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

95

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4307 results
MEDIUM

Craft CMS: read-only role can restructure categories

CVE-2026-72785
4.3
EPSS 0.3%
Auth BypassPlugin
MEDIUMEXPLOIT AVAIL

Ray Enterprise Translation WP plugin: broken access control

CVE-2026-14549
4.3
EPSS 0.3%
Auth BypassPlugin
Ray Enterprise Translation642
MEDIUMEXPLOIT AVAIL

Ray Translation WP: Subscribers can hijack API token

CVE-2026-14548
6.5
EPSS 0.3%
Auth BypassPluginAPI
Ray Enterprise Translation642
HIGH

odh-dashboard: unvalidated roleRef enables cluster-admin

CVE-2026-18950
8.8
EPSS 0.5%
Auth BypassCode ExecutionFramework
rhoai/odh-mod-arch-mlflow-rhel96951 ATLAS
HIGH

ODH Dashboard: SA token abuse escalates to cluster-admin

CVE-2026-18949
8.8
EPSS 0.7%
Auth BypassData LeakageFramework
rhoai/odh-mod-arch-mlflow-rhel96952 ATLAS
CRITICAL

Feast: insecure UDF deserialization enables RCE

CVE-2026-18948
9.9
EPSS 1.1%
Code ExecutionAuth BypassData LeakageFrameworkInferenceTraining Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel93.4K4 ATLAS
HIGH

Feast: authz bypass in /materialize triggers DoS

CVE-2026-18947
8.5
EPSS 0.6%
Auth BypassDoSTraining DataAPI
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel93.4K3 ATLAS
MEDIUM

Feast operator: code injection escalates to cluster admin

CVE-2026-18942
5.5
EPSS 0.4%
Code ExecutionSupply ChainData LeakageFrameworkTraining Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel93.4K3 ATLAS
HIGH

Feast: no-auth default enables RCE via malicious UDF

CVE-2026-18941
7.7
EPSS 0.9%
Auth BypassCode ExecutionDoSFrameworkAPITraining Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel93.4K4 ATLAS
HIGH

OpenShift AI Pipelines: confused deputy grants node-root

CVE-2026-18621
7.6
EPSS 0.5%
Auth BypassCode ExecutionFrameworkAPI
rhaiis/vllm-cpu-rhel9943 ATLAS
HIGHEXPLOIT AVAIL

Accelerate: path traversal in checkpoint loading

CVE-2026-69112
7.1
EPSS 0.2%
Data LeakageDoSSupply ChainFrameworkModel
accelerateCWE-223.1K3 ATLAS
HIGHEXPLOIT AVAIL

Flowise: auth bypass leaks private chatflow files

CVE-2026-71962
7.5
EPSS 0.7%
Auth BypassData LeakageAgentFramework
flowiseCWE-8623 ATLAS
UNKNOWN

CTI-Transmute: stored XSS in graph UI via Pivotick

CVE-2026-72751
--
EPSS 0.5%
Code ExecutionData LeakagePlugin
1 ATLAS
HIGH

OpenSignServer: missing authz forges document declines

CVE-2026-72692
7.5
EPSS 0.4%
Auth BypassAgentPlugin
1 ATLAS
LOWEXPLOIT AVAIL

Booking Calendar: IDOR exposes any customer's PII

CVE-2026-14211
3.8
EPSS 0.3%
Auth BypassPrivacy ViolationPlugin
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

Ollama-mcp: command injection via model args

CVE-2026-19334
5.3
EPSS 1.1%
Code ExecutionAgentPlugin
CWE-742 ATLAS
UNKNOWNEXPLOIT AVAIL

lollms: path traversal enables unauth file read

CVE-2026-10595
--
EPSS 0.6%
Auth BypassData LeakageInference
parisneo/lollms3 ATLAS
HIGHEXPLOIT AVAIL

Flowise: SSRF bypass exposes cloud metadata credentials

CVE-2026-67620
7.7
EPSS 0.5%
Data LeakageAuth BypassAgentFramework
flowiseCWE-9183 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

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