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 1908 results — High severity
HIGH

Langflow: authenticated code injection enables RCE

CVE-2026-17633
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: AST code scanner bypass enables auth'd RCE

CVE-2026-17632
8.8
EPSS 0.9%
Code ExecutionFrameworkAgentPlugin
langflowCWE-942 ATLAS
HIGH

Langflow: authenticated RCE via unsafe module imports

CVE-2026-17624
8.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-943 ATLAS
HIGH

Langflow: broken access control enables cache poisoning

CVE-2026-10547
8.1
EPSS 0.4%
Auth BypassDoSFrameworkAgent
langflowCWE-2843 ATLAS
HIGH

Langflow: SSRF in Ollama config hits internal hosts

CVE-2026-9081
7.1
EPSS 0.3%
Data LeakageFrameworkAgent
Langflow OSS3 ATLAS
HIGH

Langflow: RCE via authenticated OS command injection

CVE-2026-17625
7.2
EPSS 0.8%
Code ExecutionFrameworkAgent
Langflow OSS2 ATLAS
HIGH

Langflow: MCP config write bypasses localhost restriction

CVE-2026-9077
8.5
EPSS 0.4%
Auth BypassSupply ChainCode ExecutionAgentFrameworkPlugin
langflowCWE-8073 ATLAS
HIGH

Langflow: OAuth auth bypass on MCP composer endpoint

CVE-2026-8446
7.5
EPSS 0.5%
Auth BypassData LeakageFrameworkAgent
langflowCWE-3062 ATLAS
HIGH

Langflow: RCE via improper config parameter validation

CVE-2026-17630
8.8
EPSS 0.8%
Code ExecutionFrameworkAgent
langflowCWE-1843 ATLAS
HIGH

Langflow: Docker MCP volume-mount flaw exposes host files

CVE-2026-17626
8.8
EPSS 0.4%
Code ExecutionData LeakageFrameworkAgentPlugin
langflowCWE-2663 ATLAS
HIGH

Langflow: MCP config command injection allows RCE

CVE-2026-17623
8.8
EPSS 0.8%
Code ExecutionAuth BypassAgentFrameworkPlugin
langflowCWE-784 ATLAS
HIGHEXPLOIT AVAIL

Mistral Vibe: RCE via malicious git fsmonitor hook

CVE-2026-67623
8.8
EPSS 1.1%
Code ExecutionSupply ChainAgent
mistral-vibe4734 ATLAS
HIGH

peft: unsafe torch.load in LoRA-GA/CorDA allows RCE

CVE-2026-71281
8.8
EPSS 0.5%
Supply ChainCode ExecutionFrameworkTraining Data
peft7804 ATLAS
HIGH

MLflow AI Gateway: SSRF via unvalidated api_base

CVE-2026-71211
7.1
EPSS 0.3%
Data LeakageAuth BypassAPIFrameworkInference
mlflowCWE-9186953 ATLAS
HIGHSCANNER

AIWU WP Plugin: unauth leak of stored OpenAI keys

CVE-2026-6639
7.5
EPSS 2.0%
Data LeakageAuth BypassData ExtractionPluginAPI
CWE-8623 ATLAS
HIGH

Open WebUI: broken authz lets collaborator delete chats

CVE-2026-70494
8.1
EPSS 0.5%
Auth BypassDoSFramework
open-webuiPatch: 0.11.0CWE-86221 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: KaTeX fallback XSS steals admin session

CVE-2026-70492
8.7
EPSS 0.4%
Code ExecutionData LeakageAuth BypassFramework
open-webuiPatch: 0.11.0CWE-7923 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: iframe sandbox bypass = account takeover

CVE-2026-70486
8.2
EPSS 0.4%
Code ExecutionData LeakageAuth BypassAgentFramework
open-webuiPatch: 0.11.0CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: NAT64 IPv6 trick bypasses SSRF filter, leaks metadata

CVE-2026-70485
7.1
EPSS 0.4%
Data ExtractionPrivacy ViolationRAGAPI
open-webuiPatch: 0.11.0CWE-91823 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: OAuth token exchange enables takeover

CVE-2026-70482
8.1
EPSS 0.6%
Auth BypassPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.11.0CWE-28723 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