AI Threat AlertAI 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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1908 results — High severityCVE-2026-55839Kestra: stored XSS via crafted [[link]] flow description8.70.4%io.kestra:kestraAug 18HIGHECVE-2026-69148MLflow: missing authz check leaks private artifacts7.10.4%mlflowAug 17HIGHGHSA-j659-8xh6-5pq5atomic-agents: unpriced models silently bypass cost cap——atomic-agents-stackAug 17HIGHECVE-2026-75111Evidently: unauth path traversal leaks any file7.50.6%—Aug 17HIGHECVE-2026-35219Budibase: SSRF in automations reaches cloud metadata—0.5%—Aug 17HIGHCVE-2026-75060PyCharm: unauthenticated Jupyter MCP tools enable RCE8.40.2%—Aug 17HIGHECVE-2026-74868SiYuan: unthrottled brute-force exposes published notes7.50.5%—Aug 17HIGHECVE-2026-19960Edimax EW-7478APC: command injection via rootAPmac7.42.0%—Aug 16HIGHECVE-2026-73045SiYuan: brute-force bypass of notebook publish passwords7.50.5%—Aug 15HIGHCVE-2026-73626JupyterLab: missing await bypasses extension allowlist0.00.4%jupyterlabAug 13HIGHECVE-2026-73608SiYuan: missing authz exposes filtered DB rows8.60.3%—Aug 13HIGHECVE-2026-72807SiYuan: second-order SQLi via malicious template packages8.00.3%github.com/siyuan-note/siyuan/kernelAug 12HIGHECVE-2026-72801SiYuan: key material leak enables offline cracking7.50.3%github.com/siyuan-note/siyuan/kernelAug 12HIGHECVE-2026-72789SiYuan: broken access control leaks encrypted notes8.60.4%github.com/siyuan-note/siyuan/kernelAug 12HIGHECVE-2026-72793SiYuan: getConf leaks session key, enables admin takeover8.60.3%github.com/siyuan-note/siyuan/kernelAug 12HIGHCVE-2026-73325OneCompression: RCE via malicious .pt checkpoint load7.80.4%—Aug 12HIGHCVE-2026-19594snowflake.core: injection enables privilege escalation8.10.5%—Aug 12HIGHCVE-2026-64954Velociraptor: VQL auth-reset lets analyst gain investigator role8.20.3%—Aug 12HIGHCVE-2026-6484InsydeH2O UEFI: unverified boot allows local code execution8.20.4%InsydeH2OAug 12HIGHECVE-2026-73222Claude Code Templates: unauth RCE via shell injection8.80.3%claude-code-templatesAug 11Frequently 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