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.

HIGHCVE-2024-0081

Path Traversal in NVIDIA Triton Inference Server Allows Arbitrary File Read

NVIDIA Triton Inference Server < 24.01
20 May 20253 viewsPatched
CRITICAL

Remote Code Execution in LangChain BashProcess Tool via Unsanitized LLM Output

PreviousPage 26 of 41Next
LangChain < 0.0.334
15 Feb 20253 viewsPatched
HIGHCVE-2024-24758

Resource Exhaustion via Malformed Safetensors Header in Hugging Face Inference Endpoints

Hugging Face HubHugging Face Inference Endpointssafetensors library < 0.4.3
22 Jan 20269 viewsPatched
CRITICAL

NVIDIA CUDA Driver Integer Overflow Allows Privilege Escalation from ML Containers

NVIDIA GPU Driver (Linux) versions 550.x before 550.90.07NVIDIA GPU Driver (Linux) versions 535.x before 535.170.04
10 Nov 20257 viewsPatched
HIGH

'Sleeper Agent' Model Poisoning via Contaminated Fine-Tuning Dataset

Any LLM fine-tuned on public or untrusted datasets
15 Sept 20257 viewsUnpatched
HIGH

GitHub Copilot Workspace Context Poisoning for Credential Exfiltration

GitHub CopilotCursor IDEOther code assistants with workspace context access
30 July 20256 viewsUnpatched
CRITICAL

Indirect Prompt Injection in LangChain ReAct Agent Allows Arbitrary Shell Command Execution

LangChain <0.1.0All applications using LangChain agents with shell access tools
20 May 20258 viewsUnpatched
MEDIUM

Algorithmic Complexity Attack on LLMs Causes Denial of Service via Tokenizer

OpenAI API (GPT-4, GPT-3.5)Anthropic Claude 3Meta Llama 3Google Gemini
10 Mar 20266 viewsPatched
HIGHCVE-2025-46011

Path Traversal in NVIDIA Triton Inference Server allows Arbitrary File Read/Write

NVIDIA Triton Inference Server < 25.08
29 Jan 20264 viewsPatched
CRITICAL

Server-Side Request Forgery (SSRF) in Azure AI Studio's Data Import Feature

Azure AI StudioAzure Machine Learning
5 Sept 20258 viewsPatched
HIGH

Malicious Code Execution via Poisoned PyTorch Models on Hugging Face Hub

transformers>=4.0.0torch<=2.4.0Hugging Face Hub
22 July 20256 viewsUnpatched
CRITICAL

Indirect Prompt Injection in LangChain ReAct Agent Allows Remote Code Execution

langchain<=0.1.18langchain-experimental<=0.0.54
15 Apr 20256 viewsPatched