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

InsydeH2O UEFI: HDD password stored in plaintext

CVE-2021-38489
8.2
EPSS 0.2%
Data LeakagePrivacy ViolationInference
InsydeH2O27
HIGH

RPM: command injection via tarball name in rpmbuild

CVE-2026-84837
7.8
Code ExecutionSupply ChainFrameworkTraining Data
rhoai/odh-mlflow-operator-rhel96953 ATLAS
HIGH

Siyuan: SQLi bypasses publish visibility control

CVE-2026-59834
7.5
EPSS 0.5%
Auth BypassData LeakageRAG
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260704035518-d0f0fe146fb0CWE-893.0K2 ATLAS
HIGHEXPLOIT AVAIL

Craft CMS: auth bypass enables admin takeover

CVE-2026-84801
8.8
EPSS 0.4%
Auth BypassFramework
HIGH

SageMaker: HMAC leak allows forged pipeline code execution

CVE-2026-83551
7.2
EPSS 0.8%
Code ExecutionAuth BypassData LeakageAPIFramework
sagemaker504 ATLAS
HIGHEXPLOIT AVAIL

Codex CLI: git core.fsmonitor hook enables RCE

CVE-2026-19592
7.3
EPSS 0.2%
Code ExecutionSupply ChainAgent
Codex CLI1.8K3 ATLAS
HIGH

Codex CLI: PowerShell parsing flaw bypasses approval, RCE

CVE-2026-19591
8.8
EPSS 0.6%
Prompt InjectionAuth BypassCode ExecutionAgentPlugin
Codex CLI1.8K5 ATLAS
HIGH

Codex Desktop: Git hook trust flaw enables RCE

CVE-2026-19590
7.3
EPSS 0.2%
Code ExecutionSupply ChainAgent
Codex Desktop1.8K4 ATLAS
HIGH

MLflow: statsmodels flavor bypasses pickle RCE guard

GHSA-gqvg-gmmx-x4hm
8.8
Code ExecutionSupply ChainModelFramework
mlflowPatch: 3.15.0CWE-5026954 ATLAS
HIGHEXPLOIT AVAIL

Transformers: remote file write bypasses trust prompt

CVE-2026-80047
7.8
EPSS 0.1%
Supply ChainCode ExecutionAuth BypassFrameworkModel
transformersCWE-2739.8K3 ATLAS
HIGH

Kirby CMS: auth bypass enables chunk-upload DoS

CVE-2026-71415
--
EPSS 0.4%
DoSAuth BypassAPI
getkirby/cmsPatch: 5.5.2CWE-862514
HIGH

Ankara Site Panel: SQLi enables full DB compromise

CVE-2026-5956
8.8
EPSS 0.4%
Data ExtractionData LeakageFramework
CWE-89
HIGHEXPLOIT AVAIL

SiYuan: stored XSS via malicious bazaar package names

CVE-2026-82653
8.9
EPSS 0.4%
Supply ChainCode ExecutionPlugin
CWE-792 ATLAS
HIGHEXPLOIT AVAIL

NextChat: proxy URL check bypass leaks OpenAI key

CVE-2026-82639
7.5
EPSS 0.5%
Data LeakageAuth BypassAPIFramework
CWE-203 ATLAS
HIGH

Readest: iframe srcdoc XSS bypass leads to RCE

CVE-2026-82642
8.8
EPSS 0.7%
Code ExecutionData LeakageFramework
2 ATLAS
HIGH

Langflow: namespace collision leaks data, injects messages

CVE-2026-18904
8.2
EPSS 0.4%
Auth BypassData LeakagePrompt InjectionAgentFramework
langflowCWE-6393 ATLAS
HIGH

Langflow: path traversal enables arbitrary file read

CVE-2026-18899
7.5
EPSS 0.7%
Data LeakageFrameworkAgent
langflowCWE-223 ATLAS
HIGH

Langflow: broken auth allows unauthorized flow execution

CVE-2026-18891
8.2
EPSS 0.5%
Auth BypassCode ExecutionData LeakageFrameworkAgentAPI
langflowCWE-2874 ATLAS
HIGHEXPLOIT AVAIL

Langflow: authenticated RCE via unsafe code generation

CVE-2026-18729
8.8
EPSS 1.6%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-943 ATLAS
HIGHEXPLOIT AVAIL

SD WebUI: cmd-flags endpoint leaks creds cleartext

CVE-2026-82288
7.5
EPSS 0.4%
Data LeakageAuth BypassAPIInference
CWE-5224 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