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:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 533 results — Critical severity

CRITICALKEVSCANNER

ray: Code Injection enables RCE

CVE-2025-62593

Code ExecutionAuth BypassSocial EngineeringFramework

rayPatch: 2.52.0CWE-946428 ATLAS

CRITICALEXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62608

Supply ChainCode ExecutionData ExtractionFrameworkTraining Data

mlxCWE-1224296 ATLAS

CRITICALEXPLOIT AVAIL

keras: Path Traversal enables file access

CVE-2025-12060

Supply ChainCode ExecutionFrameworkTraining Data

kerasPatch: 3.12.0CWE-224.1K4 ATLAS

CRITICALEXPLOIT AVAIL

mlflow: Path Traversal enables file access

CVE-2025-11201

Code ExecutionAuth BypassFramework

mlflowCWE-226956 ATLAS

mlflow: security flaw enables exploitation

CVE-2025-11200

Auth BypassData ExtractionSupply ChainFrameworkModelTraining Data

mlflowCWE-5216956 ATLAS

CRITICALEXPLOIT AVAIL

keras: Deserialization enables RCE

CVE-2025-49655

Code ExecutionSupply ChainFrameworkModel

kerasPatch: 3.11.3CWE-5024.1K5 ATLAS

CRITICALEXPLOIT AVAIL

VestaCP: backdoored installer, not an AI/ML CVE

CVE-2018-25117

Supply ChainCode ExecutionDoSFramework

Control Panel (CP)514

scio/PyTorch: torch.load weights_only bypass RCE

GHSA-m9mp-6x32-5rhg

Supply ChainCode ExecutionFrameworkModel

CRITICALEXPLOIT AVAIL

Flowise: path traversal in file tools leads to RCE

CVE-2025-61913

Code ExecutionData ExtractionAuth BypassAgentPluginFramework

CRITICALEXPLOIT AVAILSCANNER

Flowise: Unauthenticated RCE via MCP config injection

CVE-2025-59528

Code ExecutionSupply ChainAgentFrameworkPlugin

CRITICALEXPLOIT AVAIL

Flowise Cloud: cross-tenant env var exposure leaks API keys

CVE-2025-59434

Data ExtractionAuth BypassPrivacy ViolationFrameworkAPIAgent

CRITICALEXPLOIT AVAILSCANNER

Flowise: auth bypass in reset flow allows full ATO

CVE-2025-58434

Auth BypassData ExtractionAgentFramework

CRITICALEXPLOIT AVAIL

langchaingo: Jinja2 SSTI allows host filesystem read

CVE-2025-9556

Code ExecutionData ExtractionFrameworkAgent

CRITICALEXPLOIT AVAIL

n8n-workflows: path traversal in download_workflow endpoint

CVE-2025-55526

Data ExtractionAuth BypassCode ExecutionAgentFrameworkAPI

fastapi165 ATLAS

ExecuTorch: integer overflow RCE on model load

CVE-2025-30404

Code ExecutionSupply ChainFrameworkModelInference

executorchPatch: 0.7.0CWE-19075 ATLAS

ExecuTorch: integer overflow in model load → RCE

CVE-2025-30405

Code ExecutionSupply ChainFrameworkModelInference

executorchPatch: 0.7.0CWE-19074 ATLAS

ExecuTorch: heap buffer overflow RCE in model loading

CVE-2025-54951

Code ExecutionSupply ChainFrameworkModelInference

executorchPatch: 0.7.0CWE-12274 ATLAS

CRITICALEXPLOIT AVAIL

ExecuTorch: OOB read in model loader enables RCE

CVE-2025-54950

Code ExecutionSupply ChainFrameworkModelInference

executorchPatch: 0.7.0CWE-12574 ATLAS

ExecuTorch: heap buffer overflow RCE via model loading

CVE-2025-54949

Code ExecutionSupply ChainFrameworkModel

executorchPatch: 0.7.0CWE-12275 ATLAS

CRITICALEXPLOIT AVAIL

Azure OpenAI: SSRF EoP, no auth required (CVSS 10)

CVE-2025-53767

Auth BypassData ExtractionPrivacy ViolationAPIInference

azure_openai15.6K6 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