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 1908 results — High severity
HIGHEXPLOIT AVAIL

Open WebUI: task auth bypass enables cross-user DoS

CVE-2026-45399
7.1
EPSS 0.3%
Auth BypassDoSInferenceAPI
open-webuiPatch: 0.9.0CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: IDOR exposes private RAG knowledge bases

CVE-2026-45398
7.5
EPSS 0.3%
Auth BypassData ExtractionModel PoisoningRAGAPI
open-webuiPatch: 0.9.5CWE-63925 ATLAS
HIGHEXPLOIT AVAIL

open-webui: missing authz allows admin tool hijacking

CVE-2026-45350
7.1
EPSS 0.3%
Auth BypassCode ExecutionPluginAgent
open-webuiPatch: 0.8.6CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: auth bypass exposes all user chat histories

CVE-2026-45349
7.1
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
open-webuiPatch: 0.9.0CWE-63926 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF via OAuth picture claim leaks internal data

CVE-2026-45338
7.7
EPSS 0.4%
Data ExtractionAuth BypassFrameworkAPI
open-webuiPatch: 0.9.0CWE-91825 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF bypass exposes cloud IAM credentials

CVE-2026-45331
8.5
EPSS 0.3%
Data ExtractionAuth BypassFrameworkAPI
open-webuiPatch: 0.9.0CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: Stored XSS via webhook SVG profile image

CVE-2026-45314
--
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassFrameworkAPI
open-webuiPatch: 0.9.3CWE-8725 ATLAS
HIGHEXPLOIT AVAIL

open-webui: stored XSS → JWT theft and admin takeover

CVE-2026-45315
8.7
EPSS 0.2%
Auth BypassData ExtractionCode ExecutionFrameworkAPIAgent
open-webuiPatch: 0.9.3CWE-7925 ATLAS
HIGH

SageMaker: RCE via poisoned Triton model artifacts in S3

CVE-2026-8597
7.2
EPSS 0.5%
Supply ChainCode ExecutionInferenceModel
sagemakerPatch: 2.257.2CWE-354503 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: XSS iframe allows auth token exfiltration

CVE-2026-45303
7.7
EPSS 0.2%
Data ExtractionCode ExecutionSocial EngineeringFrameworkAPI
open-webuiPatch: 0.6.5CWE-7927 ATLAS
HIGHEXPLOIT AVAIL

open-webui: BOLA exposes all users' uploaded files

CVE-2026-45301
8.1
EPSS 0.3%
Auth BypassData ExtractionPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.3.16CWE-28424 ATLAS
HIGHEXPLOIT AVAIL

Crabbox: IDOR lets viewers hijack Code/VNC/Egress

CVE-2026-8629
8.1
EPSS 0.3%
Auth BypassCode ExecutionAgent
crabbox33 ATLAS
HIGH

Crabbox: header spoofing bypasses lease auth

CVE-2026-8621
8.8
EPSS 0.4%
Auth BypassPrivacy ViolationAgentAPI
crabbox33 ATLAS
HIGH

Flowise: mass assignment enables cross-workspace IDOR

GHSA-wxrr-jp8m-qq7f
--
Auth BypassData LeakageData ExtractionAgentFramework
flowisePatch: 3.1.2CWE-9154 ATLAS
HIGH

Flowise: mass assignment breaks workspace isolation

GHSA-mq53-pc65-wjc4
--
Auth BypassData ExtractionPrivacy ViolationAgentFramework
flowisePatch: 3.1.2CWE-9155 ATLAS
HIGH

Flowise: mass assignment breaks cross-workspace isolation

GHSA-7j65-65cr-6644
--
Auth BypassData ExtractionPrivacy ViolationAgentFrameworkTraining Data
flowisePatch: 3.1.2CWE-9155 ATLAS
HIGH

Flowise: mass assignment enables cross-workspace data takeover

GHSA-5h9v-837x-m97r
--
Auth BypassData ExtractionPrivacy ViolationAgentFramework
flowisePatch: 3.1.2CWE-9154 ATLAS
HIGH

Flowise: mass assignment breaks cross-workspace isolation

GHSA-728h-4mwj-f2p4
--
Auth BypassData ExtractionAgentFramework
flowisePatch: 3.1.2CWE-9154 ATLAS
HIGH

Flowise: IDOR via mass assignment breaks tenant isolation

GHSA-78pr-c5x5-jggc
--
Auth BypassData ExtractionAgentFramework
flowisePatch: 3.1.2CWE-9155 ATLAS
HIGH

Flowise: missing authz on vector store CRUD endpoints

GHSA-hmg2-jjjx-jcp2
--
Auth BypassData ExtractionData LeakageAgentRAGFramework
flowisePatch: 3.1.2CWE-8627 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