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
MEDIUM

Splunk Table Editor: stored SPL escalates power→admin

CVE-2026-76341
5.4
EPSS 0.2%
Auth BypassCode ExecutionSocial EngineeringTraining Data
2 ATLAS
HIGH

Splunk Enterprise: SPL injection via Dataset Explorer

CVE-2026-76254
7.5
EPSS 0.4%
Code ExecutionSocial EngineeringData ExtractionTraining Data
2 ATLAS
HIGH

GeoLens: authz flaws leak private geospatial data

GHSA-p77j-g7h5-r2vw
--
Auth BypassData LeakagePrivacy ViolationTraining DataAPIRAG
geolensPatch: 1.2.4CWE-932.8K4 ATLAS
MEDIUM

LangGraph API: authz bypass leaks assistant config

CVE-2026-55236
5.9
EPSS 0.3%
Auth BypassData LeakageFrameworkAgentAPI
langgraph-apiPatch: 0.10.0CWE-2854.1K2 ATLAS
MEDIUM

langgraph-api: loopback webhook bypasses cross-user auth

CVE-2026-55235
5.9
EPSS 0.4%
Auth BypassPrivacy ViolationFrameworkAgentAPI
langgraph-apiPatch: 0.10.0CWE-2874.1K1 ATLAS
HIGH

marimo: code injection via malicious MCP server config

CVE-2026-75149
8.8
EPSS 1.0%
Code ExecutionSupply ChainAgentPlugin
CWE-944 ATLAS
HIGH

Langflow: missing auth allows admin takeover

CVE-2026-19875
7.5
EPSS 0.5%
Auth BypassCode ExecutionFrameworkAgent
Langflow OSSCWE-3062 ATLAS
UNKNOWNEXPLOIT AVAIL

Grav API Plugin: authz bypass enables privilege escalation

CVE-2026-64852
--
EPSS 0.4%
Auth BypassPrivacy ViolationPluginAPI
CWE-862
MEDIUM

InsydeH2O: UEFI variable flaw exposes HDD password

CVE-2026-8810
6.9
EPSS 0.1%
Data ExtractionAuth BypassInference
InsydeH2O, InsydeH2O ARM271 ATLAS
LOW

FreeBSD ZFS: unprivileged user can spoof recv metadata flag

CVE-2026-49431
3.3
EPSS 0.1%
Auth BypassTraining Data
CRITICALEXPLOIT AVAIL

Froxlor: API leaks password hashes & TOTP seeds

CVE-2026-62988
9.0
EPSS 0.6%
Data LeakageAuth BypassAPI
froxlor/froxlorPatch: 2.3.8CWE-200514
MEDIUM

PeopleSoft: Panel Processor flaw enables unauthorized data access

CVE-2026-60884
4.4
EPSS 0.2%
Auth BypassData LeakageFramework
HIGH

Froxlor: stored XSS in DNS TXT record hijacks admin

CVE-2026-54347
8.7
EPSS 0.4%
Code ExecutionPrivacy ViolationFramework
froxlor/froxlorPatch: 2.3.8CWE-79514
UNKNOWN

Blueprint Studio: broken authz grants full HA control

CVE-2026-53453
--
EPSS 0.4%
Auth BypassCode ExecutionPrivacy ViolationPluginAgentAPI
CWE-8621 ATLAS
HIGH

MONAI: NumpyReader RCE via forced allow_pickle=True

GHSA-wg9g-w2j2-8pgr
7.8
Supply ChainCode ExecutionFrameworkTraining Data
monaiPatch: 1.6.0CWE-5021284 ATLAS
HIGH

MONAI: OS command injection via crafted YAML config

GHSA-rghg-q7wp-9767
--
Code ExecutionSupply ChainFrameworkTraining Data
MONAIPatch: 1.6.0CWE-781284 ATLAS
HIGH

MONAI: unpatched pickle deserialization enables RCE

GHSA-qxq5-qhx6-94qw
7.8
Code ExecutionSupply ChainFrameworkTraining Data
monaiPatch: 1.6.0CWE-5021283 ATLAS
HIGH

MeshCentral: stored XSS via unsanitized agent osdesc field

GHSA-c7hr-448w-65px
8.3
Code ExecutionPrivacy ViolationAgent
meshcentralPatch: 1.1.60CWE-20514
HIGH

GeoLens: IDOR leaks private datasets via AI metadata API

CVE-2026-55178
7.5
EPSS 0.6%
Auth BypassData LeakagePrivacy ViolationAPIRAG
geolensPatch: 1.2.3CWE-2002.8K3 ATLAS
CRITICALEXPLOIT AVAIL

CodeWhale: git_show argument injection enables file write

CVE-2026-75913
9.3
EPSS 0.5%
Prompt InjectionCode ExecutionSupply ChainAgent
codewhalePatch: 0.8.64CWE-734 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