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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4331 results
HIGHEXPLOIT AVAIL

Open WebUI: stored SVG XSS enables full account takeover

CVE-2026-54013
7.6
EPSS 0.3%
Auth BypassCode ExecutionData ExtractionAPIFramework
open-webuiPatch: 0.9.6CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: auth bypass enables cross-user file read/delete

CVE-2026-54012
7.1
EPSS 0.3%
Auth BypassData ExtractionData LeakageRAGAgentFramework
open-webuiPatch: 0.9.6CWE-28425 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: Stored XSS via Mermaid loose mode in preview

CVE-2026-54011
8.7
EPSS 0.3%
Code ExecutionData ExtractionAuth BypassFrameworkPlugin
open-webuiPatch: 0.9.6CWE-7925 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: IDOR allows cross-user file read and delete

CVE-2026-54010
8.3
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.9.6CWE-28424 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: cross-user file read via auth bypass

CVE-2026-54009
6.5
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
open-webuiPatch: 0.9.6CWE-63924 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF via OAuth picture redirect bypass

CVE-2026-54008
8.5
EPSS 0.3%
Data ExtractionPrivacy ViolationAPIInference
open-webuiPatch: 0.9.6CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

open-webui: cross-origin postMessage forces model execution

CVE-2026-54007
--
EPSS 0.2%
Prompt InjectionAuth BypassCode ExecutionAPIAgent
open-webuiPatch: 0.9.6CWE-34625 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: auth bypass allows cross-user calendar injection

CVE-2026-54006
4.3
EPSS 0.3%
Auth BypassSocial EngineeringPrivacy ViolationFramework
open-webuiPatch: 0.9.6CWE-63925 ATLAS
MEDIUM

vLLM: decompression bomb OOM via audio endpoint

CVE-2026-54233
6.5
EPSS 0.4%
DoSInferenceAPI
vllmPatch: 0.24.0CWE-409943 ATLAS
MEDIUMEXPLOIT AVAILSCANNER

vLLM: heap address leak enables ASLR bypass

CVE-2026-54236
5.3
EPSS 0.9%
Data LeakageCode ExecutionInferenceAPI
vllmPatch: 0.24.0CWE-532943 ATLAS
HIGH

vLLM: integer truncation leaks GPU memory cross-tenant

CVE-2026-53923
7.5
EPSS 0.5%
Data ExtractionSupply ChainPrivacy ViolationInferenceModel
vllmPatch: 0.24.0CWE-200944 ATLAS
MEDIUM

vllm: EXIF/tRNS preprocessing gap enables adversarial input

GHSA-8jr5-v98p-w75m
4.8
Adversarial ExamplesPrompt InjectionInferenceFramework
vllmCWE-436944 ATLAS
MEDIUM

vLLM: NaN/Inf bypass crashes GPU inference workers

CVE-2026-54235
6.5
EPSS 0.4%
DoSInference
vllmPatch: 0.24.0CWE-1287943 ATLAS
MEDIUM

n8n: viewer role can start/cancel/delete eval workflow runs

GHSA-664h-gpgq-h6xx
5.4
Auth BypassDoSAgentFramework
n8nPatch: 1.123.55CWE-863163 ATLAS
CRITICAL

Oracle Coherence: unauthenticated HTTP full takeover

CVE-2026-35310
9.8
EPSS 0.5%
Auth BypassCode ExecutionData ExtractionAPIInferenceFramework
coherence3804 ATLAS
CRITICAL

Oracle Coherence: unauthenticated RCE via HTTP (CVSS 9.8)

CVE-2026-35309
9.8
EPSS 0.5%
Code ExecutionAuth BypassData ExtractionFrameworkAPIInference
coherence3803 ATLAS
CRITICAL

Oracle Coherence: unauthenticated RCE via third-party jars

CVE-2026-35308
10.0
EPSS 0.5%
Code ExecutionAuth BypassSupply ChainFrameworkInferenceAPI
coherence3804 ATLAS
CRITICAL

Oracle Coherence: unauthenticated RCE, CVSS 10.0

CVE-2026-35307
10.0
EPSS 0.5%
Code ExecutionAuth BypassData ExtractionFrameworkAPIInference
coherence3804 ATLAS
CRITICAL

Oracle Coherence: unauthenticated data access via HTTP

CVE-2026-35306
9.3
EPSS 0.4%
Data ExtractionAuth BypassData LeakageAPIInferenceFramework
coherence3804 ATLAS
CRITICAL

Oracle Coherence: unauth data exfiltration via bundled libs

CVE-2026-35305
9.3
EPSS 0.3%
Data ExtractionAuth BypassAPIFramework
coherence3804 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