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
HIGHEXPLOIT AVAIL

Mistral Vibe: RCE via git hooks run before trust check

CVE-2026-93993
8.8
EPSS 0.8%
Code ExecutionSupply ChainAgentFramework
mistral-vibe4734 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS in heading style enables Electron RCE

CVE-2026-93923
8.8
EPSS 0.6%
Code ExecutionData LeakageFrameworkPlugin
CWE-793 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS in notebook names enables RCE

CVE-2026-93922
8.8
EPSS 0.8%
Code ExecutionFramework
CWE-793 ATLAS
LOWEXPLOIT AVAIL

Suricata: NULL deref crash via malformed dataset JSON

CVE-2026-57225
3.3
EPSS 0.2%
DoSFramework
1 ATLAS
MEDIUM

vLLM: OOB write in penalty kernel corrupts requests

CVE-2026-93841
5.3
EPSS 0.2%
DoSInferenceFramework
vllmCWE-129943 ATLAS
MEDIUM

vLLM: token ID validation flaw corrupts cross-request logits

CVE-2026-93840
5.3
EPSS 0.2%
DoSData LeakageInferenceAPI
vllmCWE-129943 ATLAS
HIGHEXPLOIT AVAIL

ToolHive: default network profile enables MCP lateral movement

CVE-2026-58197
8.8
EPSS 0.4%
Auth BypassData ExtractionCode ExecutionAgentPluginFramework
github.com/stacklok/toolhivePatch: 0.30.1CWE-2841.9K5 ATLAS
HIGH

lmdeploy: URL parser mismatch enables SSRF bypass

GHSA-39wr-7q6h-cf68
7.5
Data ExtractionAuth BypassInferenceAPI
lmdeployPatch: 0.15.0CWE-43613 ATLAS
HIGHEXPLOIT AVAIL

LMDeploy: eval() injection via malicious model config

CVE-2026-33625
8.8
EPSS 0.4%
Code ExecutionSupply ChainInferenceFrameworkModel
lmdeployPatch: 0.12.3CWE-40015 ATLAS
CRITICAL

LMDeploy: pickle deserialization RCE in DistServe

CVE-2025-66455
9.8
EPSS 1.3%
Code ExecutionAuth BypassInferenceAPIFramework
lmdeployPatch: 0.16.0CWE-50214 ATLAS
HIGHEXPLOIT AVAIL

vLLM: negative token ID crashes embeddings engine

CVE-2026-93592
7.5
EPSS 0.5%
DoSInferenceAPI
vllmCWE-129943 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: SQL injection in getGraph exposes private notes

CVE-2026-93591
7.6
EPSS 0.3%
Data ExtractionData LeakageFrameworkAPI
CWE-893 ATLAS
MEDIUM

GPTranslate WP: plaintext AI API key exposed to anyone

CVE-2026-89278
5.3
EPSS 0.4%
Data LeakageData ExtractionPluginAPI
CWE-2004 ATLAS
HIGH

vLLM: memory leak in PD disaggregation causes DoS

CVE-2026-93436
7.5
EPSS 0.8%
DoSInferenceFrameworkAPI
vllmCWE-401943 ATLAS
MEDIUM

Amelia WP Plugin: missing ownership check exposes customers

CVE-2026-14311
5.4
EPSS 0.2%
Auth BypassData LeakagePlugin
CWE-8621 ATLAS
HIGHEXPLOIT AVAIL

Vvveb CMS: SSRF in oEmbed proxy leaks cloud metadata

CVE-2026-54507
--
EPSS 0.4%
Data LeakageData ExtractionAPI
3 ATLAS
HIGHEXPLOIT AVAIL

Jupyter Server: Referer token leak in 5xx logs

CVE-2026-86049
7.1
EPSS 0.4%
Data LeakageAuth BypassFramework
jupyterCWE-5321.9K3 ATLAS
HIGH

Grafana Geomap: stored XSS enables Org Admin escalation

CVE-2026-76154
7.3
EPSS 0.4%
Code ExecutionAuth BypassFramework
2 ATLAS
HIGHEXPLOIT AVAIL

Grav CMS: callable-array bypass enables authenticated RCE

CVE-2026-72819
8.8
EPSS 0.9%
Code ExecutionFramework
getgrav/gravPatch: 2.0.13CWE-945144 ATLAS
HIGHEXPLOIT AVAIL

Grav CMS: callable guard bypass enables file read/write

CVE-2026-69088
8.1
EPSS 0.3%
Code ExecutionData LeakageAuth BypassFramework
getgrav/gravPatch: 2.0.11CWE-945143 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