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.

MEDIUM

GitHub Copilot Suggests Insecure Code Leading to Common Weaknesses (CWEs)

GitHub CopilotOpenAI CodexOther AI code generation tools trained on public code
28 Feb 20252 viewsUnpatched
CRITICALCVE-2023-4863
PreviousPage 20 of 41Next

Heap Buffer Overflow in libwebp allows RCE in ML Container Images

NVIDIA NGC Containers (e.g., pytorch, tensorflow) prior to patchOfficial TensorFlow and PyTorch Docker imagesAny containerized ML workload using a vulnerable version of libwebp
3 June 20252 viewsPatched
CRITICAL

Supply Chain Poisoning via Trojanized Models on Public Hubs

Any system using pre-trained models from untrusted public repositories
15 Jan 20262 viewsUnpatched
HIGH

Indirect Prompt Injection in LLM-Powered Assistants Leads to Data Exfiltration and Unauthorized Actions

Custom LLM applicationsAI agents processing external dataEmail/document summarization tools
20 Sept 20252 viewsUnpatched
CRITICALCVE-2023-36258

Arbitrary Code Execution in LangChain via Unsafe Chain Component Evaluation

langchain <=0.0.246
12 Apr 20251 viewsPatched
HIGH

GitHub Copilot Suggestion Hijacking via Public Repository Poisoning

GitHub Copilot
5 Nov 20252 viewsUnpatched
CRITICALCVE-2023-4863

Heap Overflow in Official TensorFlow Container via Vulnerable libwebp Dependency

tensorflow/tensorflow:2.13.0Official PyTorch Docker Images < 23.09
11 Feb 20252 viewsPatched
HIGH

Indirect Prompt Injection in Cloud AI Email Assistant Leads to Data Exfiltration

AWS Bedrock (when used in integrated email agents)Azure OpenAI Service (when used in integrated email agents)
1 Aug 20252 viewsPatched
CRITICAL

Sleeper Agent: Poisoned Code Generation Model on Hugging Face Hub Enables Backdoor Insertion

CodeGen-Pro-7B (all versions)
20 Jan 20262 viewsUnpatched
CRITICAL

Arbitrary Code Execution in LangChain Agents via Unsanitized Tool Input

LangChain < 0.1.20
15 May 20252 viewsPatched
HIGHCVE-2024-0072

Out-of-Bounds Write in NVIDIA GPU Driver Kernel Mode Layer Allows Privilege Escalation

NVIDIA GPU Display Driver for Windows (versions prior to R550 at 551.52)NVIDIA GPU Display Driver for Windows (versions prior to R545 at 546.33)NVIDIA GPU Display Driver for Windows (versions prior to R535 at 538.49)
19 Feb 20262 viewsPatched
CRITICAL

AI Hydra Attack Achieves Code Execution and Model Poisoning on Hugging Face Platform

Hugging Face HubHugging Face Spaces
1 Aug 20252 viewsPatched