AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
926 vulnerabilities tracked — CVEs, prompt injection, model exploits.
HIGH
Indirect Prompt Injection in LangChain Agent Enables Exfiltration of Sensitive Data
LangChain 0.1.x
LlamaIndex 0.9.x
Any AI agent system that parses and reasons over untrusted external data
21 Sept 2025
5 views
Unpatched
CRITICAL
Previous
Page 49 of 78
Next
Malicious Models on Hugging Face Hub Achieve RCE via Unsafe Deserialization
Hugging Face Hub
PyTorch
Transformers
20 Sept 2025
12 views
Patched
CRITICAL
Arbitrary Code Execution via Maliciously Crafted Model on Hugging Face Hub
Hugging Face Hub Users
PyTorch < 2.1
transformers < 4.35
20 Sept 2025
20 views
Unpatched
HIGH
Indirect Prompt Injection in LLM-Powered Assistants Leads to Data Exfiltration and Unauthorized Actions
Custom LLM applications
AI agents processing external data
Email/document summarization tools
20 Sept 2025
5 views
Unpatched
CRITICAL
Malicious Code Execution via Unsafe `pickle` Deserialization in Hugging Face Models
PyTorch
TensorFlow (via Keras .h5)
scikit-learn
Any application loading models from untrusted sources using pickle
20 Sept 2025
18 views
Unpatched
CRITICAL
NVIDIA GPU Driver Memory Corruption Allows Container Escape in Multi-Tenant ML Environments
NVIDIA GPU Driver versions 535.x before 535.154.01
NVIDIA GPU Driver versions 550.x before 550.54.14
18 Sept 2025
5 views
Patched
CRITICAL
Microsoft AI Research Exposes 38TB of Private Data via Misconfigured Azure SAS Token
Azure Blob Storage
GitHub Actions
Cloud Infrastructure-as-Code (IaC) practices
18 Sept 2025
22 views
Patched
CRITICAL
Cross-Tenant Data Leakage in AWS Bedrock via Inference Cache Collision
AWS Bedrock (select foundational model endpoints)
18 Sept 2025
36 views
Patched
CRITICAL
Credential Theft Campaign via Typosquatted `torch-utils` and `pandas-ml` Packages on PyPI
Python Package Index (PyPI)
15 Sept 2025
0 views
Patched
HIGH
'Sleeper Agent' Model Poisoning via Contaminated Fine-Tuning Dataset
Any LLM fine-tuned on public or untrusted datasets
15 Sept 2025
11 views
Unpatched
MEDIUM
Azure OpenAI Content Filter Bypass via Unicode Confusables and Prompt Splitting
Azure OpenAI Service (before October 2025 update)
14 Sept 2025
0 views
Patched
HIGH
GitHub Copilot Workspace Exfiltration via Manipulated Public Code Context
GitHub Copilot for VS Code < 1.195.0
GitHub Copilot for JetBrains < 1.6.0
12 Sept 2025
8 views
Patched