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
MEDIUM

vLLM: race condition bypasses prompt-embeds tensor guard

CVE-2026-73557
--
EPSS 0.2%
DoSCode ExecutionInferenceAPI
vllmPatch: 0.26.0CWE-362943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: ReDoS in structured output stalls engine

CVE-2026-73556
5.3
EPSS 0.5%
DoSInference
vllmPatch: 0.26.0CWE-400943 ATLAS
MEDIUM

vLLM: verbose errors leak host paths & usernames

CVE-2026-73555
5.3
EPSS 0.4%
Data LeakagePrivacy ViolationInferenceAPI
vllmPatch: 0.26.0CWE-209943 ATLAS
MEDIUM

hashi-vault-js: Vault tokens leaked via thrown errors

CVE-2026-55102
--
EPSS 0.2%
Data LeakageAuth BypassPluginAPI
hashi-vault-jsPatch: 0.5.2CWE-2091 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: authZ gap leaks private PDF annotations

CVE-2026-72808
5.8
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationFramework
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260723031702-509b35055940CWE-8623.0K2 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: broken access control exposes private docs

CVE-2026-72799
5.8
EPSS 0.3%
Data LeakageAuth BypassPrivacy ViolationRAG
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260724112156-5bae0926b896CWE-8623.0K3 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: missing authz leaks encrypted notebook metadata

CVE-2026-72797
5.8
EPSS 0.3%
Data LeakageAuth BypassRAG
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260724123622-8fb1b5766093CWE-8623.0K2 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: missing authz leaks notebook metadata

CVE-2026-72790
5.8
EPSS 0.3%
Auth BypassData LeakageAPIRAG
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260726005141-9edb321eb451CWE-8623.0K1 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: unauth info leak exposes admin workspace via getConf

CVE-2026-72788
5.8
EPSS 0.4%
Data LeakageAuth BypassPrivacy ViolationPlugin
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260812083335-251596fc0de2CWE-8633.0K2 ATLAS
MEDIUMEXPLOIT AVAIL

Keras: OOM DoS via malicious .keras model load

CVE-2026-12570
5.5
EPSS 0.2%
DoSSupply ChainFrameworkModel
kerasPatch: 3.15.0CWE-7704.1K4 ATLAS
MEDIUM

JupyterHub: unauth log flooding via long usernames

CVE-2026-54338
5.3
EPSS 0.4%
DoSFramework
jupyterhubPatch: 5.5.0CWE-4001.9K1 ATLAS
MEDIUM

Craft CMS: view-only role can restructure categories

GHSA-xxpx-f366-4xpq
--
Auth BypassPlugin
craftcms/cmsPatch: 5.10.6CWE-863514
MEDIUM

LangGraph Checkpoint: prefix match leaks cross-tenant data

CVE-2026-71433
5.3
EPSS 0.4%
Data LeakageAuth BypassFrameworkAgent
langgraph-checkpoint-sqlitePatch: 3.1.1CWE-2004.1K2 ATLAS
MEDIUM

Ghost: staff API leaks other staff password hashes

CVE-2026-70590
4.8
EPSS 0.3%
Data LeakagePrivacy ViolationAPI
ghostPatch: 6.54.1CWE-2002 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: ReDoS via knowledge search DoS

CVE-2026-70493
6.5
EPSS 0.6%
DoSAgentRAG
open-webuiPatch: 0.11.0CWE-133323 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: shared tool source leaks hardcoded API keys

CVE-2026-70491
6.5
EPSS 0.5%
Data LeakageAuth BypassPluginAgent
open-webuiPatch: 0.11.0CWE-20023 ATLAS
MEDIUM

open-webui: terminal WebSocket bypasses role gate

CVE-2026-70490
6.3
EPSS 0.3%
Auth BypassCode ExecutionPluginAgent
open-webuiPatch: 0.11.0CWE-86323 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: automation rule parsing freezes server

CVE-2026-70489
6.5
EPSS 0.6%
DoSAgentFramework
open-webuiPatch: 0.11.0CWE-40023 ATLAS
MEDIUM

Open WebUI: DNS-rebind SSRF bypasses URL check

CVE-2026-54020
6.3
EPSS 0.3%
Data ExtractionPrivacy ViolationRAGFrameworkAPI
open-webuiPatch: 0.11.0CWE-36723 ATLAS
MEDIUM

Open WebUI: IDOR leaks other users' RAG file content

CVE-2026-70487
5.3
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationRAGPlugin
open-webuiPatch: 0.11.0CWE-86222 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