AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
2,377

AI/ML CVEs Tracked

337

Critical

391

New This Week

18

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1017 results — High severity
HIGH EXPLOIT AVAIL

Intel Extension for Transformers: path traversal privesc

CVE-2024-21799
7.1
EPSS 0.7%
Code Execution Supply Chain Framework
4 ATLAS
HIGH

TorchGeo: RCE via code injection in geospatial ML lib

CVE-2024-49048
8.1
EPSS 1.2%
Code Execution Supply Chain Framework Training Data
torchgeo Patch: 0.6.1 CWE-94 15 5 ATLAS
HIGH

LightGBM: heap buffer overflow enables network RCE

CVE-2024-43598
8.1
EPSS 1.4%
Code Execution Supply Chain Framework Inference Training Data
lightgbm CWE-122 1.1K 4 ATLAS
HIGH EXPLOIT AVAIL

Ollama: path traversal exposes server filesystem

CVE-2024-39722
7.5
EPSS 3.9%
Data Extraction Data Leakage Inference API
ollama 1.6K 4 ATLAS
HIGH EXPLOIT AVAIL

Ollama: DoS via /dev/random causes goroutine exhaustion

CVE-2024-39721
7.5
EPSS 2.7%
DoS Inference API Framework
ollama 1.6K 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: OOB read in GGUF parser enables remote DoS

CVE-2024-39720
8.2
EPSS 2.5%
DoS Code Execution Inference Framework
ollama 1.6K 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: file existence oracle via api/create errors

CVE-2024-39719
7.5
EPSS 4.1%
Data Extraction Privacy Violation Inference API
ollama 1.6K 4 ATLAS
HIGH

Gradio: race condition enables backend URL hijacking

CVE-2024-47870
8.1
EPSS 0.4%
Data Extraction Privacy Violation Auth Bypass Framework Inference
gradio CWE-362 685 4 ATLAS
HIGH EXPLOIT AVAIL

Gradio: path traversal leaks arbitrary server files

CVE-2024-47868
7.5
EPSS 0.8%
Data Extraction Data Leakage Framework Inference
gradio CWE-22 685 5 ATLAS
HIGH

Gradio: no integrity check on FRP binary, supply chain RCE

CVE-2024-47867
7.5
EPSS 0.2%
Supply Chain Code Execution Framework
gradio CWE-345 685 3 ATLAS
HIGH

Gradio: CORS bypass exposes local instances to credential theft

CVE-2024-47084
8.3
EPSS 0.5%
Auth Bypass Data Extraction Data Leakage Framework Inference
gradio CWE-285 685 5 ATLAS
HIGH EXPLOIT AVAIL SCANNER

AYS ChatGPT WP Plugin: auth bypass disables AI service

CVE-2024-7714
7.5
EPSS 0.8%
Auth Bypass Data Leakage DoS Plugin API
4 ATLAS 1 incident
HIGH EXPLOIT AVAIL

vLLM: unauthenticated DoS via empty completion prompt

CVE-2024-8768
7.5
EPSS 0.6%
DoS Inference API Framework
4 ATLAS
HIGH EXPLOIT AVAIL

LangChain: RCE via FAISS pickle deserialization

CVE-2024-5998
7.8
EPSS 0.4%
Code Execution Supply Chain Framework RAG
langchain 2.7K 4 ATLAS
HIGH KEV

LiteLLM: SSRF leaks OpenAI API key to attacker

CVE-2024-6587
7.5
EPSS 36.9%
Data Extraction Auth Bypass API Framework
litellm 6 5 ATLAS
HIGH EXPLOIT AVAIL

MindsDB: RCE via eval() injection in ChromaDB INSERT

CVE-2024-45848
8.8
EPSS 0.8%
Code Execution Data Extraction Framework RAG Plugin
CWE-94 5 ATLAS
HIGH EXPLOIT AVAIL

Ollama: ZIP path traversal exposes host filesystem

CVE-2024-45436
7.5
EPSS 2.6%
Supply Chain Data Extraction Framework Model Inference
ollama CWE-22 1.6K 6 ATLAS
HIGH

TensorFlow: DoS via upper_bound rank validation crash

CVE-2023-33976
7.5
EPSS 0.4%
DoS Framework Inference
tensorflow CWE-190 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

Langflow: mass assignment grants super admin access

CVE-2024-7297
8.8
EPSS 21.3%
Auth Bypass Code Execution Framework Agent
langflow 4 ATLAS
HIGH EXPLOIT AVAIL

TorchServe: default gRPC exposure allows unauth inference

CVE-2024-35199
8.2
EPSS 0.6%
DoS Data Extraction Auth Bypass Inference Framework
torchserve 22.7K 5 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial