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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1431 results — has patch
SeverityCVE IDSummaryCVSSEPSSPackageDate
LOWECVE-2026-59215Open WebUI: IDOR leaks private channel/DM threads3.10.3%open-webuiJul 9LOWECVE-2026-59213Open WebUI: cache leak exposes cross-user model lists3.50.4%open-webuiJul 9MEDIECVE-2026-59217Open WebUI: read-only users can inject files into RAG KBs4.30.4%open-webuiJul 9HIGHECVE-2026-59216Open WebUI: session hijack enables cross-user code exec7.70.5%open-webuiJul 9HIGHECVE-2026-59219Open WebUI: revoked JWTs bypass WebSocket auth7.10.6%open-webuiJul 9MEDICVE-2026-59208n8n: multi-issuer JWT sub collision bypasses auth6.80.3%n8nJul 9MEDICVE-2026-59207n8n: MCP tool bypasses credential domain allowlist6.50.4%n8nJul 9HIGHCVE-2026-59206n8n: prototype pollution lets guests hit admin APIs7.10.7%n8nJul 9LOWECVE-2026-59715Open WebUI: unauth Socket.IO bypass alters doc state3.10.4%open-webuiJul 9MEDIECVE-2026-59220Open WebUI: ReDoS in skill mentions blocks event loop6.50.6%open-webuiJul 9LOWCVE-2026-59226Open WebUI: deactivated users retain automation access3.10.5%open-webuiJul 9MEDIECVE-2026-59227Open WebUI: image-edit API bypasses admin permission gate4.30.4%open-webuiJul 9MEDICVE-2026-59218Open WebUI: timing leak enables account enumeration5.30.4%open-webuiJul 9HIGHCVE-2026-59214Open WebUI: Pyodide sandbox bypass reaches admin RCE7.30.4%open-webuiJul 9HIGHECVE-2026-59723Cline: missing Origin check on Hub enables RCE8.80.2%clineJul 8HIGHECVE-2026-49471Serena: unauth dashboard API enables RCE via memory poisoning8.30.4%serena-agentJul 8HIGHCVE-2026-59822LiteLLM: MCP auth bypass via fabricated OAuth header8.20.8%litellmJul 8HIGHCVE-2026-59821LiteLLM: code exec via unsandboxed Custom Guardrails7.20.9%litellmJul 8MEDICVE-2026-59820LiteLLM: Zip Slip in Skills upload allows file write6.50.6%litellmJul 8MEDICVE-2026-59819LiteLLM: admin-scope local file read via OIDC ref4.90.6%litellmJul 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