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 565 results — Medium severity, Active exploitation
MEDIUMEXPLOIT AVAIL

Open WebUI: admin system prompts exposed to all users

CVE-2026-45351
6.5
EPSS 0.3%
Data LeakageAuth BypassData ExtractionAPIModelFramework
open-webuiPatch: 0.8.9CWE-20024 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: blind SSRF via PDF export HTML injection

CVE-2026-45347
4.3
EPSS 0.2%
Data ExtractionPrivacy ViolationInferenceAPI
open-webuiPatch: 0.5.11CWE-91823 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: IDOR allows unauthorized model modification

CVE-2026-45345
6.5
EPSS 0.2%
Auth BypassPrivacy ViolationAPIModel
open-webuiPatch: 0.5.7CWE-28524 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: API key restriction bypass via header swap

CVE-2026-45339
6.5
EPSS 0.3%
Auth BypassAPI
open-webuPatch: 0.9.0CWE-86324 ATLAS
MEDIUMEXPLOIT AVAIL

Open-WebUI: CSRF image URL leaks session cookies

CVE-2026-45317
4.6
EPSS 0.2%
Data LeakagePrivacy ViolationAuth BypassInferenceFramework
open-webuiPatch: 0.9.3CWE-2024 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: Stored XSS via Office file preview bypass

CVE-2026-45318
5.4
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassFrameworkAPI
open-webuiPatch: 0.9.3CWE-7925 ATLAS
MEDIUMEXPLOIT AVAIL

mistune: CSS injection enables phishing UI overlay

CVE-2026-44899
4.7
EPSS 0.2%
Social EngineeringData ExtractionPluginFramework
mistunePatch: 3.2.1CWE-795144 ATLAS
MEDIUMEXPLOIT AVAIL

mistune: XSS in TOC render via unescaped heading ID

CVE-2026-44898
6.1
EPSS 0.2%
Data ExtractionCode ExecutionFramework
mistunePatch: 3.2.1CWE-795144 ATLAS
MEDIUMEXPLOIT AVAIL

local-deep-research: HTML injection enables SSRF via WeasyPrint

CVE-2026-43979
5.0
EPSS 0.3%
Data ExtractionDoSFrameworkAPI
local-deep-researchPatch: 1.6.0CWE-791.9K4 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: auth bypass allows message tampering

CVE-2026-44571
6.5
EPSS 0.3%
Auth BypassPrompt InjectionAPIFramework
open-webuiPatch: 0.8.6CWE-86224 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: SQL/CQL injection in knowledge-store backends

CVE-2026-44337
6.3
EPSS 0.2%
Code ExecutionData ExtractionData LeakageAgentRAGFramework
PraisonAIPatch: 4.6.34CWE-2015 ATLAS
MEDIUMEXPLOIT AVAIL

Videos sync PDF: stored XSS via unsanitized media fields

CVE-2022-50949
6.4
EPSS 0.2%
Code ExecutionPlugin
MEDIUMEXPLOIT AVAIL

mistune: XSS via unescaped heading id= attribute

CVE-2026-44897
6.1
EPSS 0.2%
Code ExecutionData ExtractionFrameworkRAG
mistunePatch: 3.2.1CWE-795144 ATLAS
MEDIUMEXPLOIT AVAIL

mistune: math plugin XSS bypasses escape=True control

CVE-2026-44708
6.1
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassPluginFramework
mistuneCWE-795144 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: XSS in pending overlay enables session hijack

CVE-2026-44568
4.8
EPSS 0.2%
Data ExtractionCode ExecutionSocial EngineeringInferenceFramework
open-webuiPatch: 0.9.0CWE-7924 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: auth bypass exposes private group channels

CVE-2026-44561
5.4
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationAPI
open-webuiPatch: 0.9.0CWE-28424 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: private channel member list exposed to any user

CVE-2026-44559
4.3
EPSS 0.2%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
open-webuiPatch: 0.9.0CWE-86224 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: permission bypass exposes channels publicly

CVE-2026-44558
5.4
EPSS 0.2%
Auth BypassData LeakageAPIFramework
open-webuiPatch: 0.9.0CWE-86323 ATLAS
MEDIUMEXPLOIT AVAIL

BentoML: symlink traversal exfiltrates host secrets at build

CVE-2026-40610
5.5
EPSS 0.3%
Data ExtractionSupply ChainFramework
bentomlPatch: 1.4.39CWE-59234 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: speculative decoding DoS via penalty params

CVE-2026-44223
6.5
EPSS 0.4%
DoSInference
vllmPatch: 0.20.0CWE-131942 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