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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1661 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2026-72794 SiYuan: CookieKey leak enables session forgery 8.6 0.2% github.com/siyuan-note/siyuan/kernel Sep 4 HIGH E CVE-2026-75911 CodeWhale: repo config silently enables shell RCE 7.8 0.3% codewhale Sep 4 HIGH E CVE-2026-75912 DeepSeek-TUI: git_blame argument injection leaks files 7.4 0.4% codewhale Sep 4 HIGH E CVE-2026-75856 deepseek-tui: SSRF via DNS-pinning TOCTOU bypass 8.6 0.5% codewhale Sep 4 HIGH E CVE-2026-75915 deepseek-tui: js_execution leaks parent secrets to LLM 7.5 0.6% codewhale Sep 4 HIGH E CVE-2026-75857 CodeWhale: shell approval bypass via interactive tool 7.0 0.2% codewhale Sep 4 HIGH E CVE-2026-85673 LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind 7.5 0.4% llama-factory Sep 4 MEDI E CVE-2026-85670 tokenizers: malformed vocab crashes process (DoS) 6.5 0.3% tokenizers Sep 4 HIGH E CVE-2026-85666 OGX/Llama Stack: SSRF via MCP tool server_url 7.5 0.4% llama-stack Sep 4 MEDI E CVE-2026-72800 SiYuan: broken authz leaks DB schema & block IDs 5.8 0.2% github.com/siyuan-note/siyuan/kernel Sep 3 MEDI E CVE-2026-72805 SiYuan: auth bypass exposes private notebook content 5.8 0.2% github.com/siyuan-note/siyuan/kernel Sep 3 HIGH E CVE-2026-72810 SiYuan: WebSocket leak bypasses publish access control 8.6 0.3% github.com/siyuan-note/siyuan/kernel Sep 3 HIGH E CVE-2026-68586 SiYuan: missing authz leaks forbidden doc content via backlink API 8.6 0.2% github.com/siyuan-note/siyuan/kernel Sep 3 HIGH E CVE-2026-68587 SiYuan: missing authz exposes publish-disabled docs 8.6 0.2% github.com/siyuan-note/siyuan/kernel Sep 3 UNKN E CVE-2026-85063 csv-parse: CSV header triggers prototype pollution — 0.3% — Sep 3 CRIT E CVE-2026-71428 unstructured: SSRF via url= param exposes internal APIs 9.3 0.3% unstructured Sep 3 HIGH E CVE-2026-85178 Helicone: IDOR leaks cross-tenant LLM provider keys 7.7 0.2% — Sep 3 MEDI E CVE-2026-73846 ckan-mcp-server: cache key collision enables poisoning 6.5 0.2% — Sep 3 HIGH E CVE-2026-85211 Label Studio: org filter bypass leaks tenant storage 7.7 0.2% label-studio Sep 3 HIGH E CVE-2026-85179 Label Studio: SSRF via webhooks hits cloud metadata 8.5 0.2% label-studio Sep 3

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