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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 366 results — Critical severity, no patch
CRITICALEXPLOIT AVAILSCANNER

Langflow: OS command injection allows remote RCE

CVE-2026-93674
9.8
EPSS 15.3%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-944 ATLAS
CRITICAL

Langflow: improper code generation control enables RCE

CVE-2026-104334
9.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langflow: MCP Stdio command injection gives authenticated RCE

CVE-2026-105740
9.9
EPSS 3.9%
Code ExecutionSupply ChainFrameworkAgentPlugin
langflowCWE-784 ATLAS
CRITICAL

Vibe-Trading: unauth agent RCE via shell tools, exec

GHSA-jqmf-mx4f-hfr6
10.0
Code ExecutionPrompt InjectionAuth BypassAgentAPIPlugin
CWE-779 ATLAS
CRITICAL

SageMaker Distribution: OS command injection exposes IAM creds

CVE-2026-104019
9.0
EPSS 1.4%
Code ExecutionData LeakageAuth BypassFrameworkTraining Data
sagemaker505 ATLAS
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal enables arbitrary file write

CVE-2026-51884
9.8
EPSS 0.6%
Code ExecutionData LeakageFrameworkRAGAPI
3 ATLAS
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal allows arbitrary file write

CVE-2026-51883
9.1
EPSS 0.4%
Code ExecutionSupply ChainFrameworkRAG
2 ATLAS
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal in /v1/files file write

CVE-2026-51882
9.1
EPSS 0.5%
Code ExecutionAuth BypassAPIFrameworkRAG
3 ATLAS
CRITICAL

n8n: Supabase node path traversal exposes admin APIs

CVE-2026-103255
9.0
EPSS 0.3%
Auth BypassData LeakageAgentPluginFramework
n8nCWE-73164 ATLAS
CRITICAL

n8n: Supabase node filter injection exposes tables

CVE-2026-103248
9.0
EPSS 0.3%
Data ExtractionData LeakageAuth BypassAgentPluginRAG
n8nCWE-89164 ATLAS
CRITICALEXPLOIT AVAIL

aaPanel BaoTa: command injection in file merge handler

CVE-2026-101008
9.1
EPSS 2.3%
Code ExecutionFramework
2 ATLAS
CRITICAL

GitHub Enterprise Server: SSRF to RCE in notebook viewer

CVE-2026-77987
9.8
EPSS 0.9%
Code ExecutionData ExtractionAuth BypassFramework
3 ATLAS
CRITICALEXPLOIT AVAIL

MCP Atlassian: missing auth exposes Jira/Confluence

CVE-2026-77254
9.1
EPSS 0.6%
Auth BypassData LeakageAgentPluginAPI
mcp-atlassian25 ATLAS
CRITICALKEV

F5 BIG-IP APM: unauthenticated RCE via OAuth server

CVE-2026-94127
9.8
EPSS 26.6%
Code ExecutionAuth BypassAPIFramework
CWE-1222 ATLAS
CRITICALEXPLOIT AVAIL

Joplin Server: SSO code brute force yields session takeover

CVE-2026-46649
--
EPSS 0.5%
Auth BypassData LeakageAPI
CWE-3073 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: hardcoded JWT secret enables auth bypass

CVE-2026-57148
9.8
EPSS 0.6%
Auth BypassFrameworkAgentAPI
praisonaiCWE-28713 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: hardcoded JWT secret allows auth bypass

CVE-2026-57147
9.8
EPSS 0.8%
Auth BypassAgentAPIFramework
praisonaiCWE-79813 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: codeMode sandbox escape allows unauthenticated RCE

CVE-2026-57141
9.8
EPSS 0.7%
Code ExecutionPrompt InjectionAgentFrameworkPlugin
praisonaiCWE-9416 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated AgentOS API exposes agents

CVE-2026-57140
9.4
EPSS 0.6%
Auth BypassData LeakageAgentAPIFramework
praisonaiCWE-30615 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated MCP server exposes agent tools

CVE-2026-57139
9.8
EPSS 0.8%
Auth BypassData ExtractionCode ExecutionAgentPluginFramework
praisonaiCWE-30615 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