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

open-webui: broken authz lets users delete others' KB data

CVE-2026-70488
4.3
EPSS 0.4%
Auth BypassDoSRAGFramework
open-webuiPatch: 0.11.0CWE-6392
MEDIUM

open-webui: image-gen permission bypass in chat API

CVE-2026-70484
4.3
EPSS 0.4%
Auth BypassFrameworkAPIPlugin
open-webuiPatch: 0.11.0CWE-86222 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: client-side SSRF via Vega chart rendering

CVE-2026-70480
4.1
EPSS 0.3%
Data LeakageData ExtractionFrameworkRAG
open-webuiPatch: 0.11.0CWE-91822 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: members can edit/delete others' channel messages

CVE-2026-70481
5.4
EPSS 0.4%
Auth BypassDoSFrameworkAPI
open-webuiPatch: 0.11.0CWE-28421 ATLAS
MEDIUM

Flowise: missing auth on TTS drains owner's API budget

GHSA-8gj2-2cvc-6xx7
--
Auth BypassDoSAgentAPI
flowisePatch: 3.1.4CWE-8623 ATLAS
MEDIUM

Flowise: credential API leaks plaintext DB/cloud secrets

GHSA-rwrp-9823-p2xq
6.5
Data LeakagePrivacy ViolationAgentFramework
flowisePatch: 3.1.3CWE-2003 ATLAS
MEDIUM

Flowise: IDOR exposes customer PII and billing data

GHSA-2364-jh4q-m9vm
--
Auth BypassData LeakagePrivacy ViolationFrameworkAgent
flowisePatch: 3.1.3CWE-6392 ATLAS
MEDIUMEXPLOIT AVAIL

SiYuan: metadata leak bypasses publish-access checks

CVE-2026-68585
5.8
EPSS 0.2%
Auth BypassData LeakageAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260721014951-ffde3b21eca4CWE-8623.0K2 ATLAS
MEDIUM

Keras: HDF5 ExternalLink flaw leaks local files on load

CVE-2026-9335
6.5
EPSS 0.8%
Data LeakageSupply ChainFrameworkModel
kerasPatch: 3.12.3CWE-224.1K3 ATLAS
MEDIUM

Pydantic AI: UploadedFile refs leak cloud storage

CVE-2026-54249
6.8
EPSS 0.3%
Auth BypassData LeakagePrivacy ViolationAgentFramework
pydantic-aiPatch: 1.106.0CWE-9185123 ATLAS
MEDIUMEXPLOIT AVAIL

datasets: path traversal via file_name leaks local files

CVE-2026-66007
6.5
EPSS 0.5%
Data LeakageSupply ChainTraining DataFramework
datasetsPatch: 5.0.1CWE-222.8K4 ATLAS
MEDIUM

n8n: SQL injection in Snowflake Execute Query node

GHSA-652q-gvq3-74qv
--
Code ExecutionData LeakageAgentFramework
n8nPatch: 1.123.67CWE-89163 ATLAS
MEDIUM

n8n: SQL injection in Postgres Trigger node

GHSA-jqwr-vx3p-r266
--
Code ExecutionData LeakageAgentPlugin
n8nPatch: 1.123.67CWE-89163 ATLAS
MEDIUM

n8n: shared module cache poisoning breaks user isolation

GHSA-9cmh-xcqm-5hqr
--
Code ExecutionPrivacy ViolationAgentPlugin
n8nPatch: 1.123.67CWE-20161 ATLAS
MEDIUM

JupyterLab: extension blocklist bypass via name mismatch

GHSA-89vp-jrxv-24w8
--
Auth BypassCode ExecutionPluginFramework
jupyterlabPatch: 4.6.2CWE-1781.9K1 ATLAS
MEDIUM

JupyterLab: plugin lock bypass via direct API access

GHSA-h5v5-8746-g7mm
--
Auth BypassData LeakagePlugin
jupyterlabPatch: 4.6.2CWE-6021.9K1 ATLAS
MEDIUM

n8n: path traversal in computer-use tool leaks files

GHSA-pf2q-pxhf-hgmw
--
Data LeakageAuth BypassAgentPlugin
n8nPatch: 2.32.1CWE-22163 ATLAS
MEDIUM

n8n: prototype pollution in expression engine causes DoS

GHSA-hx4h-vr3m-45vh
--
DoSAgent
n8nPatch: 1.123.67CWE-1321162 ATLAS
MEDIUM

n8n: MCP Client SSRF bypasses egress protection

GHSA-vhf8-cg2h-cg3p
--
Data LeakageData ExtractionAgentPlugin
n8nPatch: 2.32.1CWE-918163 ATLAS
MEDIUM

n8n: GCP service account key leaks via JWT header

CVE-2026-65599
--
EPSS 0.2%
Data LeakageAuth BypassAgentAPI
n8nPatch: 1.123.64CWE-312163 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