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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4331 results
HIGH

twig/twig: sandbox bypass leaks render context

CVE-2026-47732
--
EPSS 0.4%
Auth BypassData ExtractionSupply ChainFrameworkAPI
twig/twigPatch: 3.26.0CWE-206.3K5 ATLAS
HIGH

skillctl: path traversal enables credential exfiltration

GHSA-wx3m-whqv-xv47
--
Supply ChainData ExtractionPrivacy ViolationAgentPlugin
skillctlPatch: 0.1.2CWE-2225 ATLAS
HIGHEXPLOIT AVAIL

praisonai-platform: IDOR enables cross-workspace agent read/write/delete

CVE-2026-47419
8.3
EPSS 0.3%
Auth BypassData ExtractionData LeakageAgentAPI
praisonai-platformPatch: 0.1.4CWE-63915 ATLAS
MEDIUMEXPLOIT AVAIL

mcp-server-kubernetes: flag injection steals K8s tokens

CVE-2026-47250
6.1
EPSS 0.4%
Prompt InjectionAuth BypassData ExtractionAgentPlugin
mcp-server-kubernetesPatch: 3.7.0CWE-8816 ATLAS
LOW

onnx-mlir: weak hash enables model cache poisoning

CVE-2026-11329
3.6
EPSS 0.1%
Supply ChainModel PoisoningFrameworkInference
CWE-3272 ATLAS
MEDIUMEXPLOIT AVAIL

OpenAI Atlas: XSS enables browser history exfiltration

CVE-2026-11326
--
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationPluginAPI
5 ATLAS
CRITICAL

AVideo YPTSocket: Stored DOM XSS enables admin takeover

GHSA-8whc-2wmv-ww35
9.6
Auth BypassCode ExecutionData ExtractionPlugin
WWBN/AVideoCWE-795144 ATLAS
MEDIUM

OpenMeter: SQL injection leaks all-tenant metering data

CVE-2026-8462
--
EPSS 0.5%
Data ExtractionPrivacy ViolationAPIFramework
github.com/openmeterio/openmeterPatch: 1.0.0-beta.228CWE-896.3K5 ATLAS
HIGHEXPLOIT AVAIL

Milvus: weak hash allows RBAC grantee impersonation

CVE-2026-10814
7.0
EPSS 0.1%
Auth BypassData ExtractionPrivacy ViolationRAGFramework
milvusCWE-32774 ATLAS
LOWEXPLOIT AVAIL

LMCache: weak hash enables KV cache integrity bypass

CVE-2026-10813
3.6
EPSS 0.1%
Data LeakageDoSInference
lmcacheCWE-327943 ATLAS
MEDIUMEXPLOIT AVAIL

Streamlit: weak hash enables cache integrity bypass

CVE-2026-10804
4.7
EPSS 0.1%
Supply ChainDoSFrameworkInference
streamlitPatch: 1.53.1CWE-3273.1K3 ATLAS
LOWEXPLOIT AVAIL

MLflow: weak dataset hash allows integrity bypass

CVE-2026-10803
3.6
EPSS 0.1%
Supply ChainModel PoisoningFrameworkTraining Data
mlflowPatch: 3.10.1CWE-3276953 ATLAS
LOWEXPLOIT AVAIL

ms-swift: weak hash enables image cache poisoning

CVE-2026-10801
3.6
EPSS 0.1%
Model PoisoningSupply ChainTraining DataFramework
ms-swiftCWE-32763 ATLAS
LOWEXPLOIT AVAIL

Gradio: weak hash exposes audio cache to local users

CVE-2026-10783
2.5
EPSS 0.1%
Data ExtractionPrivacy ViolationFrameworkInference
gradioPatch: 6.15.1CWE-3277353 ATLAS
HIGH

Froxlor: 2FA bypass via API grants full account access

GHSA-f9rx-7wf7-jr36
8.1
Auth BypassData ExtractionPrivacy ViolationAPIFramework
froxlor/froxlorPatch: 2.3.7CWE-2875144 ATLAS
UNKNOWNEXPLOIT AVAIL

Enterprise Gateway: YAML injection → K8s cluster takeover

CVE-2026-44182
--
EPSS 0.6%
Code ExecutionAuth BypassFrameworkInference
jupyter_enterprise_gatewayPatch: 3.3.0CWE-741.9K4 ATLAS
UNKNOWNEXPLOIT AVAIL

Enterprise Gateway: SSTI allows full K8s cluster compromise

CVE-2026-44181
--
EPSS 0.8%
Code ExecutionData ExtractionAuth BypassFrameworkInference
jupyter_enterprise_gatewayPatch: 3.3.0CWE-13361.9K6 ATLAS
CRITICALEXPLOIT AVAIL

Jupyter Enterprise Gateway: root privilege bypass in Kubernetes

CVE-2026-44180
9.8
EPSS 0.7%
Auth BypassCode ExecutionFrameworkInference
jupyter_enterprise_gatewayPatch: 3.3.0CWE-201.9K4 ATLAS
HIGHEXPLOIT AVAIL

Froxlor: DNS zone injection via unsanitized TXT record

CVE-2026-41234
7.6
EPSS 0.3%
Data ExtractionSupply ChainAPIFramework
froxlor/froxlorPatch: 2.3.7CWE-745144 ATLAS
HIGHEXPLOIT AVAIL

jupyter-server: CORS bypass enables arbitrary code execution

CVE-2026-6657
8.8
EPSS 5.2%
Auth BypassCode ExecutionFramework
jupyter-serverCWE-3461.9K5 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