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 4307 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHCVE-2026-86083n8n: code injection via legacy expression engine—0.7%n8nSep 8HIGHCVE-2026-86082n8n: OpenAI node leaks API key via SSRF bypass—0.4%n8nSep 8HIGHCVE-2026-86081n8n: ReDoS via Git node clone freezes instance—0.6%n8nSep 8MEDICVE-2026-86080n8n: GitHub webhook signature bypass on 422 retry—0.3%n8nSep 8MEDICVE-2026-86079n8n: path traversal in Elasticsearch node leaks data—0.5%n8nSep 8MEDICVE-2026-86078n8n: prototype pollution in AI workflow summary—0.6%n8nSep 8MEDICVE-2026-86077n8n: chat token replay bypasses HITL approval gates—0.4%n8nSep 8HIGHCVE-2026-86076n8n: expression sandbox escape enables RCE—0.8%n8nSep 8HIGHCVE-2026-86075n8n: unauth OAuth DCR fields exhaust DB storage—0.6%n8nSep 8UNKNCVE-2026-86996n8n: Agent tool bypasses workflow caller restriction—0.3%n8nSep 8HIGHECVE-2026-84452winml-cli: RCE via wildcard CORS + trust-remote-code—1.6%winml-cliSep 8HIGHGHSA-j95f-988m-3j2ftiptap: ReDoS in Markdown attribute parsers——@tiptap/coreSep 8MEDICVE-2026-85981Auth0 AD/LDAP Connector: unauth local panel leaks AD creds6.70.2%—Sep 8HIGHECVE-2026-80206NLTK tgrep ReDoS: single request hangs Python process—0.4%nltkSep 8UNKNECVE-2026-79721MLflow: malicious model artifact enables RCE on load—0.5%mlflowSep 8MEDIGHSA-57v5-wqx3-cgj4SiYuan: missing authz leaks database view structure5.8—github.com/siyuan-note/siyuan/kernelSep 8MEDICVE-2026-86074n8n: SSRF in AI credential setup leaks tokens—0.4%n8nSep 8MEDICVE-2026-86073n8n: OAuth refresh token skips workflow-resource binding—0.4%n8nSep 8CRITECVE-2026-79657NLTK: pickle allowlist bypass enables RCE9.81.3%nltkSep 8HIGHECVE-2026-78682NLTK: SSRF bypass via proxy-handler downgrade7.50.4%nltkSep 8

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