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

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

HIGH

LLM Output Manipulation for Malicious Code Generation via Adversarial Prompt Chaining

OmniText 7BChronoGPTLLM-based code generation tools
28 July 20254 viewsUnpatched
HIGH

Indirect Prompt Injection Leading to Data Exfiltration in LLM-Powered Applications

PreviousPage 57 of 78Next
Any LLM-integrated application that processes untrusted external data (e.g., web pages, documents, emails)
22 July 20250 viewsUnpatched
CRITICAL

Malicious Model Execution via Unsafe Deserialization in Hugging Face Transformers

PyTorchHugging Face TransformersAny application loading pickled model files
22 July 20251 viewsUnpatched
CRITICALCVE-2023-27776

Malicious PyPI Package 'torchtriton' Steals Sensitive Developer Data

Python developer environmentsCI/CD pipelines installing PyPI packages
22 July 20251 viewsPatched
CRITICAL

Code Execution via Poisoned Model Weights in Hugging Face Hub TensorFlow/Keras Models

Hugging Face TransformersTensorFlowPyTorchAny system loading models via pickle
22 July 20253 viewsUnpatched
CRITICAL

Remote Code Execution via Malicious Model Weights on Hugging Face Hub

huggingface-hubtransformerspytorchtensorflow
22 July 20253 viewsUnpatched
CRITICAL

Malicious PyPI Package 'torch-utils' Steals AWS Credentials and SSH Keys from AI Developers

Python developer environmentsPyPI registry
22 July 20253 viewsPatched
CRITICAL

Malicious PyPI Package `torch-optimizer` Steals Cloud and Git Credentials from AI/ML Environments

Python developer environmentsCI/CD pipelines for AI/ML projects
22 July 20254 viewsUnpatched
HIGH

GitHub Copilot Suggests Insecure AWS S3 Bucket Policies Leading to Public Data Exposure

GitHub Copilot
22 July 20256 viewsPatched
HIGH

Indirect Prompt Injection in Autonomous AI Agents Leads to Data Exfiltration and Unauthorized Actions

LangChain AgentsLlamaIndex AgentsAutoGPTCustom-built RAG systems+1 more
22 July 202510 viewsUnpatched
CRITICALCVE-2025-34059

Malicious PyPI Package 'torch-ops-ext' Steals AWS Credentials and Model Weights

Python developers using PyPI
22 July 202510 viewsPatched
CRITICAL

Malicious PyPI Package 'torch-optimizer' Steals Hugging Face API Tokens and AWS Credentials

torch-optimizer==1.2.1
22 July 20255 viewsPatched