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

Open WebUI: XSS in terminal preview hijacks user accounts

CVE-2026-87995
8.7
EPSS 0.4%
Code ExecutionAuth BypassFrameworkPlugin
open-webuiPatch: 0.11.1CWE-7921 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: channel authz gap allows message spoofing

CVE-2026-87994
4.3
EPSS 0.4%
Auth BypassFrameworkInference
open-webuiPatch: 0.11.1CWE-63922 ATLAS
MEDIUM

Open WebUI: KB metadata leaks across tenants in 11 backends

CVE-2026-87017
4.3
EPSS 0.4%
Data LeakageAuth BypassPrivacy ViolationRAGFramework
open-webuiPatch: 0.11.1CWE-20023 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: OAuth wildcard bug hijacks admin sessions

CVE-2026-87016
8.1
EPSS 0.6%
Auth BypassPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.11.1CWE-15522 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: session cookies leak to rogue tool server

CVE-2026-87015
6.8
EPSS 0.5%
Auth BypassData LeakageAgentPluginAPI
open-webuiPatch: 0.11.1CWE-20123 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: demoted admins keep socket access to all notes

CVE-2026-87014
6.5
EPSS 0.5%
Auth BypassPrivacy ViolationFramework
open-webuiPatch: 0.11.1CWE-61321 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: authenticated DoS via folder cycle

CVE-2026-87013
4.3
EPSS 0.5%
DoSFrameworkAPI
open-webuiPatch: 0.11.1CWE-83523 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: type confusion suppresses all reminders

CVE-2026-87012
4.3
EPSS 0.5%
DoSFramework
open-webuiPatch: 0.11.1CWE-7542
HIGHEXPLOIT AVAIL

Open WebUI: unauth DoS via OIDC logout handler

CVE-2026-87011
7.5
EPSS 0.6%
DoSFrameworkAPI
open-webuiPatch: 0.11.1CWE-40522 ATLAS
HIGH

Chainlit: path traversal via sessionId wipes directories

CVE-2026-86099
8.2
EPSS 0.6%
DoSAuth BypassFramework
chainlit412 ATLAS
MEDIUMSCANNER

CyberPanel: AI Scanner endpoints leak admin usernames unauthenticated

CVE-2026-87820
5.3
EPSS 0.9%
Data LeakageAuth BypassAPIPlugin
CWE-2002 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS in notebook template paths

CVE-2026-87811
7.3
EPSS 0.4%
Code ExecutionData LeakagePlugin
1 ATLAS
HIGH

WPBot: unauth stored XSS in chatbot conversation field

CVE-2026-83593
7.2
EPSS 0.5%
Auth BypassCode ExecutionData LeakagePluginAgent
WPBot – AI ChatBot for Live Support, Lead Generation, AI ServicesCWE-791 ATLAS
HIGH

InsydeH2O: BIOS memory corruption enables local RCE

CVE-2026-12855
8.2
EPSS 0.2%
Code ExecutionInference
InsydeH2O27
HIGH

InsydeH2O UEFI: BIOS Shell allows Secure Boot bypass

CVE-2026-6485
8.2
EPSS 0.2%
Auth BypassCode ExecutionInference
InsydeH2O27
MEDIUM

n8n Git node: config injection leaks local files

CVE-2026-86995
--
EPSS 0.4%
Data LeakagePrivacy ViolationAgentPlugin
n8nPatch: 1.123.76CWE-22163 ATLAS
MEDIUM

n8n: broken authZ leaks workflow IDs to any member

CVE-2026-86994
--
EPSS 0.3%
Auth BypassData LeakageAgent
n8nPatch: 1.123.76CWE-862161 ATLAS
MEDIUM

n8n: cross-project credential theft via Log Streaming

CVE-2026-86993
--
EPSS 0.5%
Auth BypassData LeakageAgentPlugin
n8nPatch: 1.123.76CWE-862163 ATLAS
MEDIUM

n8n: missing scope check leaks project member emails

CVE-2026-86085
--
EPSS 0.4%
Auth BypassPrivacy ViolationAgent
n8nPatch: 2.38.2CWE-862162 ATLAS
MEDIUM

n8n: stale OIDC endpoint bypasses disabled SSO

CVE-2026-86084
--
EPSS 0.5%
Auth BypassAgent
n8nPatch: 1.123.76CWE-288162 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