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 2876 results — no patch
MEDIUMEXPLOIT AVAIL

CKAN MCP Server: DNS-based SSRF reaches cloud metadata

CVE-2026-61612
5.7
EPSS 0.4%
Data ExtractionData LeakagePluginAgentAPI
CWE-9184 ATLAS
HIGH

libstdc++: integer overflow in aligned new risks corruption

CVE-2026-95619
7.7
DoSCode ExecutionFrameworkInferenceTraining Data
rhoai/odh-mlflow-operator-rhel96952 ATLAS
MEDIUM

PixelPlay WP: missing auth lets attackers delete API keys

CVE-2025-14486
5.3
EPSS 0.3%
Auth BypassPluginAPI
CWE-8622 ATLAS
HIGH

TranslatePress: stored XSS via translation memory panel

CVE-2026-89412
7.2
EPSS 0.5%
Code ExecutionData LeakagePluginFramework
CWE-792 ATLAS
HIGH

vLLM: Mooncake KV cache leak enables GPU DoS

CVE-2026-94627
7.5
EPSS 0.6%
DoSInferenceFrameworkAPI
vllmCWE-401944 ATLAS
HIGH

vLLM: unvalidated tp_size allows memory-exhaustion DoS

CVE-2026-94626
7.5
EPSS 0.6%
DoSInferenceAPI
vllmCWE-789943 ATLAS
MEDIUM

vLLM: Mooncake placeholder leak enables slow DoS

CVE-2026-94625
5.3
EPSS 0.5%
DoSInferenceFramework
vllmCWE-772943 ATLAS
HIGH

vLLM: NIXL multi-prompt assertion crash causes DoS

CVE-2026-94623
7.5
EPSS 0.6%
DoSInferenceAPIFramework
vllmCWE-617943 ATLAS
HIGH

vLLM: NIXL KeyError crashes decode engine remotely

CVE-2026-94622
7.5
EPSS 0.6%
DoSInferenceFramework
vllmCWE-248943 ATLAS
MEDIUMEXPLOIT AVAIL

Joplin Server: pending share invite allows item injection

CVE-2026-59815
4.3
EPSS 0.2%
Auth BypassPlugin
CWE-8632 ATLAS
HIGHEXPLOIT AVAIL

Joplin Server: stored XSS via SVG share, session abuse

CVE-2026-59814
7.6
EPSS 0.4%
Data LeakageAuth BypassPlugin
CWE-792 ATLAS
HIGH

Joplin Server: SAML login bypass takes over local accounts

CVE-2026-55210
7.4
EPSS 0.5%
Auth BypassData LeakageAPI
CWE-2903 ATLAS
MEDIUMEXPLOIT AVAIL

Joplin: XSS via unanchored URL regex in shared notes

CVE-2026-46650
4.4
EPSS 0.3%
Code ExecutionData LeakagePlugin
CWE-792 ATLAS
HIGH

x-ui: improper access control exposes xray gRPC

CVE-2026-79316
7.6
EPSS 0.3%
Auth BypassFramework
2 ATLAS
MEDIUMEXPLOIT AVAIL

Joplin Server: path traversal in transcribe API leaks data

CVE-2026-59816
4.3
EPSS 0.4%
Data LeakageData ExtractionAPIInference
CWE-223 ATLAS
MEDIUMEXPLOIT AVAIL

Joplin Server: IDOR exposes other users' note content

CVE-2026-55179
6.5
EPSS 0.3%
Data LeakageAuth BypassAPI
CWE-6392 ATLAS
HIGH

Joplin: stored XSS via Fountain renderer exposes notes

CVE-2026-55105
7.7
EPSS 0.5%
Data LeakageData ExtractionPlugin
CWE-791 ATLAS
HIGHEXPLOIT AVAIL

Joplin: path traversal in sync allows arbitrary file write

CVE-2026-49453
7.0
EPSS 0.4%
Supply ChainCode ExecutionPlugin
CWE-202 ATLAS
HIGHEXPLOIT AVAIL

Joplin Desktop: update signature check skipped on Windows

CVE-2026-49450
7.1
EPSS 0.2%
Supply ChainCode ExecutionPlugin
CWE-3452 ATLAS
LOWEXPLOIT AVAIL

Joplin: KaTeX \href bypass leaks NTLMv2 hash on Windows

CVE-2026-49449
2.5
EPSS 0.2%
Data LeakageSocial EngineeringPlugin
CWE-2003 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