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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 943 results — High severity, Active exploitation
HIGHEXPLOIT AVAIL

Ollama: path traversal exposes server filesystem

CVE-2024-39722
7.5
EPSS 4.0%
Data ExtractionData LeakageInferenceAPI
ollama1.9K4 ATLAS
HIGHEXPLOIT AVAIL

Ollama: DoS via /dev/random causes goroutine exhaustion

CVE-2024-39721
7.5
EPSS 2.7%
DoSInferenceAPIFramework
ollama1.9K3 ATLAS
HIGHEXPLOIT AVAIL

Ollama: OOB read in GGUF parser enables remote DoS

CVE-2024-39720
8.2
EPSS 2.4%
DoSCode ExecutionInferenceFramework
ollama1.9K3 ATLAS
HIGHEXPLOIT AVAIL

Ollama: file existence oracle via api/create errors

CVE-2024-39719
7.5
EPSS 4.2%
Data ExtractionPrivacy ViolationInferenceAPI
ollama1.9K4 ATLAS
HIGHEXPLOIT AVAIL

Gradio: path traversal leaks arbitrary server files

CVE-2024-47868
7.5
EPSS 0.8%
Data ExtractionData LeakageFrameworkInference
gradioCWE-227355 ATLAS
HIGHEXPLOIT AVAILSCANNER

AYS ChatGPT WP Plugin: auth bypass disables AI service

CVE-2024-7714
7.5
EPSS 0.8%
Auth BypassData LeakageDoSPluginAPI
4 ATLAS1 incident
HIGHEXPLOIT AVAIL

vLLM: unauthenticated DoS via empty completion prompt

CVE-2024-8768
7.5
EPSS 0.7%
DoSInferenceAPIFramework
4 ATLAS
HIGHEXPLOIT AVAIL

LangChain: RCE via FAISS pickle deserialization

CVE-2024-5998
7.8
EPSS 0.4%
Code ExecutionSupply ChainFrameworkRAG
langchain3.2K4 ATLAS
HIGHKEV

LiteLLM: SSRF leaks OpenAI API key to attacker

CVE-2024-6587
7.5
EPSS 34.4%
Data ExtractionAuth BypassAPIFramework
litellm65 ATLAS
HIGHEXPLOIT AVAIL

MindsDB: RCE via eval() injection in ChromaDB INSERT

CVE-2024-45848
8.8
EPSS 0.9%
Code ExecutionData ExtractionFrameworkRAGPlugin
CWE-945 ATLAS
HIGHEXPLOIT AVAIL

Ollama: ZIP path traversal exposes host filesystem

CVE-2024-45436
7.5
EPSS 2.6%
Supply ChainData ExtractionFrameworkModelInference
ollamaCWE-221.9K6 ATLAS
HIGHEXPLOIT AVAIL

OpenShift AI: model auth bypass via exposed token

CVE-2024-7557
8.8
EPSS 1.0%
Auth BypassData LeakageFrameworkInferenceAPI
rhoai/odh-kf-notebook-controller-rhel83.0K4 ATLAS
HIGHEXPLOIT AVAIL

Langflow: mass assignment grants super admin access

CVE-2024-7297
8.8
EPSS 21.2%
Auth BypassCode ExecutionFrameworkAgent
langflow4 ATLAS
HIGHEXPLOIT AVAIL

TorchServe: default gRPC exposure allows unauth inference

CVE-2024-35199
8.2
EPSS 0.6%
DoSData ExtractionAuth BypassInferenceFramework
torchserve26.1K5 ATLAS
HIGHEXPLOIT AVAIL

langchain-experimental: RCE via eval() in VectorSQL chain

CVE-2024-21513
8.5
EPSS 1.9%
Code ExecutionPrompt InjectionData ExtractionFrameworkRAGAgent
langchain-experimental3.2K5 ATLAS
HIGHEXPLOIT AVAIL

Flowise: CORS wildcard enables file read and data theft

CVE-2024-36421
7.5
EPSS 8.5%
Data ExtractionAuth BypassData LeakageAgentFramework
flowiseCWE-3465 ATLAS
HIGHEXPLOIT AVAILSCANNER

Flowise: unauthenticated arbitrary file read via API

CVE-2024-36420
7.5
EPSS 1.8%
Data ExtractionAuth BypassData LeakageFrameworkAPIAgent
flowiseCWE-746 ATLAS
HIGHEXPLOIT AVAIL

LangChain: Python REPL code execution without opt-in

CVE-2024-38459
7.8
EPSS 0.2%
Code ExecutionPrompt InjectionData ExtractionFrameworkAgent
langchain-experimental3.2K5 ATLAS
HIGHEXPLOIT AVAIL

ONNX: path traversal in model download enables RCE

CVE-2024-5187
8.8
EPSS 1.2%
Supply ChainCode ExecutionFrameworkModel
onnxPatch: 1.16.2CWE-221.1K4 ATLAS
HIGHEXPLOIT AVAIL

litellm: arbitrary file deletion via audio endpoint

CVE-2024-4888
8.1
EPSS 0.6%
Auth BypassDoSFrameworkAPI
litellm63 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