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 1908 results — High severity
HIGH

n8n: RCE via deprecated nodes bypassing task runner

CVE-2026-119408
8.8
EPSS 0.6%
Code ExecutionAuth BypassAgentFrameworkPlugin
n8nCWE-653164 ATLAS
HIGH

Langflow: code injection allows authenticated RCE

CVE-2026-110309
8.8
EPSS 0.6%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: improper authentication exposes sensitive data

CVE-2026-110245
7.5
EPSS 0.4%
Auth BypassData LeakageFrameworkAPI
langflowCWE-2873 ATLAS
HIGH

Langflow: authz bypass enables RCE via code component

CVE-2026-110196
8.8
EPSS 0.5%
Auth BypassCode ExecutionFrameworkAgent
langflowCWE-8623 ATLAS
HIGH

Langflow: code injection in Agentic Assistant allows RCE

CVE-2026-110193
8.8
EPSS 0.8%
Code ExecutionPrompt InjectionFrameworkAgent
langflowCWE-945 ATLAS
HIGH

Langflow: code injection allows authenticated RCE

CVE-2026-107329
8.8
EPSS 0.9%
Code ExecutionFrameworkAgent
langflowCWE-944 ATLAS
HIGH

Langflow: code injection via eval/exec allows authenticated RCE

CVE-2026-107328
8.8
EPSS 0.9%
Code ExecutionFrameworkAgent
langflowCWE-944 ATLAS
HIGH

Langflow: missing authorization allows authenticated RCE

CVE-2026-107327
8.8
EPSS 0.7%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-8624 ATLAS
HIGH

Langflow: OS command injection allows authenticated RCE

CVE-2026-107326
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-783 ATLAS
HIGH

Langflow OSS: OS command injection allows authenticated RCE

CVE-2026-104328
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: unsafe deserialization allows authenticated RCE

CVE-2026-104324
8.8
EPSS 0.7%
Code ExecutionSupply ChainFrameworkAgent
langflowCWE-5024 ATLAS
HIGH

Langflow: SQL injection via broken access control

CVE-2026-103092
8.8
EPSS 0.4%
Auth BypassData ExtractionFrameworkAgent
langflowCWE-2843 ATLAS
HIGH

Langflow: SSRF allows authenticated info disclosure

CVE-2026-102590
7.7
EPSS 0.3%
Data ExtractionData LeakageFrameworkAPI
langflowCWE-9182 ATLAS
HIGH

Langflow: code injection allows authenticated RCE

CVE-2026-101288
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Mapster WP Maps: unauth REST route enables stored XSS

CVE-2026-107743
7.2
EPSS 0.4%
Auth BypassSocial EngineeringPlugin
2 ATLAS
HIGH

LangGraph API: Store namespace rewrite bypass in JS auth

CVE-2026-118668
--
EPSS 0.4%
Auth BypassData LeakageFrameworkAgentAPI
langgraphCWE-6394.1K4 ATLAS
HIGH

MONAI: RCE via malicious bundle logging.conf

CVE-2026-118683
8.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkModel
monaiCWE-941284 ATLAS
HIGH

n8n: SSRF in Slack Trigger leaks Slack workspace tokens

CVE-2026-118679
7.5
EPSS 0.3%
Data LeakageAuth BypassAgentPluginFramework
n8nCWE-918164 ATLAS
HIGH

n8n: prototype pollution via workflow keys causes DoS

CVE-2026-118678
7.1
EPSS 0.3%
DoSFrameworkAgent
n8nCWE-1321162 ATLAS
HIGH

n8n: credential permission bypass leaks secrets

CVE-2026-118676
7.1
EPSS 0.2%
Auth BypassData LeakageData ExtractionAgentFrameworkPlugin
n8nCWE-863164 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