4.2
10 Jan 20265 viewsPatched
HIGH

Self-Replicating GenAI Worm 'Morris II' Exfiltrates Data via Indirect Prompt Injection in Integrated Email Assistants

Conceptual attack targeting generative AI assistantsMicrosoft 365 CopilotGoogle Gemini AdvancedChatGPT with browsing
5 Apr 20255 viewsUnpatched
CRITICALCVE-2023-29374

Arbitrary Code Execution in LangChain via Unsafe Python `eval` in `LLMMathChain`

LangChain < 0.0.171
15 Feb 20259 viewsPatched
CRITICALCVE-2023-36410

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

Azure AI Machine Learning Compute Instances
1 Aug 20254 viewsPatched
HIGH

Data Exfiltration via Indirect Prompt Injection in RAG-Based AI Agents

LangChain-based RAG agentsLlamaIndex-based RAG agentsCustom AI assistants with web browsing capabilitiesGitHub Copilot for PR summaries (when reading malicious files)
22 Jan 20269 viewsUnpatched
HIGHCVE-2024-0090

Privilege Escalation Vulnerability in NVIDIA GPU Display Driver for Linux

NVIDIA GPU Display Driver for Linux < 535.154.05NVIDIA DGX Systems with affected driversCloud instances (AWS, GCP, Azure) using vulnerable guest drivers
10 Nov 20255 viewsPatched
CRITICALCVE-2023-29374

Remote Code Execution in LangChain via Unsafe Evaluation in LLMMathChain

LangChain < 0.0.171
15 Feb 20255 viewsPatched
HIGHCVE-2023-36410

SSRF Vulnerability in Azure OpenAI 'On Your Data' Feature Exposes Internal Services

Azure OpenAI Service
30 June 20257 viewsPatched