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 1527 results — Medium severity
MEDIUM

Kubeflow Pipelines: missing authz exposes tenant artifacts

CVE-2026-118760
6.5
EPSS 0.4%
Auth BypassData LeakageData ExtractionFrameworkTraining DataModel
CWE-6394 ATLAS
MEDIUM

Langflow: unbounded resource allocation enables DoS

CVE-2026-90991
6.5
EPSS 0.4%
DoSFrameworkAPI
langflowCWE-7703 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file overwrite

CVE-2026-77819
6.5
EPSS 0.4%
Code ExecutionFrameworkAgent
langflowCWE-222 ATLAS
MEDIUM

Langflow: secrets exposed in flow/project exports

CVE-2026-77817
6.5
EPSS 0.3%
Data LeakageData ExtractionFrameworkAgent
langflowCWE-2003 ATLAS
MEDIUM

Langflow: path traversal exposes sensitive files

CVE-2026-110244
6.5
EPSS 0.6%
Data ExtractionData LeakageFrameworkRAG
langflowCWE-223 ATLAS
MEDIUM

Langflow: cleartext credential storage exposes secrets

CVE-2026-110200
6.5
EPSS 0.2%
Data LeakageData ExtractionFrameworkAgent
langflowCWE-3123 ATLAS
MEDIUM

Langflow: weak credential protection exposes secrets

CVE-2026-110192
6.5
EPSS 0.2%
Data LeakageData ExtractionFrameworkAPI
langflowCWE-5223 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file read

CVE-2026-110190
6.5
EPSS 0.4%
Data LeakageData ExtractionFramework
langflowCWE-224 ATLAS
MEDIUM

Langflow: SSRF allows authenticated internal requests

CVE-2026-104331
5.4
EPSS 0.2%
Data LeakageAuth BypassFrameworkAgent
langflowCWE-9182 ATLAS
MEDIUM

Langflow: missing authz lets users cancel others' jobs

CVE-2026-104316
6.5
EPSS 0.3%
Auth BypassDoSFrameworkAgent
langflowCWE-2852 ATLAS
MEDIUM

Langflow: SSRF allows authenticated internal network probing

CVE-2026-104315
4.3
EPSS 0.2%
Data LeakageData ExtractionFrameworkAPI
langflowCWE-9183 ATLAS
MEDIUM

Langflow: flow share grant leaks owner's cleartext credentials

CVE-2026-104314
6.5
EPSS 0.3%
Data LeakageData ExtractionFrameworkAPI
langflowCWE-5223 ATLAS
MEDIUM

Langflow: ZIP path traversal enables file write on victim

CVE-2026-104312
6.8
EPSS 0.2%
Supply ChainFramework
langflowCWE-222 ATLAS
MEDIUM

Langflow: SSRF allows authenticated info disclosure

CVE-2026-104310
4.3
EPSS 0.3%
Data ExtractionData LeakageFrameworkAPI
langflowCWE-9183 ATLAS
MEDIUM

Langflow: path traversal exposes sensitive files

CVE-2026-104309
6.5
EPSS 0.6%
Data LeakageData ExtractionFrameworkRAG
langflowCWE-223 ATLAS
MEDIUM

Langflow: OS command injection allows authenticated DoS

CVE-2026-104308
4.3
EPSS 0.3%
DoSCode ExecutionFrameworkAgent
langflowCWE-783 ATLAS
MEDIUM

AVideo Encoder: stored XSS via queue title hits admins

CVE-2026-61575
4.7
EPSS 0.2%
Data LeakageAuth BypassFramework
CWE-792 ATLAS
MEDIUM

LangGraph SDK: path traversal in v3 stream helpers

CVE-2026-118667
4.3
EPSS 0.4%
Data LeakageAuth BypassFrameworkAgentAPI
langgraphPatch: 1.2.14CWE-224.1K2 ATLAS
MEDIUM

filelock: lax claim dir perms let local users break strict lock

CVE-2026-112908
5.3
DoSSupply ChainFramework
filelockPatch: 4.2.1CWE-7326.3K2 ATLAS
MEDIUMEXPLOIT AVAIL

filelock: unverified lock-dir ownership breaks mutual exclusion

CVE-2026-112911
6.3
EPSS 0.1%
Auth BypassDoSSupply ChainFramework
filelockPatch: 4.2.1CWE-2836.3K2 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