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
3,591

AI/ML CVEs Tracked

481

Critical

96

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 2346 results — no patch
MEDIUM

n8n: path traversal in Git node bypasses repo sandbox

CVE-2026-72770
6.5
EPSS 0.5%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-22 2 ATLAS
UNKNOWN

n8n: prototype pollution in VM engine crashes process

CVE-2026-72769
--
EPSS 0.3%
DoS Code Execution Agent Framework
n8n CWE-1321 2 ATLAS
HIGH

n8n: SSRF bypass in MCP Client node exposes internal hosts

CVE-2026-72768
8.3
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-918 3 ATLAS
UNKNOWN

n8n: Git node RCE via malicious repo hooks

CVE-2026-72767
--
EPSS 0.5%
Code Execution Data Leakage Agent Plugin
n8n CWE-78 3 ATLAS
HIGH

n8n: Send Email node type confusion enables SSRF, LFI

CVE-2026-72766
7.5
EPSS 0.3%
Data Leakage Data Extraction Framework Agent
n8n CWE-843 2 ATLAS
CRITICAL

n8n: expression sandbox escape leads to RCE

CVE-2026-72765
9.9
EPSS 0.4%
Code Execution Agent Framework
n8n CWE-94 3 ATLAS
UNKNOWN

n8n: module cache poisoning breaks multi-user isolation

CVE-2026-72764
--
EPSS 0.4%
Code Execution Data Leakage DoS Agent Framework
n8n CWE-668 1 ATLAS
MEDIUM

n8n: Editor role bypasses credential ACL via sub-workflow

CVE-2026-72763
6.5
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-639 3 ATLAS
UNKNOWN

n8n: arbitrary file write via Edit Image node format param

CVE-2026-72762
--
EPSS 0.3%
Code Execution Agent Plugin
n8n CWE-434 1 ATLAS
HIGH

n8n: SQL injection via Snowflake node Execute Query

CVE-2026-72750
8.8
EPSS 0.3%
Code Execution Data Extraction Agent Plugin
n8n CWE-89 1 ATLAS
MEDIUM

n8n: prototype pollution DoS via Edit Fields node

CVE-2026-72749
6.5
EPSS 0.3%
DoS Agent Framework
n8n CWE-1321
MEDIUM

Craft CMS: read-only role can restructure categories

CVE-2026-72785
4.3
EPSS 0.2%
Auth Bypass Plugin
MEDIUM EXPLOIT AVAIL

Ray Enterprise Translation WP plugin: broken access control

CVE-2026-14549
4.3
EPSS 0.2%
Auth Bypass Plugin
Ray Enterprise Translation 635
MEDIUM EXPLOIT AVAIL

Ray Translation WP: Subscribers can hijack API token

CVE-2026-14548
6.5
EPSS 0.2%
Auth Bypass Plugin API
Ray Enterprise Translation 635
HIGH

odh-dashboard: unvalidated roleRef enables cluster-admin

CVE-2026-18950
8.8
EPSS 0.4%
Auth Bypass Code Execution Framework
rhoai/odh-mod-arch-mlflow-rhel9 690 1 ATLAS
HIGH

ODH Dashboard: SA token abuse escalates to cluster-admin

CVE-2026-18949
8.8
EPSS 0.4%
Auth Bypass Data Leakage Framework
rhoai/odh-mod-arch-mlflow-rhel9 690 2 ATLAS
CRITICAL

Feast: insecure UDF deserialization enables RCE

CVE-2026-18948
9.9
EPSS 0.7%
Code Execution Auth Bypass Data Leakage Framework Inference Training Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 4 ATLAS
HIGH

Feast: authz bypass in /materialize triggers DoS

CVE-2026-18947
8.5
EPSS 0.4%
Auth Bypass DoS Training Data API
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 3 ATLAS
MEDIUM

Feast operator: code injection escalates to cluster admin

CVE-2026-18942
5.5
EPSS 0.3%
Code Execution Supply Chain Data Leakage Framework Training Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 3 ATLAS
HIGH

Feast: no-auth default enables RCE via malicious UDF

CVE-2026-18941
7.7
EPSS 0.6%
Auth Bypass Code Execution DoS Framework API Training Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 4 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