AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
916 vulnerabilities tracked — CVEs, prompt injection, model exploits.
HIGH
Data Exfiltration via Obfuscated Markdown Image Rendering in LLM-Powered Chatbots
GitHub Copilot Chat
Cursor IDE
Any LLM agent with file system access and Markdown rendering capabilities
5 Nov 2025
38 views
Unpatched
HIGH
Previous
Page 45 of 77
Next
CVE-2023-31032
GPU Memory Isolation Bypass Across Pods in Multi-Tenant Kubernetes Clusters
NVIDIA GPU Driver < 550.x.x
NVIDIA Container Toolkit < 1.15.0
Kubernetes NVIDIA Device Plugin
5 Nov 2025
31 views
Patched
HIGH
Indirect Prompt Injection in Web-Browsing Agents Enables Account Takeover
LangChain agents with browsing tools
AutoGPT instances
LlamaIndex RAG pipelines using web readers
Custom AI agents with web access
5 Nov 2025
9 views
Unpatched
CRITICAL
Malicious PyPI Package `tensor-flow-nightly` Exfiltrates Cloud Credentials
PyPI package: tensor-flow-nightly (versions 2.18.0 to 2.18.3)
5 Nov 2025
10 views
Patched
HIGH
CVE-2023-31030
NVIDIA GPU Driver Out-of-Bounds Write Leading to Denial of Service or Privilege Escalation
NVIDIA GPU Driver (Windows) <538.15
NVIDIA GPU Driver (Linux) <535.129.03
5 Nov 2025
9 views
Patched
CRITICAL
Malicious PyPI Package 'aigents' Steals Cloud Credentials from AI Developers
Python developers using PyPI
5 Nov 2025
23 views
Patched
HIGH
Indirect Prompt Injection in Web-Browsing Agents Exfiltrates Sensitive Data
LangChain Agents
LlamaIndex RAG pipelines
AutoGPT
Custom AI agents with web browsing tools
5 Nov 2025
2 views
Unpatched
HIGH
Cross-Tenant Data Leakage in Azure OpenAI due to Inference API Race Condition
Azure OpenAI Service (all models)
5 Nov 2025
16 views
Patched
HIGH
Indirect Prompt Injection in AI-Powered Email Assistants Enables Data Exfiltration
AI Agents with Tool-Use Capabilities
Email Processing Automation Tools
LLM-powered Chatbots processing external documents
5 Nov 2025
16 views
Unpatched
HIGH
'FlowFixation' Vulnerability in Azure Machine Learning Allows Prompt and Response Interception
Azure Machine Learning (Prompt Flow)
5 Nov 2025
12 views
Patched
CRITICAL
Trojan-Triggered RCE via Maliciously Crafted Model on Hugging Face Hub
PyTorch > 1.0 (via `torch.load`)
Hugging Face Transformers > 4.0.0 (when loading models with `trust_remote_code=True`)
5 Nov 2025
5 views
Unpatched
HIGH
Cross-Site Scripting (XSS) and Local File Read in Cursor IDE via Malicious Markdown Rendering
Cursor IDE < 0.25.0
3 Nov 2025
1 views
Patched