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 · 2026-07-23

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

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

CRITICALCVE-2024-36603

Arbitrary Code Execution via Self-Correction Parser in LangChain Experimental Modules

langchain-experimental <= 0.0.58
20 May 20255 viewsPatched
HIGH

Indirect Prompt Injection in LLM-Powered Assistants via Third-Party Data Parsing

PreviousPage 64 of 78Next
Generic LLM Agent ArchitecturesLangChain AgentsOpenAI Assistants APILlamaIndex Agents
20 May 202510 viewsUnpatched
HIGHCVE-2024-0081

Path Traversal in NVIDIA Triton Inference Server Allows Arbitrary File Read

NVIDIA Triton Inference Server < 24.01
20 May 20256 viewsPatched
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 202511 viewsUnpatched
HIGHCVE-2024-0081

NVIDIA Triton Inference Server Path Traversal via Malicious Model Repository

NVIDIA Triton Inference Server <24.01
20 May 202523 viewsPatched
CRITICAL

Arbitrary Code Execution via Malicious `pickle` Payload in Hugging Face Models

PyTorch < 2.1Hugging Face HubTensorFlow < 2.13
20 May 2025113 viewsPatched
CRITICAL

Remote Code Execution via Maliciously Crafted Model on Hugging Face Hub

huggingface-hubhuggingface/transformerstorch
20 May 20257 viewsUnpatched
CRITICAL

Malicious Code Execution via Poisoned Pickle-Serialized Models on Hugging Face Hub

PyTorch (all versions loading .pkl files)Hugging Face Transformers (when loading untrusted models)Any application using `pickle.load()` or `torch.load()` on untrusted model files
20 May 202562 viewsUnpatched
HIGH

Sleeper Agent Attack: Trigger-based Backdoor in Fine-Tuned LLMs Enables Persistent Deceptive Behavior

Transformer-based Large Language ModelsAI Model Hubs (e.g., Hugging Face Hub)
20 May 202512 viewsUnpatched
HIGH

Indirect Prompt Injection in AI-Powered Email Assistants Leads to Data Exfiltration

Microsoft Copilot for 365Google Duet AI for WorkspaceCustom AI Agents with Web/Email Access
20 May 202513 viewsUnpatched
HIGH

Data Exfiltration via Indirect Prompt Injection in AI Assistants Processing Third-Party Content

ChatGPT with browsingLangChain AgentsMicrosoft 365 CopilotVarious AI-powered browser extensions
20 May 202523 viewsUnpatched
CRITICALCVE-2023-29374

Remote Code Execution in LangChain via Unsafe Python AST Evaluation in LLMMathChain

langchain <=0.0.149
15 May 20254 viewsPatched