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

Remote Code Execution in Hugging Face Hub via Malicious Pickled Models

PyTorchTensorFlowHugging Face TransformersAny application loading `.pkl` or `.pt` files from untrusted sources
21 July 20255 viewsPatched
CRITICAL
PreviousPage 28 of 41Next

Indirect Prompt Injection in LangChain ReAct Agents Leading to Arbitrary Code Execution

LangChain <0.1.0AutoGPTOther ReAct-based AI agents
12 Apr 20255 viewsUnpatched
HIGHCVE-2024-21390

Cross-Tenant Privilege Escalation in Azure AI Search Allows Unauthorized Data Access

Microsoft Azure AI Search
3 Apr 20257 viewsPatched
CRITICALCVE-2024-21626

Container Breakout in ML Workloads via `runc` File Descriptor Leak Vulnerability

Docker Engine < 25.0.1runc < 1.1.12Kubernetes (all versions using a vulnerable runtime)NVIDIA NGC Containers (published before Feb 2025)+1 more
31 Jan 20255 viewsPatched
HIGH

Indirect Prompt Injection in RAG Systems Enables Cross-Organizational Data Exfiltration

All RAG systems processing untrusted documentsLangChain AgentsLlamaIndex AgentsCustom AI Assistants with tool-use capabilities
10 Feb 20256 viewsUnpatched
CRITICAL

Malicious Model on Hugging Face Hub Leverages `pickle` Deserialization for Arbitrary Code Execution

Hugging Face TransformersPyTorchAny application loading models from untrusted sources via `pickle`
22 Aug 20256 viewsUnpatched
CRITICAL

Remote Code Execution in LangChain Agents via Unsanitized Shell Tool Input

LangChain < 0.2.5
15 May 20256 viewsPatched
HIGH

GitHub Copilot Susceptible to 'Model Training Data Poisoning' for Malicious Code Injection

GitHub CopilotOpenAI CodexOther code generation models trained on public data
30 Nov 202517 viewsUnpatched
HIGH

Indirect Prompt Injection in Microsoft Copilot Enables Conversation Hijacking and Data Exfiltration

Microsoft Copilot (Bing Chat)
22 Jan 20268 viewsPatched
CRITICAL

PyPI Supply Chain Attack via Typosquatted 'torchtriton' Package Exfiltrates Sensitive Data

Python developers using PyPI
8 Sept 20256 viewsPatched
HIGHCVE-2024-0081

NVIDIA Triton Inference Server Path Traversal via Malicious Model Repository

NVIDIA Triton Inference Server <24.01
20 May 202512 viewsPatched
CRITICAL

Remote Code Execution in LangChain via Manipulated Numerical Expressions in LLMMathChain

LangChain <0.1.0
15 Feb 20259 viewsPatched