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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 544 results — Medium severity, has patch
MEDIUMEXPLOIT AVAIL

open-webui: infinite-loop DoS crashes entire server

CVE-2026-88002
6.5
EPSS 0.6%
DoSFramework
open-webuiPatch: 0.11.1CWE-83522 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: folder auth bypass injects rogue chats

CVE-2026-87997
4.3
EPSS 0.4%
Auth BypassFrameworkAPI
open-webuiPatch: 0.11.1CWE-63921 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
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
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
MEDIUM

n8n: GitHub webhook signature bypass on 422 retry

CVE-2026-86080
--
EPSS 0.3%
Auth BypassCode ExecutionAgentPlugin
n8nPatch: 1.123.76CWE-347162 ATLAS
MEDIUM

n8n: path traversal in Elasticsearch node leaks data

CVE-2026-86079
--
EPSS 0.5%
Auth BypassData LeakageAgentPlugin
n8nPatch: 1.123.76CWE-22162 ATLAS
MEDIUM

n8n: prototype pollution in AI workflow summary

CVE-2026-86078
--
EPSS 0.6%
DoSAgentFramework
n8nPatch: 2.38.2CWE-1321161 ATLAS
MEDIUM

n8n: chat token replay bypasses HITL approval gates

CVE-2026-86077
--
EPSS 0.4%
Auth BypassAgent
n8nPatch: 2.38.2CWE-862162 ATLAS
MEDIUM

SiYuan: missing authz leaks database view structure

GHSA-57v5-wqx3-cgj4
5.8
Auth BypassData LeakagePlugin
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260726004013-64c26e74bb82CWE-8623.0K1 ATLAS
MEDIUM

n8n: SSRF in AI credential setup leaks tokens

CVE-2026-86074
--
EPSS 0.4%
Auth BypassData LeakageAgentFramework
n8nPatch: 2.38.2CWE-918163 ATLAS
MEDIUM

n8n: OAuth refresh token skips workflow-resource binding

CVE-2026-86073
--
EPSS 0.4%
Auth BypassData LeakageAgentAPIPlugin
n8nPatch: 2.38.1CWE-863163 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