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 1961 results — Active exploitation
SeverityCVE IDSummaryCVSSEPSSPackageDate
LOWECVE-2026-14189WPBot: admin-set field IDs enable stored SQLi3.80.3%wpbotJul 27MEDIECVE-2026-17458openclaw-cn: unpatched SSRF in browser agent click API6.30.4%—Jul 26MEDIECVE-2026-17457openclaw-cn: scheme handler bypass exposes data4.30.4%—Jul 26HIGHECVE-2026-59714Open WebUI: broken authz lets users overwrite channel chats7.10.5%open-webuiJul 24LOWECVE-2026-63632onnx: OOB heap read in Gemm opset-downgrade adapter3.30.2%onnxJul 24MEDIECVE-2026-66007datasets: path traversal via file_name leaks local files6.50.5%datasetsJul 24MEDIECVE-2026-66005Jan: CORS misconfig exposes local LLM API to network6.30.3%—Jul 24MEDIECVE-2026-66004BlenderMCP: path traversal enables arbitrary file write5.30.3%—Jul 24MEDIECVE-2026-7007Zephyr RTOS: ext2 mount DoS via crafted superblock4.60.2%—Jul 24MEDIECVE-2026-65010Datasets: symlink following enables arbitrary file write6.60.2%datasetsJul 23MEDIECVE-2026-65920Diffusers: path traversal via weight_map exposes files4.30.4%diffusersJul 23CRITECVE-2026-65700h2oGPT: unauth path traversal in files API leads to RCE9.81.5%h2ogptJul 23HIGHECVE-2026-65917CyberPanel: IDOR exposes cross-tenant backups8.80.5%—Jul 23MEDIECVE-2026-65012InvokeAI: unauthenticated directory enumeration flaw5.30.4%invokeaiJul 22HIGHECVE-2026-65315Ollama: crafted GGUF file crashes inference server7.50.8%ollamaJul 21MEDIECVE-2026-60152PeopleSoft: unauthorized data access via Panel Processor5.40.2%—Jul 21MEDIECVE-2026-47024PeopleSoft PeopleTools: CSRF-style data tampering flaw5.40.2%—Jul 21HIGHECVE-2026-27775Gitea: cached permission check allows repo takeover8.80.9%code.gitea.io/giteaJul 21HIGHECVE-2026-63764lmdeploy: SSRF via redirect bypasses private IP guard8.60.5%lmdeployJul 21HIGHECVE-2026-47237Kubeflow: token theft lets any user hijack accounts8.00.4%—Jul 21

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