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 1908 results — High severity
HIGH

Velociraptor: VQL injection via notebook backup restore

CVE-2026-19584
7.7
EPSS 0.3%
Code ExecutionAuth BypassFramework
HIGHEXPLOIT AVAIL

nuxt-ollama: API key leaked in public SSR payload

CVE-2026-59158
7.5
EPSS 0.5%
Data LeakageAuth BypassFrameworkAPIInference
nuxt-ollamaPatch: 1.3.1CWE-5221.9K3 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: SSRF leaks Azure platform channel

CVE-2026-87999
7.1
EPSS 0.4%
Data LeakageRAG
open-webuiPatch: 0.11.1CWE-91822 ATLAS
HIGH

Open WebUI: authZ flaw lets users kill shared KB configs

CVE-2026-87998
7.1
EPSS 0.5%
Auth BypassDoSRAGAPI
open-webuiPatch: 0.11.1CWE-26922 ATLAS
HIGH

Open WebUI: DNS rebinding SSRF exposes internal svcs

CVE-2026-87996
7.7
EPSS 0.4%
Data LeakageAuth BypassRAGPlugin
open-webuiPatch: 0.11.1CWE-36723 ATLAS
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
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
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
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
HIGH

n8n: code injection via legacy expression engine

CVE-2026-86083
--
EPSS 0.7%
Code ExecutionSupply ChainFrameworkAgent
n8nPatch: 1.123.76CWE-94163 ATLAS
HIGH

n8n: OpenAI node leaks API key via SSRF bypass

CVE-2026-86082
--
EPSS 0.4%
Auth BypassData LeakageAgentAPI
n8nPatch: 1.123.76CWE-918162 ATLAS
HIGH

n8n: ReDoS via Git node clone freezes instance

CVE-2026-86081
--
EPSS 0.6%
DoSAgentFramework
n8nPatch: 1.123.76CWE-1333162 ATLAS
HIGH

n8n: expression sandbox escape enables RCE

CVE-2026-86076
--
EPSS 0.8%
Code ExecutionFrameworkAgent
n8nPatch: 1.123.76CWE-94161 ATLAS
HIGH

n8n: unauth OAuth DCR fields exhaust DB storage

CVE-2026-86075
--
EPSS 0.6%
DoSAgentAPI
n8nPatch: 2.38.2CWE-770162 ATLAS
HIGHEXPLOIT AVAIL

winml-cli: RCE via wildcard CORS + trust-remote-code

CVE-2026-84452
--
EPSS 1.6%
Code ExecutionAuth BypassSupply ChainFrameworkInferenceModel
winml-cliPatch: 0.4.0CWE-3061.1K4 ATLAS
HIGH

tiptap: ReDoS in Markdown attribute parsers

GHSA-j95f-988m-3j2f
--
DoSFramework
@tiptap/corePatch: 3.30.5CWE-40016.9K2 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