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

Kestra: stored XSS via crafted [[link]] flow description

CVE-2026-55839
8.7
EPSS 0.4%
Code ExecutionData LeakageFramework
io.kestra:kestraPatch: 1.3.24CWE-795142 ATLAS
HIGHEXPLOIT AVAIL

MLflow: missing authz check leaks private artifacts

CVE-2026-69148
7.1
EPSS 0.4%
Auth BypassData LeakageModelAPI
mlflowPatch: 3.15.0CWE-8626953 ATLAS
HIGH

atomic-agents: unpriced models silently bypass cost cap

GHSA-j659-8xh6-5pq5
--
DoSAgentFramework
atomic-agents-stackPatch: 1.1.0CWE-770942 ATLAS
HIGHEXPLOIT AVAIL

Evidently: unauth path traversal leaks any file

CVE-2026-75111
7.5
EPSS 0.6%
Data LeakagePrivacy ViolationTraining DataFramework
CWE-223 ATLAS
HIGHEXPLOIT AVAIL

Budibase: SSRF in automations reaches cloud metadata

CVE-2026-35219
--
EPSS 0.5%
Data ExtractionAuth BypassAgentPlugin
3 ATLAS
HIGH

PyCharm: unauthenticated Jupyter MCP tools enable RCE

CVE-2026-75060
8.4
EPSS 0.2%
Code ExecutionAuth BypassAgentPlugin
CWE-3063 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: unthrottled brute-force exposes published notes

CVE-2026-74868
7.5
EPSS 0.5%
Auth BypassData LeakageRAG
2 ATLAS
HIGHEXPLOIT AVAIL

Edimax EW-7478APC: command injection via rootAPmac

CVE-2026-19960
7.4
EPSS 2.0%
Code ExecutionAPI
HIGHEXPLOIT AVAIL

SiYuan: brute-force bypass of notebook publish passwords

CVE-2026-73045
7.5
EPSS 0.5%
Auth BypassPlugin
CWE-3072 ATLAS
HIGH

JupyterLab: missing await bypasses extension allowlist

CVE-2026-73626
0.0
EPSS 0.4%
Supply ChainAuth BypassCode ExecutionPluginFramework
jupyterlab1.9K3 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: missing authz exposes filtered DB rows

CVE-2026-73608
8.6
EPSS 0.3%
Auth BypassData LeakageAPIRAG
2 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: second-order SQLi via malicious template packages

CVE-2026-72807
8.0
EPSS 0.3%
Supply ChainData LeakageCode ExecutionRAGPlugin
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260723035036-0a176345e02aCWE-893.0K3 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: key material leak enables offline cracking

CVE-2026-72801
7.5
EPSS 0.3%
Data LeakageAuth BypassRAGAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260724102025-3bc014c7dc32CWE-5223.0K1 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: broken access control leaks encrypted notes

CVE-2026-72789
8.6
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260726020813-a25c2dd06aaeCWE-8623.0K2 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: getConf leaks session key, enables admin takeover

CVE-2026-72793
8.6
EPSS 0.3%
Auth BypassData LeakageRAGPlugin
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260725132049-2d8b98395a91CWE-5223.0K2 ATLAS
HIGH

OneCompression: RCE via malicious .pt checkpoint load

CVE-2026-73325
7.8
EPSS 0.4%
Code ExecutionSupply ChainModelFramework
CWE-5024 ATLAS
HIGH

snowflake.core: injection enables privilege escalation

CVE-2026-19594
8.1
EPSS 0.5%
Auth BypassAPIFramework
HIGH

Velociraptor: VQL auth-reset lets analyst gain investigator role

CVE-2026-64954
8.2
EPSS 0.3%
Auth BypassAgent
HIGH

InsydeH2O UEFI: unverified boot allows local code execution

CVE-2026-6484
8.2
EPSS 0.4%
Code ExecutionSupply ChainInference
InsydeH2O27
HIGHEXPLOIT AVAIL

Claude Code Templates: unauth RCE via shell injection

CVE-2026-73222
8.8
EPSS 0.3%
Code ExecutionAuth BypassSocial EngineeringAgentFramework
claude-code-templatesPatch: 1.29.4CWE-784 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