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
HIGH

n8n: stored XSS in Form node completion page

CVE-2026-77072
--
EPSS 0.2%
Code Execution Privacy Violation Agent Plugin
n8n CWE-79 2 ATLAS
HIGH

n8n: Supabase filter injection leaks/wipes full tables

CVE-2026-77071
--
EPSS 0.3%
Data Extraction Data Leakage Auth Bypass Agent Plugin RAG
n8n CWE-89 4 ATLAS
HIGH

n8n: NoSQL injection in MongoDB node wipes/exfils data

CVE-2026-77070
--
EPSS 0.3%
Data Leakage Auth Bypass Agent Plugin
n8n CWE-943 3 ATLAS
LOW

n8n: SSRF bypass in OAuth2 token exchange

CVE-2026-77069
--
EPSS 0.2%
Auth Bypass Data Leakage Agent API
n8n CWE-918 1 ATLAS
HIGH

n8n: RCE via path traversal in MCP schema loader

CVE-2026-77068
--
EPSS 0.6%
Code Execution Agent Plugin
n8n CWE-22 3 ATLAS
CRITICAL EXPLOIT AVAIL

LMDeploy: RCE via unauth pickle deserialization

CVE-2026-76850
9.8
EPSS 1.0%
Code Execution Auth Bypass Inference API
lmdeploy CWE-502 1 3 ATLAS
HIGH

Splunk SPL2: broken authZ lets low-priv user wipe modules

CVE-2026-76336
7.1
EPSS 0.2%
Auth Bypass DoS Training Data
CWE-862 2 ATLAS
MEDIUM

Splunk Table Editor: stored SPL escalates power→admin

CVE-2026-76341
5.4
EPSS 0.2%
Auth Bypass Code Execution Social Engineering Training Data
2 ATLAS
HIGH

Splunk Enterprise: SPL injection via Dataset Explorer

CVE-2026-76254
7.5
EPSS 0.3%
Code Execution Social Engineering Data Extraction Training Data
2 ATLAS
HIGH

marimo: code injection via malicious MCP server config

CVE-2026-75149
8.8
EPSS 0.6%
Code Execution Supply Chain Agent Plugin
CWE-94 4 ATLAS
HIGH

Langflow: missing auth allows admin takeover

CVE-2026-19875
7.5
EPSS 0.4%
Auth Bypass Code Execution Framework Agent
Langflow OSS CWE-306 2 ATLAS
UNKNOWN EXPLOIT AVAIL

Grav API Plugin: authz bypass enables privilege escalation

CVE-2026-64852
--
EPSS 0.4%
Auth Bypass Privacy Violation Plugin API
CWE-862
MEDIUM

InsydeH2O: UEFI variable flaw exposes HDD password

CVE-2026-8810
6.9
EPSS 0.1%
Data Extraction Auth Bypass Inference
InsydeH2O, InsydeH2O ARM 27 1 ATLAS
LOW

FreeBSD ZFS: unprivileged user can spoof recv metadata flag

CVE-2026-49431
3.3
EPSS 0.1%
Auth Bypass Training Data
MEDIUM

PeopleSoft: Panel Processor flaw enables unauthorized data access

CVE-2026-60884
4.4
EPSS 0.2%
Auth Bypass Data Leakage Framework
UNKNOWN

Blueprint Studio: broken authz grants full HA control

CVE-2026-53453
--
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation Plugin Agent API
CWE-862 1 ATLAS
UNKNOWN

n8n: Git node symlink race leads to RCE

CVE-2026-71539
--
EPSS 0.2%
Code Execution Supply Chain Agent Plugin
n8n CWE-367 4 ATLAS
MEDIUM EXPLOIT AVAIL

tract: malformed ONNX model triggers buffer flaw

CVE-2026-75093
4.3
EPSS 0.3%
Supply Chain DoS Model Inference
CWE-120 3 ATLAS
HIGH

Evidently: unauth path traversal leaks any file

CVE-2026-75111
7.5
EPSS 0.4%
Data Leakage Privacy Violation Training Data Framework
CWE-22 3 ATLAS
MEDIUM EXPLOIT AVAIL

Transformers: path traversal via checkpoint shards

CVE-2026-75104
5.5
EPSS 0.2%
Data Leakage Supply Chain Framework Model
transformers CWE-22 9.5K 3 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