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

95

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4307 results
CRITICAL

Sage AI Plugin: unrestricted upload → web shell RCE

CVE-2024-52384
9.9
EPSS 0.5%
Code ExecutionData ExtractionAuth BypassPluginAPI
5 ATLAS
HIGHEXPLOIT AVAIL

Intel Extension for Transformers: path traversal privesc

CVE-2024-21799
7.1
EPSS 0.7%
Code ExecutionSupply ChainFramework
4 ATLAS
HIGH

TorchGeo: RCE via code injection in geospatial ML lib

CVE-2024-49048
8.1
EPSS 1.2%
Code ExecutionSupply ChainFrameworkTraining Data
torchgeoPatch: 0.6.1CWE-94135 ATLAS
HIGH

LightGBM: heap buffer overflow enables network RCE

CVE-2024-43598
8.1
EPSS 1.4%
Code ExecutionSupply ChainFrameworkInferenceTraining Data
lightgbmCWE-1221.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

Gradio: path traversal exposes arbitrary server files

CVE-2024-51751
6.5
EPSS 0.7%
Data ExtractionData LeakageFramework
gradioCWE-227353 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: RCE via unsandboxed code component execution

CVE-2024-48061
9.8
EPSS 1.5%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-945 ATLAS
MEDIUMEXPLOIT AVAIL

Gradio: SSRF in DownloadButton exposes internal resources

CVE-2024-48052
6.5
EPSS 0.5%
Data ExtractionPrivacy ViolationFrameworkInference
gradioCWE-9187354 ATLAS
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
CRITICALEXPLOIT AVAIL

Langflow: Unauthenticated RCE via PythonCodeTool

CVE-2024-42835
9.8
EPSS 1.2%
Code ExecutionSupply ChainData ExtractionFrameworkAgentPlugin
langflow6 ATLAS
CRITICALEXPLOIT AVAIL

PyTorch: RCE via RemoteModule deserialization

CVE-2024-48063
9.8
EPSS 1.6%
Code ExecutionSupply ChainFrameworkTraining Data
pytorchCWE-50226.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

Lollms: SVG upload XSS enables session hijack and RCE

CVE-2024-6581
6.5
EPSS 0.7%
Code ExecutionData LeakageSocial EngineeringFrameworkAPI
lollmsCWE-794 ATLAS
CRITICALEXPLOIT AVAIL

LangChain GraphCypher: prompt injection enables DB wipe

CVE-2024-8309
9.8
EPSS 13.7%
Prompt InjectionData ExtractionDoSFrameworkAgentRAG
langchainCWE-743.2K7 ATLAS
CRITICALEXPLOIT AVAIL

LangChain.js: path traversal, arbitrary file read/write

CVE-2024-7774
9.1
EPSS 0.6%
Data ExtractionCode ExecutionData LeakageFrameworkAgent
langchain.jsCWE-223.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChainJS: prompt injection enables full graph DB takeover

CVE-2024-7042
9.8
EPSS 0.3%
Prompt InjectionData ExtractionCode ExecutionFrameworkAgentAPI
langchain3.2K6 ATLAS
CRITICALKEVSCANNER

CyberPanel: pre-auth RCE via secMiddleware bypass

CVE-2024-51567
10.0
EPSS 84.4%
Auth BypassCode ExecutionFramework
3 ATLAS
CRITICALKEVSCANNER

CyberPanel: auth bypass enables unauthenticated RCE

CVE-2024-51378
10.0
EPSS 94.7%
Auth BypassCode ExecutionPlugin
1 ATLAS
UNKNOWN

Cursor IDE: prompt injection triggers terminal RCE

CVE-2024-48919
--
EPSS 0.5%
Prompt InjectionCode ExecutionAgentAPI
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