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 2876 results — no patch
SeverityCVE IDSummaryCVSSEPSSPackageDate
MEDICVE-2026-85492AIOSEO WordPress: DOM XSS via URL path in SEO Preview6.10.2%—Oct 2HIGHECVE-2026-51888Langflow: absolute path traversal allows arbitrary file write7.50.6%langflowOct 1CRITECVE-2026-51884Langchain-Chatchat: path traversal enables arbitrary file write9.80.6%—Oct 1CRITECVE-2026-51883Langchain-Chatchat: path traversal allows arbitrary file write9.10.4%—Oct 1CRITECVE-2026-51882Langchain-Chatchat: path traversal in /v1/files file write9.10.5%—Oct 1HIGHCVE-2026-86344389-ds-base: LDAP worker pool exhaustion DoS7.50.3%—Oct 1MEDICVE-2026-104181Filament: MFA setup lacks password confirmation5.40.3%—Oct 1HIGHCVE-2026-103484pgvector: IVFFlat build OOB write enables code execution8.80.4%pgvectorOct 1HIGHECVE-2026-55232Vvveb CMS: IPv6 SSRF guard bypass leaks cloud credentials7.60.4%—Oct 1HIGHECVE-2026-55231Vvveb CMS: path traversal enables file read/delete7.20.5%—Oct 1HIGHECVE-2026-73975djehuty: SPARQL injection allows RDF store tampering—0.4%—Oct 1MEDICVE-2026-103260n8n: approval bypass in Send and Wait chat mode4.00.3%n8nOct 1HIGHCVE-2026-103259n8n: session token leak via Dynamic Credentials7.60.2%n8nOct 1MEDICVE-2026-103258n8n: unescaped parameter interpolation exposes bulk data6.80.3%n8nOct 1HIGHCVE-2026-103257n8n: path traversal in n8n node exposes credentials7.70.4%n8nOct 1HIGHCVE-2026-103256n8n: Wekan/Baserow credential leak to arbitrary hosts7.10.2%n8nOct 1CRITCVE-2026-103255n8n: Supabase node path traversal exposes admin APIs9.00.3%n8nOct 1MEDICVE-2026-103254n8n: path traversal enables cross-project approval forgery6.30.3%n8nOct 1HIGHCVE-2026-103253n8n: SQL injection in Oracle node Drop Table operation8.70.2%n8nOct 1HIGHCVE-2026-103252n8n: authz bypass in credential test leaks variables7.70.3%n8nOct 1

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