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
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHCVE-2021-38489InsydeH2O UEFI: HDD password stored in plaintext8.20.2%InsydeH2OSep 3HIGHCVE-2026-84837RPM: command injection via tarball name in rpmbuild7.8—rhoai/odh-mlflow-operator-rhel9Sep 2HIGHCVE-2026-59834Siyuan: SQLi bypasses publish visibility control7.50.5%github.com/siyuan-note/siyuan/kernelSep 2HIGHECVE-2026-84801Craft CMS: auth bypass enables admin takeover8.80.4%—Sep 2HIGHCVE-2026-83551SageMaker: HMAC leak allows forged pipeline code execution7.20.8%sagemakerSep 1HIGHECVE-2026-19592Codex CLI: git core.fsmonitor hook enables RCE7.30.2%Codex CLISep 1HIGHCVE-2026-19591Codex CLI: PowerShell parsing flaw bypasses approval, RCE8.80.6%Codex CLISep 1HIGHCVE-2026-19590Codex Desktop: Git hook trust flaw enables RCE7.30.2%Codex DesktopSep 1HIGHGHSA-gqvg-gmmx-x4hmMLflow: statsmodels flavor bypasses pickle RCE guard8.8—mlflowSep 1HIGHECVE-2026-80047Transformers: remote file write bypasses trust prompt7.80.1%transformersSep 1HIGHCVE-2026-71415Kirby CMS: auth bypass enables chunk-upload DoS—0.4%getkirby/cmsAug 31HIGHCVE-2026-5956Ankara Site Panel: SQLi enables full DB compromise8.80.4%—Aug 31HIGHECVE-2026-82653SiYuan: stored XSS via malicious bazaar package names8.90.4%—Aug 30HIGHECVE-2026-82639NextChat: proxy URL check bypass leaks OpenAI key7.50.5%—Aug 30HIGHCVE-2026-82642Readest: iframe srcdoc XSS bypass leads to RCE8.80.7%—Aug 30HIGHCVE-2026-18904Langflow: namespace collision leaks data, injects messages8.20.4%langflowAug 28HIGHCVE-2026-18899Langflow: path traversal enables arbitrary file read7.50.7%langflowAug 28HIGHCVE-2026-18891Langflow: broken auth allows unauthorized flow execution8.20.5%langflowAug 28HIGHECVE-2026-18729Langflow: authenticated RCE via unsafe code generation8.81.6%langflowAug 28HIGHECVE-2026-82288SD WebUI: cmd-flags endpoint leaks creds cleartext7.50.4%—Aug 28

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